diff --git "a/Notebooks/CodeForge.ipynb" "b/Notebooks/CodeForge.ipynb" --- "a/Notebooks/CodeForge.ipynb" +++ "b/Notebooks/CodeForge.ipynb" @@ -2,10 +2,21 @@ "cells": [ { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "e02e1b00", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "import os\n", "import cloudinary\n", @@ -27,10 +38,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "c11377c5", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "❌ Upload failed: [Errno 2] No such file or directory: 'c:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\python\\\\machine_learning\\\\Learning_Files\\\\ChirayuResume.pdf'\n" + ] + } + ], "source": [ "import os\n", "import cloudinary\n", @@ -179,7 +198,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "b010e49b", "metadata": {}, "outputs": [], @@ -189,7 +208,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "7164448e", "metadata": {}, "outputs": [], @@ -199,30 +218,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "6d1029c0", "metadata": {}, "outputs": [], "source": [ - "import cloudinary.uploader\n", - "import os\n", + "# import cloudinary.uploader\n", + "# import os\n", "\n", - "# Your resume path (using 'r' for raw string to handle backslashes correctly)\n", - "resume_path = r\"c:\\Users\\ATHARVA\\Downloads\\my codes\\python\\machine_learning\\Learning_Files\\ChirayuResume.pdf\"\n", + "# # Your resume path (using 'r' for raw string to handle backslashes correctly)\n", + "# resume_path = r\"c:\\Users\\ATHARVA\\Downloads\\my codes\\python\\machine_learning\\Learning_Files\\ChirayuResume.pdf\"\n", "\n", - "# Extract filename without extension for the public_id\n", - "file_name = os.path.basename(resume_path).split('.')[0] \n", - "thread_id = \"trial_thread_001\"\n", + "# # Extract filename without extension for the public_id\n", + "# file_name = os.path.basename(resume_path).split('.')[0] \n", + "# thread_id = \"trial_thread_001\"\n", "\n", - "# Upload directly using the file path\n", - "upload_result = cloudinary.uploader.upload(\n", - " resume_path, \n", - " folder=f\"threads/{thread_id}\",\n", - " public_id=file_name,\n", - " resource_type=\"auto\" # Handles the PDF correctly\n", - ")\n", + "# # Upload directly using the file path\n", + "# upload_result = cloudinary.uploader.upload(\n", + "# resume_path, \n", + "# folder=f\"threads/{thread_id}\",\n", + "# public_id=file_name,\n", + "# resource_type=\"auto\" # Handles the PDF correctly\n", + "# )\n", "\n", - "print(f\"Upload Successful! URL: {upload_result['secure_url']}\")\n" + "# print(f\"Upload Successful! URL: {upload_result['secure_url']}\")\n" ] }, { @@ -275,7 +294,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 3, "id": "b75a238a", "metadata": {}, "outputs": [], @@ -332,7 +351,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 4, "id": "7da5b1c6", "metadata": {}, "outputs": [], @@ -353,13 +372,6 @@ " description=\"Role title of the candidate. Example: 'Backend Intern', 'Software Engineer'\"\n", " )\n", "\n", - " experience_type: Optional[Literal['internship', 'full_time', 'contract', 'freelance']] = Field(\n", - " None,\n", - " description=\"Type of experience: internship, full_time, contract, or freelance\"\n", - " )\n", - "\n", - "\n", - "\n", " technologies: Optional[List[str]] = Field(\n", " default_factory=list,\n", " description=\"Technologies, tools, or frameworks used in this role\"\n", @@ -379,13 +391,6 @@ " \n", "\n", "\n", - "class CertificationItem(BaseModel):\n", - " name: str = Field(..., description=\"Certification name\")\n", - " \n", - " topics_covered: List[str] = Field(\n", - " default_factory=list,\n", - " description=\"Key topics or skills the certification covers\"\n", - " )\n", "\n", "\n", "\n", @@ -423,11 +428,7 @@ " default_factory=list,\n", " description=\"Projects with technologies used and what was built\"\n", " )\n", - " certifications: Optional[List[CertificationItem]] = Field(\n", - " None,\n", - " description=\"Certifications with topics they cover. None if not present.\"\n", - " )\n", - " \n", + "\n", "\n", "\n", " is_fresher: bool = Field(\n", @@ -440,6 +441,14 @@ ")\n" ] }, + { + "cell_type": "markdown", + "id": "2792c778", + "metadata": {}, + "source": [ + "remove certifications from schema" + ] + }, { "cell_type": "markdown", "id": "99ac1086", @@ -461,7 +470,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "id": "4b2441cd", "metadata": {}, "outputs": [], @@ -495,15 +504,7 @@ " )\n", "\n", "\n", - "class ConstraintItem(BaseModel):\n", - " type: str = Field(\n", - " ...,\n", - " description=\"Constraint type such as location, duration, eligibility\"\n", - " )\n", - " value: str = Field(\n", - " ...,\n", - " description=\"Constraint value (e.g., 'Pune only', '6 months', 'Fresher')\"\n", - " )\n", + "\n", "\n", "\n", "\n", @@ -518,36 +519,10 @@ " description=\"Company offering the job\"\n", " )\n", "\n", - " location: Optional[str] = Field(\n", - " None,\n", - " description=\"Job location if specified\"\n", - " )\n", - "\n", - " employment_type: Optional[str] = Field(\n", - " None,\n", - " description=\"Type of job: internship, full-time, contract\"\n", - " )\n", - "\n", - " duration_months: Optional[int] = Field(\n", - " None,\n", - " description=\"Duration of role in months (for internships/contracts)\"\n", - " )\n", - "\n", - " is_fresher_allowed: Optional[bool] = Field(\n", - " None,\n", - " description=\"Whether freshers are eligible for this role\"\n", - " )\n", - "\n", " skills_required: Optional[List[SkillRequirement]] = Field(\n", " None,\n", " description=\"List of required skills and expected levels\"\n", " )\n", - "\n", - " tools_technologies: Optional[List[str]] = Field(\n", - " None,\n", - " description=\"Specific tools/frameworks mentioned (e.g., Pandas, WordPress)\"\n", - " )\n", - "\n", " responsibilities: Optional[List[ResponsibilityItem]] = Field(\n", " None,\n", " description=\"Key job responsibilities\"\n", @@ -557,11 +532,15 @@ " None,\n", " description=\"General requirements like availability, qualifications\"\n", " )\n", - "\n", - " constraints: Optional[List[ConstraintItem]] = Field(\n", - " None,\n", - " description=\"Special constraints like location restriction, duration, etc.\"\n", - " )" + "\n" + ] + }, + { + "cell_type": "markdown", + "id": "64666596", + "metadata": {}, + "source": [ + "remove constraints" ] }, { @@ -574,7 +553,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 6, "id": "4f1341e0", "metadata": {}, "outputs": [], @@ -634,7 +613,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 7, "id": "18663bb3", "metadata": {}, "outputs": [], @@ -642,7 +621,7 @@ "class RoadmapStep(BaseModel):\n", " course_id: str\n", " title: str\n", - " reasoning: str = Field(..., description=\"Why this specific course was chosen for this user\")\n", + " reasoning: str = Field(..., description=\"Why this specific course was chosen for user\")\n", " is_foundation: bool\n", " sequence_order: int = Field(..., description=\"The order in which the course should be taken\")\n", "\n", @@ -655,13 +634,13 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 13, "id": "679a529f", "metadata": {}, "outputs": [], "source": [ "class SearchCourse(BaseModel):\n", - " query:str=Field(..., description=\"The skill to find with semantic terms (e.g., 'FastAPI', 'PostgreSQL', 'Docker','Enterprise VMS Strategy','Utilization Management')\")" + " query:str=Field(..., description=\"The skill to find with semantic terms (e.g., 'FastAPI','Utilization Management')\")" ] }, { @@ -682,13 +661,13 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 9, "id": "14dab004", "metadata": {}, "outputs": [], "source": [ "resume_agent=ChatGroq(\n", - " model=\"moonshotai/kimi-k2-instruct-0905\",\n", + " model=\"meta-llama/llama-4-scout-17b-16e-instruct\",\n", " temperature=0.2,\n", ")\n", "\n", @@ -712,13 +691,13 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 10, "id": "472dae2f", "metadata": {}, "outputs": [], "source": [ "jd_agent=ChatGroq(\n", - " model=\"meta-llama/llama-4-scout-17b-16e-instruct\",\n", + " model=\"openai/gpt-oss-20b\",\n", " temperature=0.2,\n", ")\n", "\n", @@ -742,13 +721,13 @@ }, { "cell_type": "code", - "execution_count": 80, + "execution_count": 11, "id": "0d5e3b17", "metadata": {}, "outputs": [], "source": [ "gap_analysis_agent=ChatGroq(\n", - " model=\"moonshotai/kimi-k2-instruct-0905\",\n", + " model=\"openai/gpt-oss-120b\",\n", " temperature=0.2,\n", ")\n", "\n", @@ -774,13 +753,13 @@ }, { "cell_type": "code", - "execution_count": 81, + "execution_count": 12, "id": "0ccc026b", "metadata": {}, "outputs": [], "source": [ "rd_planner_agent=ChatGroq(\n", - " model=\"openai/gpt-oss-120b\",\n", + " model=\"qwen/qwen3-32b\",\n", " temperature=0.1,\n", ")" ] @@ -795,7 +774,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 17, "id": "c8827093", "metadata": {}, "outputs": [ @@ -806,12 +785,12 @@ "Index ready: {'_response_info': {'raw_headers': {'connection': 'keep-alive',\n", " 'content-length': '187',\n", " 'content-type': 'application/json',\n", - " 'date': 'Tue, 24 Mar 2026 14:52:30 GMT',\n", + " 'date': 'Fri, 10 Apr 2026 05:48:34 GMT',\n", " 'grpc-status': '0',\n", " 'server': 'envoy',\n", - " 'x-envoy-upstream-service-time': '64',\n", - " 'x-pinecone-request-latency-ms': '67',\n", - " 'x-pinecone-response-duration-ms': '69'}},\n", + " 'x-envoy-upstream-service-time': '65',\n", + " 'x-pinecone-request-latency-ms': '64',\n", + " 'x-pinecone-response-duration-ms': '66'}},\n", " 'dimension': 384,\n", " 'index_fullness': 0.0,\n", " 'memoryFullness': 0.0,\n", @@ -829,7 +808,7 @@ "PINECONE_API_KEY = os.getenv(\"PINECONE_API_KEY\")\n", "pc = Pinecone(api_key=PINECONE_API_KEY)\n", "\n", - "index_name = \"final-catalog-index\"\n", + "index_name = \"final-courses-index\"\n", "\n", "\n", "# Create index if not exists\n", @@ -859,7 +838,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 18, "id": "7561b3a1", "metadata": {}, "outputs": [], @@ -888,7 +867,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 19, "id": "f0845a99", "metadata": {}, "outputs": [], @@ -898,7 +877,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 20, "id": "c8e6d2a5", "metadata": {}, "outputs": [ @@ -906,14 +885,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\ATHARVA\\AppData\\Local\\Temp\\ipykernel_7492\\2526755923.py:1: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the `langchain-huggingface package and should be used instead. To use it run `pip install -U `langchain-huggingface` and import as `from `langchain_huggingface import HuggingFaceEmbeddings``.\n", + "C:\\Users\\ATHARVA\\AppData\\Local\\Temp\\ipykernel_4264\\2526755923.py:1: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the `langchain-huggingface package and should be used instead. To use it run `pip install -U `langchain-huggingface` and import as `from `langchain_huggingface import HuggingFaceEmbeddings``.\n", " embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\", model_kwargs={\"device\": device})\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "86dbcd8effee4deaac275a8cd43f19c3", + "model_id": "284f4293bae24db185c91466f4a7e51d", "version_major": 2, "version_minor": 0 }, @@ -944,14 +923,14 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 21, "id": "6bc7292f", "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "2c3b9d66d82549a8bd12615b72b8732c", + "model_id": "8a451ea68a804344b31d09911a94ec1d", "version_major": 2, "version_minor": 0 }, @@ -978,7 +957,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 22, "id": "03c755a1", "metadata": {}, "outputs": [], @@ -1018,73 +997,31 @@ }, { "cell_type": "code", - "execution_count": 20, - "id": "9db28710", - "metadata": {}, - "outputs": [], - "source": [ - "import json\n", - "from typing import Optional, Dict, Any\n", - "from langchain_core.tools import tool\n", - "\n", - "class CourseLookup:\n", - " def __init__(self, catalog_path: str = \"course_catalog.json\"):\n", - " self.catalog_path = catalog_path\n", - " self.courses_map = {}\n", - " self._load_catalog()\n", - "\n", - " def _load_catalog(self):\n", - " \"\"\"Loads the catalog into a dictionary for O(1) lookup speed.\"\"\"\n", - " try:\n", - " with open(self.catalog_path, 'r') as f:\n", - " catalog = json.load(f)\n", - " # Key the dictionary by course_id for instant retrieval\n", - " self.courses_map = {course['course_id']: course for course in catalog}\n", - " except FileNotFoundError:\n", - " print(f\"Error: {self.catalog_path} not found.\")\n", - " except json.JSONDecodeError:\n", - " print(f\"Error: Failed to decode {self.catalog_path}.\")\n", - "\n", - " def get_course_details(self, course_id: str) -> Optional[Dict[str, Any]]:\n", - " \"\"\"Retrieves full details of a course by its ID.\"\"\"\n", - " return self.courses_map.get(course_id)\n", - "\n", - "\n", - "lookup_service = CourseLookup(r\"C:\\Users\\ATHARVA\\Downloads\\my codes\\web\\AdaptiveEngineService\\app\\tools\\Catalog.json\")\n", - "\n", - "@tool\n", - "def get_course_by_id(course_id: str) -> str:\n", - " \"\"\"\n", - " Retrieves full details for a specific course using its unique course_id.\n", - " Use this tool when you find a prerequisite ID in another course and \n", - " need to fetch its title, description, and duration to add to the roadmap.\n", - " \"\"\"\n", - " details = lookup_service.get_course_details(course_id)\n", - " if not details:\n", - " return f\"Error: Course with ID {course_id} not found in catalog.\"\n", - " \n", - " # Return a clean string for the agent to process\n", - " return json.dumps(details, indent=2)" - ] - }, - { - "cell_type": "code", - "execution_count": 21, + "execution_count": 23, "id": "09d238ab", "metadata": {}, "outputs": [], "source": [ + "from typing import Annotated\n", + "from langchain_core.messages import ToolMessage\n", + "from langgraph.types import Command\n", + "from langchain_core.tools import InjectedToolCallId\n", "\n", "@tool(args_schema=LearningRoadmap)\n", - "def submit_final_roadmap(candidate_name, target_role, roadmap, onboarding_summary):\n", + "def submit_final_roadmap(\n", + " candidate_name, \n", + " target_role, \n", + " roadmap, \n", + " onboarding_summary,\n", + " tool_call_id: Annotated[str, InjectedToolCallId] # Injected automatically\n", + "):\n", " \"\"\"\n", " STRICTLY call this tool to submit the final structured learning roadmap.\n", " This saves the data to the global system and the graph state.\n", " \"\"\"\n", " \n", - " \n", - " # Construct the structured JSON\n", - " result = {\n", + " # 1. Construct the structured JSON\n", + " result_data = {\n", " \"candidate_name\": candidate_name,\n", " \"target_role\": target_role,\n", " \"onboarding_summary\": onboarding_summary,\n", @@ -1093,58 +1030,90 @@ " for step in roadmap\n", " ]\n", " }\n", - " \n", - " \n", - " \n", - " # Return to LangGraph (will be stored in state via a post-processing node)\n", - " return result" + "\n", + " # 2. Return Command to update \"final_roadmap\" in state\n", + " return Command(\n", + " update={\n", + " \"final_roadmap\": result_data, # This updates your state key\n", + " \"messages\": [\n", + " ToolMessage(\n", + " content=\"SUCCESS: Final roadmap has been submitted and saved to state.\",\n", + " tool_call_id=tool_call_id\n", + " )\n", + " ]\n", + " }\n", + " )\n" ] }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 24, "id": "6ad04bc6", "metadata": {}, "outputs": [], "source": [ "\n", + "from typing import Annotated\n", + "from langchain_core.messages import ToolMessage\n", + "from langgraph.types import Command\n", + "from langchain_core.tools import InjectedToolCallId\n", "\n", "@tool\n", - "def submit_mermaid_visualization(mermaid_code: str):\n", + "def submit_mermaid_visualization(\n", + " mermaid_code: str,\n", + " tool_call_id: Annotated[str, InjectedToolCallId] # Automatically injected by ToolNode\n", + "):\n", " \"\"\"\n", " STRICTLY call this tool to save the Mermaid.js visualization of the roadmap.\n", " \"\"\"\n", + " if not mermaid_code:\n", + " return \"No Mermaid visualization found.\"\n", " \n", - " \n", - " # 2. Now this assignment updates the global variable\n", - " mermaid_roadmap_code = mermaid_code\n", - " \n", - " return \"Mermaid visualization saved successfully.\"" + " # Return Command to update the state key 'mermaid_code'\n", + " return Command(\n", + " update={\n", + " \"mermaid_code\": mermaid_code, # Updates your graph state\n", + " \"messages\": [\n", + " ToolMessage(\n", + " content=\"SUCCESS: Mermaid visualization saved successfully.\",\n", + " tool_call_id=tool_call_id\n", + " )\n", + " ]\n", + " }\n", + " )\n" ] }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 69, "id": "285f74bb", "metadata": {}, "outputs": [], "source": [ - "roadmap_planner_agent_tools=[search_courses, get_course_by_id,submit_final_roadmap,submit_mermaid_visualization]" + "roadmap_planner_agent_tools=[search_courses,submit_final_roadmap,submit_mermaid_visualization]" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 70, "id": "47564782", "metadata": {}, "outputs": [], "source": [ - "# roadmap_planner_agent=roadmap_planner_agent.bind_tools(roadmap_planner_agent_tools)" + "base_llm = ChatGroq(\n", + " model=\"qwen/qwen3-32b\",\n", + " temperature=0.1, \n", + ")\n", + "\n", + "\n", + "\n", + "\n", + "roadmap_planner_agent=base_llm.bind_tools(roadmap_planner_agent_tools)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "id": "c311f642", "metadata": {}, "outputs": [], @@ -1163,7 +1132,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "id": "7cfbfc3a", "metadata": {}, "outputs": [], @@ -1181,7 +1150,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 29, "id": "5deda2bb", "metadata": {}, "outputs": [], @@ -1214,7 +1183,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 30, "id": "c8df9934", "metadata": {}, "outputs": [], @@ -1228,19 +1197,6 @@ "You are a precise resume parser. Your only job is to extract structured information from a raw resume text.\n", "\n", "\n", - "\n", - "- Extract ONLY what is explicitly present in the resume. Do NOT infer or hallucinate missing fields.\n", - "- current_role: the job title stated at the top of the resume or most recent role. If the candidate is a student with no job, set it to \"Student\".\n", - "- is_fresher: set True ONLY if the candidate has zero professional work experience. Having projects or certifications does NOT make someone non-fresher.\n", - "- total_experience_years: total years of professional work only. Set 0.0 for freshers.\n", - "- skills: extract from the explicit skills section only. Do NOT pull skills from project descriptions here.\n", - "- experience: each role is a SEPARATE entry. Ignore company name. Focus on job_title, technologies used, and what they did or learned.\n", - "- projects: extract each project separately. Capture technologies and one line on what was built.\n", - "- certifications: extract ONLY if present. Set null if none found. Include topics the certification covers.\n", - "- achievements: extract ONLY if present. Set null if none found. Include the domain (e.g. Hackathon, Quiz, Competitive Programming).\n", - "\n", - "\n", - "\n", "\n", "Return a single valid JSON object matching the schema. No extra text, no markdown, no explanation.\n", "\n", @@ -1251,7 +1207,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 31, "id": "608efafd", "metadata": {}, "outputs": [], @@ -1291,29 +1247,23 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 32, "id": "8a6c1483", "metadata": {}, "outputs": [], "source": [ "gap_analysis_agent_prompt=\"\"\"\n", "\n", - "You are an expert technical assessor and the core intelligence of an AI-driven, adaptive onboarding engine[cite: 5]. \n", - "Your objective is to parse a new hire's current capabilities against a target job description and identify precise skill gaps to reach role-specific competency[cite: 5].\n", + "You are an expert technical assessor and the core intelligence of an AI-driven, adaptive onboarding engine. \n", + "Your objective is to parse a new hire's current capabilities against a target job description and identify precise skill gaps to reach role-specific competency.\n", "\n", - "\n", - "\n", - "Current corporate onboarding utilizes static, \"one-size-fits-all\" curricula, resulting in significant inefficiencies[cite: 3]. \n", - "Your ultimate goal is to solve this: you must ensure experienced hires do NOT waste time on known concepts, while ensuring beginners are NOT overwhelmed by advanced modules[cite: 3, 4].\n", - "\n", - "\n", "\n", "- Cross-reference the JD's `skills_required` and `tools_technologies` against the candidate's `skills_list`, `experience.technologies`, and `projects.technologies`.\n", "- Identify Hard Gaps: Technologies explicitly required by the JD that are completely absent from the candidate's profile.\n", "- Apply Adaptive Logic (Proficiency Gaps):\n", " - For Experienced Hires: If they possess the skill, DO NOT flag it for basic training. Only flag a gap if they need an advanced, role-specific upgrade based on low duration of use.\n", " - For Beginners/Freshers: Flag foundational gaps and prerequisites heavily to ensure they are prepared before tackling complex JD requirements.\n", - "- Keep skills atomic and highly specific (e.g., output \"FastAPI\" or \"PostgreSQL\", do NOT output vague terms like \"Backend Frameworks\").\n", + "- Keep skills atomic and highly specific (e.g., output \"FastAPI\" or \"PostgreSQL\", do NOT output terms like \"Backend Frameworks\").\n", "- Do NOT hallucinate requirements that are not explicitly stated in the JD data.\n", "- Do NOT attempt to build the curriculum or suggest courses yet. Your sole focus is diagnosing the gaps.\n", "- Provide a concise `reasoning` string for each identified gap. This reasoning MUST justify why the gap exists based on the user's experience level to prove the adaptive logic.\n", @@ -1328,7 +1278,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 33, "id": "059e5f86", "metadata": {}, "outputs": [], @@ -1341,18 +1291,12 @@ "\n", "\n", "STEP 1 — SEARCH\n", - "For every gap → call search_courses.\n", - "Use ONLY course IDs returned by the tool. Never guess IDs.\n", - "\n", - "STEP 2 — RESOLVE PREREQUISITES\n", - "For each retrieved course inspect its prerequisites list.\n", - "If candidate's resume does NOT prove mastery → call get_course_by_id for each missing prerequisite.\n", - "Skip courses the candidate already demonstrates via projects or experience.\n", + "For every gap → call search_courses.\n", + "Use ONLY course IDs returned by the tool. Never guess IDs.\n", "\n", "STEP 3 — SEQUENCE\n", - "Prerequisites always before target modules.\n", "sequence_order must be 1, 2, 3... strictly.\n", - "If is_fresher_adaptation_needed is True → add a professional fundamentals module first.\n", + "If is_fresher_adaptation_needed is True → add professional fundamentals first.\n", "\n", "STEP 4 — SUBMIT (TERMINAL STEP)\n", "Call submit_final_roadmap ONCE with the complete roadmap.\n", @@ -1360,39 +1304,33 @@ "After both return → STOP. Do not call any tool again.\n", "\n", "\n", - "\n", - "- gap courses → :::gap\n", - "- known prerequisites → :::known\n", - "- start node → :::start\n", - "- end node → :::done\n", - "- group by week using subgraph\n", - "\n", + "\n", + "Gap courses → :::gap\n", + "Start → :::start | End → :::done\n", + "Group by week using subgraph W1, W2, W3, etc.\n", "\n", - "\n", + "Example:\n", "flowchart TD\n", - " A([Start — Candidate's current skills]):::start\n", - " subgraph W1[\"Week 1 — Core gaps\"]\n", - " B[CS-DOCKER-101\\nDocker & Containerization]:::gap\n", - " C[CS-PY-101\\nPython Fundamentals]:::known\n", + " A([Start]):::start\n", + " subgraph W1[\"Week 1\"]\n", + " B[CS-DOCKER-101]:::gap\n", " end\n", - " subgraph W2[\"Week 2 — Role readiness\"]\n", - " D[CS-CICD-201\\nCI/CD with GitHub Actions]:::gap\n", + " subgraph W2[\"Week 2\"]\n", + " C[CS-CICD-201]:::gap\n", " end\n", - " Z([Role-ready — DevOps Engineer]):::done\n", - " A --> B & C\n", - " B --> D\n", - " D --> Z\n", - " classDef gap fill:#EEEDFE,stroke:#534AB7,color:#26215C\n", - " classDef known fill:#E1F5EE,stroke:#0F6E56,color:#085041\n", - " classDef start fill:#1D9E75,stroke:#0F6E56,color:#E1F5EE\n", - " classDef done fill:#534AB7,stroke:#3C3489,color:#EEEDFE\n", - "\n", + " Z([Ready]):::done\n", + " A --> B --> C --> Z\n", + " classDef gap fill:#EEEDFE,stroke:#534AB7\n", + " classDef known fill:#E1F5EE,stroke:#0F6E56\n", + " classDef start fill:#1D9E75,stroke:#0F6E56\n", + " classDef done fill:#534AB7,stroke:#3C3489\n", + "\n", "\"\"\"" ] }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 34, "id": "9c4dea1e", "metadata": {}, "outputs": [], @@ -1431,7 +1369,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 35, "id": "eb13ffc0", "metadata": {}, "outputs": [], @@ -1469,7 +1407,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 86, "id": "330acef6", "metadata": {}, "outputs": [], @@ -1524,7 +1462,7 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 85, "id": "7352181c", "metadata": {}, "outputs": [], @@ -1534,10 +1472,9 @@ " resume_data = state[\"resume_data\"] \n", " candidate_name = state[\"candidate_name\"]\n", " \n", - " # To remove noise and reduce size of the prompt.\n", + " # To remove noise and reduce size of the prompt.\n", " lean_resume_dict = resume_data.model_dump(\n", - "\n", - " exclude_none=True # Bonus: Automatically drops any fields that are None/null!\n", + " exclude_none=True # Bonus: Automatically drops any fields that are None/null!\n", " )\n", "\n", " raw_jd = state[\"JobDescriptionExtract_data\"]\n", @@ -1545,124 +1482,117 @@ " # Strip the HR noise and text bloat\n", " lean_jd_dict = raw_jd.model_dump(\n", " exclude={\n", - " \n", - " \n", - " \n", - " \n", - " \"responsibilities\": True, # Dropping verbose bullet points\n", + " \"responsibilities\": True, # Dropping verbose bullet points\n", " \"requirements\": True,\n", " \"constraints\": True\n", " },\n", - " exclude_none=True # Drops any null fields\n", + " exclude_none=True # Drops any null fields\n", " )\n", " \n", - " #Convert back to a JSON string if your prompt template requires it\n", - " \n", + " # Convert back to a JSON string if your prompt template requires it\n", " lean_resume_json = json.dumps(lean_resume_dict, indent=2)\n", - "\n", - "\n", " lean_jd_json = json.dumps(lean_jd_dict, indent=2)\n", "\n", + " # ============ DEBUGGING: Print received data ============\n", + " print(\"\\n\" + \"=\"*80)\n", + " print(\"🔍 SKILL GAP NODE - DEBUG INFO\")\n", + " print(\"=\"*80)\n", + " print(f\"✅ Candidate Name: {candidate_name}\")\n", + " print(f\"✅ Resume Data Type: {type(resume_data)}\")\n", + " print(f\"✅ JD Data Type: {type(raw_jd)}\")\n", + " print(\"\\n\" + \"-\"*80)\n", + " print(\"📄 LEAN RESUME DICT (before JSON):\")\n", + " print(\"-\"*80)\n", + " print(json.dumps(lean_resume_dict, indent=2))\n", + " print(\"\\n\" + \"-\"*80)\n", + " print(\"📄 LEAN JD DICT (before JSON):\")\n", + " print(\"-\"*80)\n", + " print(json.dumps(lean_jd_dict, indent=2))\n", + " \n", + " # ============ END DEBUGGING ============\n", + "\n", " messages = [\n", " SystemMessage(content=gap_analysis_agent_prompt),\n", " HumanMessage(content=f\"Users Resume:{lean_resume_json} Job Description:{lean_jd_json}\"),\n", - " \n", " ]\n", "\n", - " \n", " result = gap_analysis_agent.invoke(messages)\n", - " analysis_data = result[\"parsed\"] \n", - "\n", - "\n", - " task_message = HumanMessage(\n", - " content=f\"\"\"\n", - " Skill Gap Analysis Completed for {state.get('candidate_name')}.\n", - " \n", - " Gaps Identified:\n", - " {analysis_data.model_dump_json(indent=2)}\n", - " \n", - " Please proceed to search for courses and build the learning roadmap now.\n", - " \"\"\"\n", - " )\n", - "\n", - " return {\"skill_gap_analysis_data\": result[\"parsed\"],\"messages\": [task_message]}\n", + " analysis_data = result[\"parsed\"]\n", "\n", "\n", - " \n", - "\n", - " " + " return {\"skill_gap_analysis_data\": result[\"parsed\"]}" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 68, "id": "1fb2f0d1", "metadata": {}, "outputs": [], "source": [ - "# def roadmap_planning_node(state: OnboardingState):\n", - "# \"\"\"\n", - "# The agent's 'thinking' node. It looks at the Skill Gaps and \n", - "# decides which tool to call next.\n", - "# \"\"\"\n", - "# skill_gap_data = state[\"skill_gap_analysis_data\"]\n", + "def roadmap_planning_node(state: OnboardingState):\n", + " \"\"\"\n", + " The agent's 'thinking' node. It looks at the Skill Gaps and \n", + " decides which tool to call next.\n", + " \"\"\"\n", + " skill_gap_data = state[\"skill_gap_analysis_data\"]\n", "\n", - "# skill_gap_data= skill_gap_data.model_dump()\n", + " skill_gap_data= skill_gap_data.model_dump()\n", "\n", - "# system_prompt = SystemMessage(content=roadmap_planner_agent_prompt)\n", - "# input_msg = HumanMessage(content=f\" {skill_gap_data} \")\n", + " system_prompt = SystemMessage(content=roadmap_planner_agent_prompt)\n", + " input_msg = HumanMessage(content=f\" {skill_gap_data} \")\n", " \n", - "# response = roadmap_planner_agent.invoke([system_prompt, input_msg] + state[\"messages\"])\n", + " response = roadmap_planner_agent.invoke([system_prompt, input_msg] + state[\"messages\"])\n", "\n", " \n", " \n", - "# return {\"messages\": [response]}" + " return {\"messages\": [response]}" ] }, { "cell_type": "code", - "execution_count": 55, + "execution_count": null, "id": "cea90664", "metadata": {}, "outputs": [], "source": [ - "def finalize_state_node(state: OnboardingState):\n", - " \"\"\"\n", - " Final node that extracts structured data from the message scratchpad\n", - " and populates the main state keys. No global variables needed!\n", - " \"\"\"\n", - " final_roadmap = None\n", - " mermaid_code = None\n", - "\n", - " # We search the messages in reverse to find the LATEST tool calls\n", - " for msg in reversed(state[\"messages\"]):\n", - " # Check if the message has tool calls (this will be an AIMessage)\n", - " if hasattr(msg, \"tool_calls\") and msg.tool_calls:\n", - " for tool_call in msg.tool_calls:\n", + "# def finalize_state_node(state: OnboardingState):\n", + "# \"\"\"\n", + "# Final node that extracts structured data from the message scratchpad\n", + "# and populates the main state keys. No global variables needed!\n", + "# \"\"\"\n", + "# final_roadmap = None\n", + "# mermaid_code = None\n", + "\n", + "# # We search the messages in reverse to find the LATEST tool calls\n", + "# for msg in reversed(state[\"messages\"]):\n", + "# # Check if the message has tool calls (this will be an AIMessage)\n", + "# if hasattr(msg, \"tool_calls\") and msg.tool_calls:\n", + "# for tool_call in msg.tool_calls:\n", " \n", - " # 1. Extract the Roadmap JSON\n", - " if tool_call[\"name\"] == \"submit_final_roadmap\":\n", - " final_roadmap = tool_call[\"args\"]\n", + "# # 1. Extract the Roadmap JSON\n", + "# if tool_call[\"name\"] == \"submit_final_roadmap\":\n", + "# final_roadmap = tool_call[\"args\"]\n", " \n", - " # 2. Extract the Mermaid String\n", - " elif tool_call[\"name\"] == \"submit_mermaid_visualization\":\n", - " mermaid_code = tool_call[\"args\"].get(\"mermaid_code\")\n", + "# # 2. Extract the Mermaid String\n", + "# elif tool_call[\"name\"] == \"submit_mermaid_visualization\":\n", + "# mermaid_code = tool_call[\"args\"].get(\"mermaid_code\")\n", "\n", - " # Once we have both, we can stop searching\n", - " if final_roadmap and mermaid_code:\n", - " break\n", + "# # Once we have both, we can stop searching\n", + "# if final_roadmap and mermaid_code:\n", + "# break\n", "\n", " \n", " \n", - " return {\n", - " \"final_roadmap\": final_roadmap,\n", - " \"mermaid_code\": mermaid_code\n", - " }" + "# return {\n", + "# \"final_roadmap\": final_roadmap,\n", + "# \"mermaid_code\": mermaid_code\n", + "# }" ] }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 71, "id": "ba9f22e1", "metadata": {}, "outputs": [], @@ -1672,39 +1602,44 @@ }, { "cell_type": "code", - "execution_count": 87, + "execution_count": 72, "id": "668b6787", "metadata": {}, "outputs": [], "source": [ - "from langchain.agents import create_agent\n", - "from langchain.agents.middleware import ToolCallLimitMiddleware\n", + "# from langchain.agents import create_agent\n", + "# from langchain.agents.middleware import ToolCallLimitMiddleware\n", "\n", "\n", - "plan_agent=create_agent(\n", - " model=rd_planner_agent, \n", - " tools=roadmap_planner_agent_tools,\n", - " system_prompt=roadmap_planner_agent_prompt,\n", - " middleware=[\n", - " ToolCallLimitMiddleware[Any,None](\n", - " tool_name=\"search_courses\",\n", - " run_limit=4,\n", - " thread_limit=10,\n", + "# plan_agent=create_agent(\n", + "# model=rd_planner_agent, \n", + "# tools=roadmap_planner_agent_tools,\n", + "# system_prompt=roadmap_planner_agent_prompt,\n", + "# middleware=[\n", + "# ToolCallLimitMiddleware[Any,None](\n", + "# tool_name=\"search_courses\",\n", + "# run_limit=4,\n", + "# thread_limit=10,\n", "\n", "\n", - " )\n", + "# )\n", "\n", - " ] ,\n", - " )" + "# ] ,\n", + "# )" ] }, { "cell_type": "code", - "execution_count": 89, + "execution_count": 75, "id": "b5cfe4c3", "metadata": {}, "outputs": [], "source": [ + "from langchain.agents import create_agent\n", + "from langchain.agents.middleware import ToolCallLimitMiddleware\n", + "\n", + "\n", + "\n", "builder = StateGraph(OnboardingState)\n", "\n", "# Define Nodes\n", @@ -1714,13 +1649,11 @@ "builder.add_node(\"skill_gap_analysis\", skill_gap_node)\n", "\n", "# The ReAct Agent Node\n", - "builder.add_node(\"roadmap_planning_agent\", plan_agent)\n", + "builder.add_node(\"roadmap_planning_agent\", roadmap_planning_node)\n", "\n", "# The Tool Execution Node (Required for the loop)\n", "builder.add_node(\"tools\", ToolNode(roadmap_planner_agent_tools))\n", "\n", - "builder.add_node(\"finalize_state\", finalize_state_node)\n", - "\n", "# 5. Define Edges and Workflow\n", "builder.add_edge(START, \"input_node\")\n", "builder.add_edge(\"input_node\", \"resume_data_extraction\")\n", @@ -1736,10 +1669,10 @@ "# Agentic ReAct Loop\n", "builder.add_conditional_edges(\n", " \"roadmap_planning_agent\",\n", - " tools_condition, # Built-in: routes to \"tools\" if the model calls a tool\n", + " tools_condition,\n", " {\n", - " \"tools\": \"tools\",\n", - " END: \"finalize_state\" # Routes to finalize if the model gives a final answer\n", + " \"tools\": \"tools\", \n", + " END: END\n", " }\n", ")\n", "\n", @@ -1752,15 +1685,15 @@ }, { "cell_type": "code", - "execution_count": 84, + "execution_count": 76, "id": "53588a77", "metadata": {}, "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAawAAAKOCAIAAAB1JrpbAAAQAElEQVR4nOzdBWATZx8G8PeSutLS0pYipbgXZ8CA4TYKw12HDmfocNfBkAGDb/iAAcOGjgEb7gyH4las7m1y3z+5EtI2SdM2SXPp8/v4uuQsl8vdk1cud1Y8zzMAgJzKigEA5GAIQQDI0RCCAJCjIQQBIEdDCAJAjoYQBIAcDSFoMM/uRt6/GhXyJlEm4+UyJpfxUitOlsRzEsZ4JpFK5HI5L6cJORrC8fRfJpye9OksJU4x3Sccp/g/L+etrCRJSbwwSjGQp1l5iZSj5WuYh1e8nPJVPo9SDZFIOFoF9XW2smE2NhJ7F6lvIfsK9dwZQM7D4TzBLPrvTOi1E+FRoUkUNBIrZm0jsXOUUHgxuYSTMl7GhBBkysdMmX2KsKI/9Jcmo6ySC2nFc0I2KlKOS55MzqTWnCxBrsy/5NykRxIphazw+qoATQ47VeR9ClohGxlTS0MVqbViQGKsPCFOLpMxW3sufzGHxt19GECOgRDMvJtnw87t/5CUxHL7WAfUzVW8oisTs6jwhNP7Pr64G5uYIPctah/Y35cB5AAIwUzaNOtJZJiscHnHxl0trdz06GbEyZ0fkuLlrQb7euW3ZwAWDSGYGctHBrl7WXUe68cs15k/313/O6JsLZfarfMwAMuFEMywlaOCAr5yrNEiRzScrfw+qOW3PvmKOTIAC4UQzJiVo4PqdfYsIfLmvwxZNTaoWAWneh29GYAlkjDQG8VBxfquOSoByYB5Re5fibp1PowBWCKEoL62zH3q7GZVvakny3kad8vzz84PDMASIQT1cu9qRNj7pC7j/FiO5F/OJZeHFX0NMACLgxDUyz873vmXcWA5WOdxfqHvkiI+xDEAy4IQTN+j6xGJiaxpr7wsZ8vlab1/7VsGYFkQguk7dyjE1QM/smZVm7qFf0hkAJYFIZi+iI9JZWuZukd43Lhxe/fuZRn06NGjFi1aMOMoFuDCcezqiY8MwIIgBNPx8U2sXM7Kf+nGTOvOnTss4zI3l/4cXKSPbkQzAAuCk6XT8c+ud3cvRfafW5gZx5kzZzZu3Hj79m0PD4/y5csPGTKEHlSuXFkY6+TkdPLkSSrf7dy589KlS69fv/b392/VqlXbtm2FCerXr9+3b9+///772rVr3bp127RpkzB8xIgRXbp0YYa2d83L0DeJPacUYgCWAk1d6Qh7n2hjxzHjuHfv3rBhwwYMGDBt2rTHjx8vW7Zs6tSpy5cvp2SsWbPmpEmTAgMDabJFixZR/E2cOJHjuKdPn86bN8/Hx4cmoFHW1tZ//PFH1apVKQorVapEExw9evTAgQPMONw9bN4+iWcAFgQhmI74BLlUaqxGg+vXr9vZ2fXu3VsikXh7e5cqVSooKCjtZHPmzImOjs6bV9E9TYXEffv2nT17VghBSj1XV9fRo0czk3B2txYu5gpgMRCC6eDkwhVLjSIgICAuLm748OHVqlWrXbt2/vz5VRVhddRksW3bNioePnv2TBji6/v5Yn8UncxUKP/kyECwLOgYSYeVLSdLNNZxX6JEiZ9++snT05Mqwq1btx40aNCNGzdSTSOXy6nKTA2C33333YkTJy5fvkxNh+oT2NjYMFOJCk+SYJcBy4I9Oh1UAUyIlzOjqVGjBrX97d+/n1oDw8PDqVSYlJSkPgG1G1K3CXV0fPXVV87OzjQkMjKSZZPQ4AQpKg9gWRCC6ShS3iEx3lglwStXrlDrHj2gwmCLFi1GjRpFAffmzRv1acLCFJdvyZMn+cqmj5VYNgl9G+/gghQEi4IQTEfBEs7UJnjvslEuJEWV3zFjxuzevTs0NPTWrVvU8EdpSD2/tra2lHrnz5+nym+BAgWsrKw2bdoUERFBXcMLFiyoXr16qqBUoYk/fPhw8uRJVeuhYUWFy/1K4oL7YFEQgulzdJXc+CecGUHXrl2pKXDhwoUNGzbs16+fo6PjmjVrKPJoFHUZUzsglQ2p83fmzJk3b96sV68eVYoHDx7ctm1bSkzVqYLqatWqRZ0t1Fl85MgRZmjvXsbxclazpRcDsCA4WTp9V0+EnNsfMnhxEZazbV/8PDZShjOlwcKgJJi+il+5cxJ2atd7lrN9eJlQ+xsPBmBZ0Mitl4Dartf/Ca/TRvNlpanvolWrVhpHOTk5RUVFaRzl7+//v//9jxnHeiWWwVWi2jRVvTWO+n3pcxsH5l/WmQFYFlSH9bV20mMPH5tWg/KlHUXbUFusJCQkaDuPj+M4yiNmHPHx8fTSLIOrRM2R9vYa+j0SYxNXT3j23Y85vUEALBJCMANWjApqNcjHt3COu//k6nFBRQKc6uOGc2CJ0CaYAd9857335zcsh/l16iM3LxskIFgqlAQzJiIkYePM591/KODibrofq2Wj1eODyn2Z64tm6A8Bi4UQzLB3L+N2LHpZrKJjo24+zHJ9fBO/c+lLdx/rdsMKMADLhRDMpDXjH0msuDptPYqWd2EWZ8eS5+9fJJSv41qrZU68zzLkKAjBzDu0/vWTWzHWtpIi5R2/am8Jv6O4eyn82t9hoe8SXT2kXcfjpGjIERCCWXXw19evg2LjYnipFWfvLHHOZW1tx2xtrVJee5RXXZWQ45iwyTkJ4+VMImFy1UVqOMVEyWMV/02eRcIpruLHKZ+pPi7l3JxygfQZcuqzSCVMlvLCN5wwEZd64bTg+Dh5fLQ8KjwpIU5Oq5krj3WTnt5unrYMIGdACBpGVEjChaMhwc/i46JlCbFyTsLxajHEKVMwFSGSJFIml6kmE4JKeMIzXpWbio+J5+UcJ1GbPfmzU8Yjrz6LRMolX//505DUK/DpuZWthBLWxp5zy2NdpIJTiUqmvqkeQLZDCIpG+/bt58yZU7iwsW75BJAz4WdzopGUlCRcYAYADAgHlWggBAGMAQeVaCAEAYwBB5VoJCYmWltbMwAwKISgaKAkCGAMOKhEAyEIYAw4qEQDIQhgDDioRANtggDGgBAUB5lMJpFIOI5jAGBQCEFxQF0YwEhwXIkDQhDASHBciQNCEMBIcFyJA3pFAIwEISgOKAkCGAmOK3FACAIYCY4rcUAIAhgJjitxQAgCGAmOK3FACAIYCY4rcUAIAhgJjitxQAgCGAmOK3FACAIYCY4rccDJ0gBGghAUB5QEAYwEx5U4cBzn5ubGAMDQEILiQCH48eNHBgCGhhAUB6oLU42YAYChIQTFASEIYCQIQXFACAIYCUJQHBCCAEaCEBQHhCCAkSAExQEhCGAkCEFxQAgCGAlCUBwQggBGghAUB4QggJEgBMUBIQhgJAhBcUAIAhgJQlAcEIIARoIQFAeEIICRIATFASEIYCQSBmIglUrlcjnP8wwADAohKBooDAIYA4fChZkLCAiQSD5/V3Gc4iPr3r378OHDGQBkGUqC5s7f31+ihkLQz8+vc+fODAAMASFo7tq0aaNeEiR169bNkycPAwBDQAiau06dOuXPn1/1NG/evK1bt2YAYCAIQXNHxcCOHTva2NgIT6tVq6aeiQCQRQhBEWjXrl2BAgXogZeXFwUiAwDDQe9wahePfgx9lyj7dC4KxzH1LaR8xnHJ/0keRQ8UeI5nyZNKpEwu/zwndWfQKNVyaHpahFyeYstLJUwmT/GiUimTyZKHvHnz5u7dOx65PcqVL68+l+KlVa/6iYRTDEmx2p9WWLkWXKq3pnjAkp+kfr/KadXfbIp1lnK2DqxGMzcbexsGIE4Iwc8o/i4dDZVaMSsrSUJc8mZRBgRTxQwnYbxc9Zfj5UJwUKopIlAVaxIpx+T09FMISpQh+Cnj6ClNL/8UcJ8ij5PJePUhiiSVfV49WoJUQtH5eYgioTjF/1LlqUSZgnK1T/ZzarPPYSa8C+UDjvs0vXAKjvqM9I9eVFsIclI+MZ53y2PVeawfAxAhhGCyW+fC/939vlY7T7/irgwyaPvioFxuNm2HF2AAYoMQVLh1IeTfXSFdJxZhkFl/LH8qsWZdx/gxAFFBx4jCpcOh3gVtGWRB8355w4KTZDIZAxAVhKBCfDTvH4BacJbY2NhY2bDzh0IYgKjgUloKSYnMwcGaQRbxkthIOQMQFYRgMh4Hb5ZR7zYv5xiAqCAEwXB4xtDNBmKDEATDUZz/yADEBSGooDxLmEFWyXmUBEF0EIIKigDE0ZtlHMdzEmxHEBmE4CcoCWYZz3PoGAHRQQh+ghJMlnGM55CBIDYIQQVedSUYyAI++WoTAGKCEFTgGMNPqLNOwvATJBAfhCAYDM8YrscBooMQTIbqcNYlX94QQFQQgslQgsk6xS8PsRlBbNCEo5B86Xm97dq9rX7Dqkz8liyd26tPe2YoOFcaRAghqKDx2vE6lCpZplvXvsw4pk0fd/DQXgYAJoHqcGaULFmG/jHjuH//TpUqXzARUtyphENZEEQGIZgZVB1e+fPi48cuMmXBjeO4BvWbzp0/NTY2plSpsgP6DRMiskXLOp079aJQ++ffvx0dHcuWrTBh/AxnJ2ca1bR5rR7d+3Xs0F1Y4PwF0x89erB61eav6lempwsWzvh51Y/7957UsQ46Xpds3LT2yNEDHz68y5PHO6B8pRHDx0skilJ/TEzMrDk/XLt2qVChIoFft1VfYFJS0rr/rTx/4fS7d8FlygS0DmxfvXotlhE8rzhdmgGICqrDyTLdO2xlZXX7zn/H/jq46udNh/48bWtjO2feFGGUVGr1+84tLVp88/dfl+bPXf78+dNlyxfoXtrhg2fo7/ejJ+lOQN2v++v6VXv27hjYf/jO34/06T3o5KljtBrCqIWLZrx8+Xzhgp9nTFv45OkjijzVAn9aNn/nrq2tW3XYumV/ndr1p0wbc+qf4ywjFDErRQiCyCAEk/FZOLcjNibm+9GT8/r4UjDVr9fkxYtnVOASRhUpXKxK5epUZKOSWmDLtidPHktMTGQGovF1I6Mif9u2gZosa9WqS6XOunUaUK5t3rKOXvfDh/cnTh7r1LEHtWm6u+fu32+ora2dsKj4+HgqOXbu1LPl121cXVybNQ2kBW7c9EtGVkdxZ87P904GEAmE4CdZOEcmfwE/BwcH4bGTsrYbGRkhPC1SpLhqMt+8+SmJXr9+yQxE4+tSFNKrqDdZFitWMioq6tWrF2/evKKnBQv6q0YVL15KePDgwd2EhIQqlT+3RVIl+vHjoNjYWKY3xdcIzrcEsUGboAEIzW0aqYpaxM7env5GR0cxY75uSMgHxWupva69vSIoqd0wPCKMHjjYO3weZWcvPIiKiqS/Q4b1SbW0mJhoe3t7ph/1u9QDiAVC8BPjlGDUIy9OWaqys9OQKTK5we5U6ejoRH9j4z6X4CjI6K+7uwd1fShWIz4u1SiS28OT/o4aOdHXN7/60pydXRiARUMIfmKcIsyNG1dUjx8G3afGOyFlbGxsqWimGkV1WGYghQsXk0qlt2/fKFmitDDk7t1b1Djo6ZlHKDneunWjeLGS9IBqzZevXMiVy40e5/MtYGurthY7nwAAEABJREFUuPNyhYDKwlyhoSE8z9vY2Oj9ytQRxEmkDEBc0CaokNFfjOjv/Yd31DMrk8moa/jAn7u/+qqRkDXUT0J9r9RUR483bV734cM7YXoaS2l1+fL5a9cvCwW3jHJxdmnYoNnmLf87e/afiMiIo0f//GPP9rZtu1AC0pLLlCm/fv0qylzqCZk5ayL36W1T22LPHv2pJ+TmzevUOEjrNnrMoCVL52bklRV3m5Pj3usgNigJKmT0FyP6a9G89e3b/638+Ud6XLFClSHffS8M/27w6EWLZn4dWJfKhh3ad6Ou2KtXLwqjunTu/ev6VRcvnf1t6wHhpMKMGjxoFEXejFkTKEbz5s3XuVMv6hEWRo0fN33Jkjn9BnShYmCTxl9TL/DpMyeFUR07dKdS5NZt62lNqE5dulS5UaN+YACWjsO1j8jyEUGNuvr6FNG3B0BPga3rt/mmU/duxvqBnbnZNPNRsQpODTp7MQDxQElQBed2ZBUvZ7jHCIgOQlDF7ErEX7esq23U2LFTa9Wsy8yMhMNXCYgPQlBBed9hwx++e//I2M/OUlmzZqu2UW653Jn5UWQgbrkJYoMQVFDed9jsjl4f77xMVGQ842UoCoLIIAQ/wcELkCMhBD9BNS7LFBfSwomnIDYIQTAYxSVVcREZEBuEIADkaAhBBSq/4BJQADkTQlCBWrJ49IxkmUTCXbl68d8HF2vUqFG9evVcuXIxALOHEPwEPx/MMrmcL1s2gOXh/v333wULFnh7e3+hVKlSJQZgrhCCYEg21jYNmyvQ43v37p07d2716tU3b94U0pCKh/nz52cA5gQhCMZSQqlXr14JCQnnlLZs2cLzPEWhUF8WrioGkL0QggoSa04mwZXwssrKlpNaa2hVsLGxqaNEj1++fHn+/Pm9e/eOHz++dOnSFIVUQixVqhQDyCYIQQWphH//PDafvxODLJAlyH387XRPky9fvrZK9Pjq1asUiHPmzHn16pWqeOjh4cEATAjXE1TY9dPzqHDZN0MLMcism2dCbp4K6T+vCMu48PBwSsOzZ8/SXzc3N6F4WK1aNQZgfAjBZKvGBXkXsq3fEc32mbRpVlC1pm6VvsrNsubhw4cUhdSAeOnSpS8+8fPzYwDGgRD8bN2kIImE8yvj5JHXkZNoOG2QV15mgWc8l/KkQu7zKM2UV+/nkmf+fK2GTw9TziksX32YcAsUPuVFHtLeF4WeydWmESZQLIdT3Q2T41nyolXL/7TsFCuTvMIs9dqlWgfaeyLCEl7cj37/Kr7L9765vAx5aW65XH7uk7i4OFV92dHRkQEYDkIwhd3Lnn94kyhL5GU67nHEG/eSM5m+61PGZtScwKnHpn7MlJnKJc8hkTCJlDm6Sht29fQuaMQW1eDgYFV9uXDhwkLxsGzZsgwgyxCCRnH69Only5dv27aNgaH9999/QvHw8ePHquKht7c3A8gUhKDh7dq1659//lm6dCkDY4qOjlYVD+3t7YWTsemvcHtlAD0hBA1sxYoV1Nc5YcIEBib05MkTKhsKPSpVqlQR6stFimSmqxpyGoSgIU2ePJn6MXv37s0g+1y4cEGoL4eFhanqy66urgxAE4SgwfTv379ly5bCz2bBHHz48EFVX86bN69QPKxYsSIDUIMQNIzAwEAqBuJyKWbr7t27QvHw9u3bquJhvnz5GOR4CMGsCgkJadas2c6dO3FEiUJ8fLyqeEhPVedj29jYMMiREIJZQuWLoUOHHjx40NramoHYvHz5UnU+dtmyZYXO5ZIlSzLISRCCmXfy5Mm1a9du3ryZgfhduXJF6Fx+8+aNqr6cO3dWfwUI5g8hmEnbt2+/ePHiokWLGFgW6lNW1Zfd3d2FynLVqlUZWCiEYGb89NNPcXFxY8aMYWDRHj58KFSWqZyoKh7iag4WBiGYYRMmTChevHiPHj0Y5BgymUxVPKTvP1V3ioODAwORQwhmTJ8+fdq3b9+4cWMGOVVwcLCqO6Vo0aLCz/VwNQfxQghmQIsWLWbOnBkQEMAAlG7cuCH8XO/Jkyeq+rKXlxcD8UAI6uX9+/fNmjXbt2+fj48PA0gjKipKVV92dHQUzrYhHGfMy66BISAE03fr1q3Ro0cfPHgQlycBfTx+/Fg424ZQt7JQPMTVHMwWQjAdx48f37hx44YNGxhAxl24cEEoHoaFham6U1xcXBiYDYSgLlu2bKFGn/nz5zOArPnw4YOqOyV//vxCfblChQoMshtCUKvFixfT35EjRzIAg7p9+7ZQX757966qO8XX15dBdkAIajZmzJjy5ct36dKFARhNXFycqjtFKpWqulPwU3RTQghq0KNHj+7du9evX58BmMrz589V3Sn0BSycfliiRAkGRoYQTEEulzdr1mzhwoVlypRhANnkypUrQvEwODhY1Z3i7u7OwAgQgp+9efOmZcuWBw8e9PT0ZABmgPqUVd0ptFsK9eUqVaowMByEYDKqjAwaNOjAgQMMwCzdv39fqC9fu3ZN6E5p2LAhiodZhxBUoO/b0aNHr127lgGYvaSkJKE7hXqZV6xY4eRkxNve5wT4CYRCYmLiy5cvGYAYWFlZ1apVa8yYMR8+fIiKimKQNVYMlHsVfbsyAFHBfmsQCEEF7EwgRthvDQIhqICdCcRIKpXKZDIGWYMQVEAIghhhvzUIhKACdiYQI+y3BoHeYQWO4yQSCWoWIC4IQYNACCbD/gSig53WIBCCybA/gehgpzUItAkmw/4EooPeYYNACCZDCILoYKc1CIRgMuxPIDrYaQ0CIZgM+xOIDnZag0AIJsP+BKKDndYgEILJsD+B6GCnNQiEYDLsTyA66B02CIRgMoQgiA52WoPI6VeWrlChgvCbOblcTg/oLw0sXbr05s2bGYBZ+uqrryIjI6kMSHusamDevHlxc4jMyem/GClWrJjwgHKQdimqXzg5OXXv3p0BmKtatWrRtzXtqxI1jRs3ZpApOT0EKe8cHR3VhxQoUKBRo0YMwFx169bNx8dHfUi+fPk6dOjAIFNyegg2b97cz89P9dTW1hY7E5g5qr5UrlxZfUjNmjXz5MnDIFNwAQXWu3dvBwcH4TF9wbZs2ZIBmLdvv/2WSn/CYy8vr/bt2zPILISgopm5SJEiTNnX1q5dOwZg9igBqWVQeFy1atWCBQsyyCy9TpF5cjdCnijVMYGij1mtoyrNWMZz2uflmI4OagnPy7UvmdGMOkbSOnE6+r4/z9ym6eD40K0O9g7lizR+9F+07nl1v1kdq6R8o5y2dWValskpF6lhDo5pW0GNc9CH4OQs9S5kz8Tj0Y1wxmnbRT9vaOX+peEx/UeuZZT641RLU+GSh6b81D7tzZ+2cooZUy021ULTvGj60q6Wakjdqp3uXglNSkz6qlonYafVMau2vSidQygVzUdy8hJSvYSE8XLNS9b6ijyn+B8zIHlS/uL2NvY2uqdK5xSZbQuehLylnngm03k2kiIwtC+Hk3K8LLNjJRwv15GRHJNncl6JlJPrel3FZ6hlnNYdSjlWa6jreKc634dm2tZf6+tLFPuw1Jr5lXZo0j0vM2/rpz+OCpNLrZgsMXmI9q8JfY9j9cl0LC0DS8noxDoiTRvdZQTVYjL7djTPqG2tNA3P6Nd35lY1c3PR/kOHlZ09Fzggr4ev1q9/XeG1ef7jhGj5l629vAs5M7AId86HXjn2sWJ9l+pNzbcdfdXYoNw+NvW6eNvY2DCArPl39+vHN2N6Tino5GqtcQKtIbh+2mOpDWs1yJ+Bxdk6Lyivn+3X/fIz8/PzmKAyX7oE1EZfJxjShmlB/WYV0Fg11twxcvtcaFy0HAloqeq08X7xMJ6Zn32rX9raS5GAYHCevrbbf3ytcZTmELx7McLOCR3HFsu3iBO1sFw98Z6ZmXcv4zzyowoMhlcowCEyRHPPhuaki4/jpFa4toIlk0ol4R/kzMzIEiX29tYMwNA8fJ21dX9oTrqkBDkvN2hfNZiZRMVHbHaF/aREuQw7HhgBl8R4LVcdQ3EPAHI0hGAOJZFyEvNr9eUyejIxQJZpDkE6QnL2ZQYtn1zGy8yuSZApr2fGAAxP+36lOQTpCOF57IyWjL7npFJmbmQyXo5vXzAGXvk/TTTXiCQc0/nTMBA9RUkQd6eAnERbW4uWNkGOQ7XEsila38zvE0abIBiJjjKd5hBU/JYOBUGLxjPGmd9HrEhmpCAYgY7dSlsIIgMtnOKaMhKz+5DlPNoEwTgy2jECFo9nhr52G4A50/7lihDMoRSFfTOsDkvQKAhGodjZuYz0Diuu8IoKsWUzz6zhccMHMArlCS+ad3otp8jYcFbSjO2Nga3rb9y0Nu3wsLDQr+pXPnHyGMsImp7monlZDrNr97b6Dasy0zC/HORzcJvgkqVze/XJifdL0hYdhqWjw01z0skS5TJZxnbGDu27lStbgZnWkyePOnZuwUzL4C/6x54dc+ZNER6XKlmmW9e+zAR4cywL0p4qQXVYp2nTxx08tJeZlvouahDq78I00cGboE2wc6eezOTuP7jDTM7gL3r//ucFlixZhv4x41Pcu4KZHR4nyKSH9pYqVb5gpqW+ixpqgap3kS3Roc5gIUhl2jbfdOreTVGKOf73kV9//TkiMqJGjdod2nXTcwmrVi89euxPB3uH+vWb5MtXUDU8Kirq952bL1469/Tpo9zuHjVq1Onda6Cdnd2v61cJpWiqOA8aOKJd2y67/9h+/vy/d+/esrG1LV+uYp8+g33z5kv3dW/f/m/DxjX37t12zeX2RfUve3Tv5+jo+Or1y1692w3oN+ybbzrSNNHR0V26Bdar19jZyVn9RStVrNbn245zZi1ZuHhmrlxua9f8RuXEfft3Xr12KTj4tV9B/2bNWgW2bCu8kEwm+33nFnotpijxle3Zo3/ZsgHDR/a7ceMqDTl69M/VqzbfvHl95c+Ljx+7KMxCr3Xk6IEPH97lyeMdUL7SiOHjJRIJvUTvvh1Wrtiwdeuvp8+c9PTM81XdRv2+HSLNyO/gzLNjhMkzVh1+/Dgo1fZPSkpa97+V5y+cfvcuuEyZgNaB7atXT7415fPnT2mfuX7jClW6S5cu17F9d9r+NLxp81r0oXfs0F2YbP6C6Y8ePaDPgh63+qYBfUwvXz7ftfu3XMrd47vBo2fPnXTmzKn8+Qt27dy7UaPmwlyHj+zft3/XkydBhQoVqfdVIzoW0j3jMSYmZtacH65du0SzBH7dVn2Utr2I9jr6u2DhjJ9X/bh/70lth4bu19W2iY4dOzh3/tTVP28uUqQYPb1z99bg73pOmzp/9x/bUu2iW3/7lXbFKVPHtGrVfsjg0efO/fv3iSP/3bwWERFeskSZbt36VghIvjc8hcDq1Uup0OfqmqtypWrf9h3i5eWd6l2oRwdtk8VLZl+/fjkyMoLeeNOmga0CFXfBpaLops1rlyxeM2XamKdPH/v7F6HjvUnjr5khSLQPzeQhQl/06hgAABAASURBVPvlrNk/NGrUYvOmPY0btVi2fIE+c+3dt3Pvvt+HDR27cuVGHx/fjZt+UY2iz2Drb+upzDx71pL+/YedPHVMyJFePQfQjkvb9MTxy7RF6LOh1ypduvz06QvHjZ0WGhpCq5Hu67589WL0mEFx8XHLl/06Y9rCx48fjhjZj/YSSk86MNb9ulJol6QHTo5O/b8dmupFra0VVwDduHktrd6okYqXW7Fy0aVL5+iNzJ3zE+27S3+ad/7CGeG11vyybO/e36dPW/jDhFmenl5jxw+hw5I+Vyr60bFECyxWtIT6utERu2fvjoH9h+/8/Uif3oPojVOG0nDhRRctnknfFkcPn5s4fuaO3zdntNVV8dth8+uDUFzbJiO/aE67/X9aNn/nrq2tW3XYumV/ndr16Zg59c9xGp6QkEDfN/Q9MW/uskULfraSWk38YURcXFy6y9+2fUOBAn5HDp3t22fwocP7aPeoX6/JsSPnv6rbcMGiGZFRkTTZX8cPz5s/jT6+rZv30WS0AstXLkpv3dnCRTMoXhcu+Jl2vCdPH1EqqUZp24sOH1T8/X70JMoOpv3Q0E3bJmrYsFmlilVpv2LKxll60KB+k9pf1ku1i9rY2MTERO/bt3P8uOkUoLQNKcrj4+PpoKPVoG1FGzYk5CNTpu248UM/fHy/eNGqId99/+7923EThtLAVO9CHU3w+vXLGdMX7dh2sHbt+vTG7967LXwQUVGRtObfj5r091+X6tRuQN9Vb98GM0PQUhKUcJn+OQFlmVcebyHX6QuBNse165fTnYs+Tnpj9JHQYwp4Ks3R/iGMat+uKw0vWLCQ8PTWrRsXL53t329oqiWUKlX213U78uUrYKW8JnZSYuKEH0aER4S7urjqeN2//jpkbWVNeyF9U9HT0aMmderyNRWv6tZpQGH31/FDP69e0rljT/rIf1q6ztbWNtXswrd9lcrVKRCFIZMmzaFdxMc7r/D2Dx/eR2tbvVpNWhOKquHDxtHENKpatZo02ceQD7TTaFwxOrp+27Zh4IARtWrVpae0PhTQm7es+6Z1R2EC2lw0kB6UL18xr4/vgwd3aZdlejPPq8jwMl6ekbVKtf3pUKSCM1WvWn7dhp42axpIewt9odL+8+LFM/pepBKH8E0zZfLcG/9dpQMy3ZcoWqSEsLS6dRouXDSTipAUf/SUSt9UTn/+7AkNOXhwT7lyFejDpeFubu69egyYv3A6lRPpsbbFfvjwnr63xo6ZUkrZ+kH789lz/6jGatuLUi1Ez0NDnY5NRE/pi6RHrzZUcKPJ6Mhd+qOG/gra5hR8HTv2qFihijBk7Zpt9vb2whFEJUEq0Ny8dZ0WSLFOB/KGX3cKOzmVnekQoMUKU6ZFQU9Fmf+t3V6oUGF62qVzrwsXz1Csz529lJ4mJiZSuYQOc3pMpSsqIgQF3afiCNMPn+GryMh13i9dp1evXvgp34OgRInS6c5CXzs0V9MmLVVDihUrqXpMXwKXLp+bO29K0KMHwl6rcd+iL3n6DqGv0Lv3blHtVRgYFhqiOwRv375Ba6j6VLy9ffLmzUcFe8oXWuDYMVMHDupOHyQdY6W0N9UVK1pS/c3s3r2NPjw66oQBVLClv0+fPGJqW4OSevo0XWVkmp0+dfX2QdomVP2hDSWkvPomcnJyjlIWSfTHSTgz7ILgWWZqIKrtT98EVOKrUvlzkxm1IVDxjb6B6NuR6rNU3WvYoBkNLFOmvKrKppvqW4oaSeivn1/yvm1v70B/qdYml8tv3b7Rvdu3qlkqVKhCA2kvEpJFozdvXtHfggU/38usePFSDx/eS36iZS9KRc9DQ52OTURHCmUKVaipyiJLSpo4cZaTk5O25ZQo/vm4prxeu245tTN8/PhBGCLUnx49eujg4KDagPT188MERTGTElbjMqkxgeryhdTSgz7Z438f/vyinw4fZ2cXpmgoy8A+z2WiYyTT7UURyh1O9dTezj7dWSizqL1M2KsEdmpz0UdC37RU2qdPjj6ktetWaOwdo2aaHyaPom+P/v2GFS5c9PKVC2PGfsfSQ9vx3v07QiOFSqiyMM8Un3QpKmVcuny+xhe1dSzE5lMJkXb9cROGJSYmfNv3u4CAytSAOGRYH9ULKd6XbTrtNSohIR9STS9sn9jYGGEPkGTtmqg8b45Ngpm7gIJq+wsbWbXNVegD9fPzX/rjL38e3EM1QWoRo6+6nt37UQUw3YWnatpLu9kpU+jripZJ/1K8aGgI0y48Ioz+Oqjt86ojRcdelIqeh4Y6HZtIKC5QVWP9htXUXKC7x1Z1S2iqkw4b0bdihaqTJs6mYhptroaNqwujoqOjbPXe4QllqF3KuKAMpR1e9dRIPyw3/C9GXFxcqYlN9ZS+JdKdhb5jqdgVrzaX6p3Tobr/wK62bTq3aN5aGKIt/g8c/IPaualFRvdkqbjn9qC5qKVPfaCrS3LBkArn9H1O3TtLfpq7ZtWWdHseHjy8Rx0sCxespLYV1Wp4euRRvkfFl6o+W0MgTB8bF6saIszr7u5BhwfLOrPsGMnij9Zze3gyRZ1uoq9vilsqU7cSU5bpBg4YTp/11asXqewze+7kgn7+qdphiUyesUuMUeGFjtVGDZvXTlnuy+ujq1NO2Mc0Hik69iJ1+h8a6nRvIrJtu6JRnmJ9zS8/CRV83aghkr4GqEGQasTsUxlQ4ODgSAcyZbqeX9iUA3FqOzyJjon2yO3JDEHHfqVt5TJ/AoWXlw/VH+WfmnbOnf833Vko4Gku6qVVDVE1EtOHERsb6/FpD6DNrd50oo5KoOo7yr///s30UNi/KPWRUVcyVY6Ef2653IUCPBXa582f2q1rX6oUv3sbTC106S4tPFzx9a5aDerGon/C4yJFilM1ltqhhKe0B9O3/ZEjB7SuWOFilLlUW1cNoa1KhQLqC2aGIJGYa8dIFr7s8/kWENptVZ8m9TAWLFCIQor6oCj4mDKz6Ftt6pR59HFQ3ZApCjW26sUNVQ1Uf/RhURuu6kXLlC5PfbV58njpmMVb2d5H7XHCU9rPqe4iPNaxF6nT/9BQp2MTCa9FbXDUMk79D9S0d+fOzXQXSMcdVU2EBCRCH4uAKlLUenhfuZGZsnee+qaojqxtUcWLKaZ/GHRfNYT2efW2tazQsVtp6R2WKnZHlil16zakbwPqqKXjnLpE9uzZoc9c1Nj8D/WzK7s4KW5UW59K3RRJtPu+ev2Sdg5qby5bJoAaYoRWP6p3UxH69OmTtOMWKVyM6q30itQ4IvSikuC3b3S/btu2XSivqS+Ptj4tZPWan3r37fD4SRCNWrN2mUQqpa43F2eXfv2G0s7xWtmOo/6iqZZG+xMdWtt3bIqIjKCPnDYC1aaFdaDmFWqNot5hei+0kjTqypULQpMffSfTh3312iX1ChS9KE2/ecv/zp79h5Z29Oiff+zZTmsrMdCdQajZ1xw7RuRZKp7SkdyzR39q5qciPIUCHZDU9b9k6VymPFapP/HnVUtevnpBH9yWrb/SfkJpxZRdajQltbfS402b13348I5l0Ld9vjtz5iRVRWlfopeePmP8yNEDaAV0zEJfZtQuuX79KloZ+rqdOWuiqq6nYy+i/KIZLyv3c9oTdBwamdhEtPIzZ09sUL9pyRKlqXpUv15jKiwLTY0ad1GBv39ROhz27d9FU164eJZK2dTCTgULGlW5cnWacc2an/49fYKOTXqV9+/eUjeO+rtQ75uqWrUGNVMsXjyLWqio/4SaF+hF9T/HLh0Z/cWIXNFJl8m9kT6wAf2HXbx4tl6DKlSSonIyEy5QqFPXLn2aN2tFnzc1z1HhcdDAkaq5qK2BmsZ69mrbtXsrqiD07fsdPW3dpsGb4NfVq9WiD37SlNHH/z7Su/egalVr/DBpZKMmX1A7Bb0ufRFRD/1fxw/reF3KmnVrt1NzTP+BXbv3bEONu9RzT1WkO3dvUcs0fR8KvRBft/iGyoz0duix+oumWhq1y0ycMPPO3ZuBrepR3zTVzVu2bEsfZI9eipO8hg0dS008ixbPGjlqgOJQmbpAKHJ+3fwbOgC+HzP40eMUX5KDB42qWaPOjFkT2rRttOW3Xzt36pXtp5UaW9bPXqQ+/e9HT966bf3XgXWX/jSP6qSjRilOnaHEGTliAnX3d+vemj7omzevLV60ihoKadR3g0e7u+Wm6akxi9pk6tfLQCe7gCKDWkv+++9a6zYNKVOoLWzmjMVpzyVIZfy46fQt2G9Al+Zf16bCFHXUCju87r2oS+feFEaTJo+iphIdhwbL+CaiL4a3wW8GDhwhTEabJTT046bNig5ibbsooazs1rUPpSptvV27tg4dMoa+vLf+tn7xj7Pp2Fk4f6Wcl0+e8j010NvZ28+ZvVQ4oNTfhWpRNGrm9EXUnjZocI/OXVteuXpxxvSFwrmcBqB9v+I0xtOGGU95OddmeEGmt5aBX1E5RTgzBszf5lmPSlZ1qdvWMA0uhrJy1KPCAc41Whqmyg+g8v5lwsFfnn+3pEjaUZo7RrgM9tJRcZfaRHLn9mAgEuZ5jxFlQRC/nAPDy/ApMorzJzJyniAVd6mF9au6jXRMM37i8Fs3r2sc1axZK+q2Y8aRXa8LmWBJF1CgFo8JE7XuXZs37dF2znDWfd2yrrZRY8dOrVWzLgM1Wu87nKEmwRPH0/9NyOiRPyRoObdD/Wwpg8uu1zVz5vmzOZ6Z5S+aM0XRULhmq7axxktAouN13XKlczZ1DmS6+w5nV2UZlXSN5DImN7/eYfO8B16mCb97yzmvK1K4vH6OZY5FLl7OcKMlMDFtIWiWV5sDA+LM8UL2uKgqGAmvPdK09A5LMn8BBRALM/yEeYaSIBiH9tMOtPQOyy2nfRo0M8vfDksknMQMC6ggfhm+xwgnwclakA3w7QvGon2/0hKCDDfmtnCKU2Qycg1n0+DlOfduc2Bs2vYsLb8dluO2wxbOPH8xIjXLsxfBMmSsTRAgW8jkPG9+Zy+CZUMIAkCOpjkEbay5JDkaBS2ZxIq6Ys2uPmxlw0msUBQEw+OlWi8hrXmwrRMnTzK/FiMwHI5n7t42zMxYWXOxUdjxwPA+voi2stY8SnMIlq/tHBOJfdFiPb4ZSl1f5b80u9/SexW0ffcylgEY2sMb4U5ums+H0ByChcu5OblZ7Vr6mIElOnvgY9Hy5ngFnRZ9fOUJ7J89rxmA4URFxYYEJ3UdV0jjWE7Hhe//WPHy4+u48nVzl6jqxsAiXDzy9sHlyNptPEpXM+KlnLLol4mPbB1Z5Ya58xcz35UEUQgLib1w8P27Jwn95xXSdrdITvfdP/5Y+eLtswRZEm+Gl10yOM60P5jmMnJz53QnTncCCad4d7Z2XIkqTl+28mLmbdOcx5GhciZjxr4bVIY+dMUF5vS81JfiCtl6TckpF5rONPrsKjwzyc+8Mv8yuje1jrG6376OLS1V3C2Ot3fiek0trHPF9PiZUmygmG1wAAAQAElEQVRobFRs6hClirQ89bpyGpfHCS+k6Y1wmobTW1K8MY0bhVOO1LTKyXNx2n53RXNqfa+0Gr+s+aV06VJf1KyhbdHal6x84zp/7sUpP8ZUE3C84n/qK890LUGi+ww69aVpJmOe+c2uJ0S38PcJCYnaRmo+NCTClVn1nSF5w2tcVtoPhUvOAG078+ehao81LPvTEhSjdOy3nCpyPn24qSY7eeLvV69ede3WTbgpAa9lzVUvQUescEylXSflLqo8tjQHCpd8wQ3lmqSaXXXAKsen3j7JY1nyhtY2VniRtKuteMBLFMGSZi7hAS1O24FhLZHl8rZn6dHrPEF7N3t7S68QRya8tHUp7JlXZDFh2Vw98XHokiQJpX8ePthKWYKTpZMlJSUJNwMEEIvExERra2sGWYPDPhlCEEQHIWgQOOyTIQRBdLDTGgQu2ZEM+xOIDkqCBoHDPhn2JxAd+ubGTpt1CMFkKAmC6GCnNQhswWTYn0B0sNMaBLZgMuxPIDrYaQ0CWzAZ2gRBdBCCBoEtmAz7E4gOdlqDwBZMhv0JRAc7rUFgCybD/gSiQ2042GmzDlswGU65AtHBN7dBYAsmw/4EooOd1iCwBZNhfwLRwU5rENiCybA/gehgpzUIbMFk2J9AdLDTGgS2oAJ2JhAj7LcGgS2ogJ0JxAj7rUFgCypgZwIxwn5rENiCCjjpFMQIIWgQ2IIK2JlAjLDfGgS2oIKtrW3+/PkZgBhER0efPXv2zJkzefLkcXZ2ZpA1et18PSd4+/Zt9+7djxw5wgDM0r179yj4KP4ePnxYo0aNmjVr1qtXz9HRkUHWIAQ/+/DhQ/Pmzf/++2/sWGAmVIU++uvp6UnBR/EXEBDAwHAQgilQIwt9u/7222++vr4MIJtQoU/IPlWhj/7mzp2bgREgBDVo2bLlnDlzSpcuzQBMJSYmhoLv9OnTQqFPyD4U+kwAIagZtQ/279+f9kIGYEyqQt+DBw8o+GrVqoVCn4khBLUaOnRokyZNmjVrxgAMSij0CS19Hh4eKPRlL4SgLpMmTSpZsmTnzp0ZQJbdv39fqPAKhT6hpY9CkEG2QgimY9GiRfb29oMGDWIAGRcbG3tGieKPKrlChReFPrOCEEzfunXr3r59O2HCBAagH6HQR9lHTX41lVDoM1sIQb3s2rXrwoUL8+fPZwBaUKFP1b0rFPoo+ypUqMDAvCEE9XX8+PEdO3asXr2aAahRL/SpundR6BMRhGAGXLlyhQqD27dvZ5CzCYU+obEPhT6xQwhmTFBQ0ODBg/ET45yJenWFCq9Q6BMa+1DoEzuEYIYJPzGm2rGTkxMDSxcXF3fmE3d3d6HCi0KfJUEIZkZSUlL9+vW3bNmSL18+BpZIKPRR8N25c6fmJyj0WSSEYOYFBgbOmjWrTJkyDCxC2kIfBV/FihUZWDSEYJb06NGjX79++ImxqD18+FAIPhT6ciaEYFYNHTq0cePG1EooPK1bt26rVq2GDx/OwIypCn1U582VK5cQfCj05UwIQQOYPHly8eLFu3TpQmn48ePH/Pnz79ixw9ramoGZoUKf0NJ3+/Zt1Q85PD09GeRgCEHDWLx48d69e6Ojo+mxs7PzxIkTGzRowMAMUKFP9UMOKvQJLX2VKlViAEoIQcNo0aJFcHCw8Jg2aZ06dSgWGWSfoKAgobZ769Yt1Q85UOiDtHC3OQNo2bKlKgEJx3H3799/9eoVrtFvYkKhT8g+FxcXKvFRtxUKfaAbQjCr+vfvHx8fL5fL6bFEIhEGvn379vjx4927d2dgCNu3b1+5cuWpU6c0jk1V6KPsow8lT548DEAPqA4bAB2cFy9evHr1KpVE3rx5Q5lIhcEyZcps3LiRQZatWbOGQjA8PNzb2/vAgQPCwLSFPrT0QeZYQgjuXPr8w+sEuYzJZGlH0rvj9BnGFNuC8Wmn5XlKND0nZsoFa9yg2qanza9p8TpXVOcLfXo5xXqzzCxYn/F6vIRqMp3rqSLhGCdlDk7SJr08vQt8/j3i7NmzDx06FBsbS4+pw33Tpk2pCn30F4U+yArRh+DayUHWNtKi5Z3zFndJO5aj4OFSv0NteSRhnJzpuzU4OUcz8Gmm5xT5wfEalsMpAy/t0OTE0TTD51GaJtAVL/TGFZ+sROvYtJslQxMo8MoVSD8GaSXk6U5Eiwn/GPXwSvSbx/G9pxRwcLWhgePGjTtx4oTs05cbPShWrBgKfWBY4g7BNROC3PJZN+lSkIEF2TIrqE57z6Vrx16+fDnVqLx58+7bt48BGI6Eidb+X15JrCRIQMvjH+B4fMuLp0+f2tvbU+lP6HQSREZGMgCDEnHv8Nvn8T6F7RlYnC+a+wRdjZ44dk5IxPN79+49e/aMettjYmKobyQ0NJQBGJSIQ1CWIM/lacPAEkkknLPE/8vACoGBgfSUOtwfPXr06tWrhg0bMgCDEnEIJiUyeVL6zfIgRkmJKZqqbW1tSykxAEPDydIAkKMhBAEgRxNxCCrOYRZx5zakAy0dYBoiDkHFGY7pn4QLYoWfc4JpoDoMZopDDIJJIATBTPGoEINJiLk6rPiD48Ri4aMF0xBzx4jiD2pMFgsfLZgGqsMAkKOJOwRRWACALBJ3CKLZyFJxnPKqjADGJ/LqMFLQQvE8/cOnC6Yg7p9cGOQsisePg76qX/m//67pGD512tjR3w9SDbx58zqzULt2b2vQqBrLlMDW9TduWssAREXk1WFjXhY7Vy637t365snjzUA/Hdp3K1WyLAMQFfQOa+XunrtXzwEM9Na5U08GIDY5q3f4/IUz27dvvHf/tru7R5ky5fv1HZI7t0eqaahCt/W3X39cvMbWxrbPtx2X/vhLuXIVWAbJ5fKlP807feakjbVN/fpNypQuP37i8F2/H6FgjYqK+n3n5ouXzj19+ii3u0eNGnV69xpoZ2dHc7VoWadzp17379/559+/HR0dy5atMGH8DGcnZ92vde7cv3+fOPLfzWsREeElS5Tp1q1vhYDKNPzJk0e9+3ZYuWLD1q2/0pp4eub5qm6jft8OkUqlOuZSGTbiW9oC8+ctVw2ZNHn0x5APK5evf/786a/rV12/cYXn+dKly3Vs371s2QCmrA63+aYTFZ/13NQ6KO/whzZBMAVxtwlm6Ch58PDe+AnDKlSosv5/O4cOGfPo0YN586emmuav44fp8J40cXbJEqVZFvy+c8v+A7uHfPf9qlWb7e0d1v1vJft0a/bdf2zb+tt6qjnOnrWkf/9hJ08d27BxjTCXVGpFM7Zo8c3ff12aP3c5Zc2y5Qt0v1BcXNysOT/Ex8ePGzuNFliggN/EH0aEhHxkyhtU0t9Fi2dSCh89fG7i+Jk7ft984uQx3XOpNGsSeOXqRdVAmuX8hdONGjZPSEgYPrIfJem8ucsWLfjZSmpF89JY9Xn12dS6Ke//hd5hMAVRX0qLZSgGb928TgWurl16Uxh5eXmXKF7q8ZMg9QmuX79Cx2r/fkNr1qzDsubI0QO1v6xXt04Detylc6+Ll86qRrVv17VO7foFCxZKXqtbN2gsvajwtEjhYlUqV6cHpUqVDWzZdu26Fd+PmiTEmUb0jtau2WZvb+/qmoueUplu776dN29dp5cQJqhTu4GwGuXLV8zr4/vgwd0G9ZukOxf56qtGy1cupNJi2zad6SmVJelvvXqNX7x4FhoaQiW+YkVL0JApk+fe+O9qUlKS+lqlu6kBzIeIQ1Cu5fbB2pQpG0AFFqqWVq5U7Ysvaufzza9eAXz+4umq1Uvq12vSsUN3ljUymezp08dNm7RUDan9ZX1V7zMl2qXL5+bOmxL06IGQHW5u7qopixQprnrsmzd/YmLi69cvVYmpUUxM9Np1y6ly+vHjB2FIWNjnuxEVK1ZS9djJyTkqKlKfuYiNjU2D+k3/+uuQEIL//vt3zRp1XJxdqI5MXUZz509t2KBZQPlKVNVNVY9m6W1qPaEyDKYh4uowl8HeYSq5zJ3zk0duzzW/LOvWvfXo7wdRKUw1lprwoqOjqc2OZVlUdBTV5hwcHFVDhAKXgF59w4Y1zZu33rxxz4njl6mcqD6vra2d6rGdveJeetHRUTpe6+3b4GEj+lJWUhWe6rzHjpxPNYFQB8/oXIIWzb+5/+Duq9cvKdEuXDxDqadcQ1tqJ61erdbOXVuHDOvTpVurY8cOpppR96YGMCuivopMhk8TrFa1Bv2jPt8rVy7s2v3bhInDd+86Joxq3KhFiRKlFy2eVbly9YoVqrAscLB3oL8UMaohoaHJLWsUjvsP7KKyVYvmrYUhqqKZQD3y4mJjmaLCq+u2otSkSI101LRnr0zMVKW5LM5VuHDRkiXLHDq0t2jREtSyWa1aTWE4tSEOHDCcNuPVqxcPHd43e+7kgn7+Qu1YJe2m/mP3X0KfjD5wwVwwGVGXBDN22U1q8rtwUdE25+Hh2bhxi8GDRkVGRQa/fSOMpSZ/CiZqyJs1+4fwiHCWBVThzZPHizp/VUPOnD0lPKBkjI2N9fDIIzylJDp77h/1eW/cuKJ6/DDovpWVla9vfh2vRX27zs4uQpaRU/8cZ3rQf65mTQNPnvrrxImjVDWmlaEh1F1DwceUzZE1atSeOmUeDaemRvW5NG5qPQNaoPjZHAMwBRGHIJ/BX4zcun1j6rQx1GlLR+Odu7eol5YOUW8vH/Vpxnw/hQ5parBjWVPji9pHj/156fJ5KvpRh29kZIQwnBraqBhFIUJ1zPDwsPkLp5ctE0BjqSYuTPD+wzuanloVKWsO/Lmbeieo+qnjhfz9i1Kj3r79u6h5kXKHimZU9X73Lljn2mVgrnpfNf748T3VhSkNhSEUoPMXTP951ZKXr15QJ8mWrb/SQsqULq8+l8ZNTS2JDMD8iPt6ghkqClK3LB2Ty1csXPzjbAojOrx/XLxGKN2oODo6Tpk097uhvXf/sZ1a/Vlm9eje7/WbV2PGfuebN19AQGWq/1JwWFkpOnmpGW7FykU9e7WlktSggSNp7MWLZ1u3abBh/S6maIZrffv2fyt//pEeU618yHff636h+vUaP3v2eOOmX35cMoe6lceOmbpt+8atv62nYKX3m4m5Chb0V5/SwcGhUqVq79+9LVSosDCEekJGjpiwfsPqHb9vpqfU9bF40So/vxRzadzU+teFAUyJ43mxno21YmRQuTruAXXdmfmhngQqWFGhT3hKEbNly//27zupey71k43NBFXY23Vo2u/bIc2btWImtGFqUK1WngF1XBmAkYn78vo8Z6YNR5R627Zv+LbvkAb1m1y5epEKTS1btmWiEhz85tXrF1STLViwkKoubDK4lBaYjLhPls7Gw+TrlnW1jRo7dmrPHv3Cw0OPHj3wy9plnp5erVt1SHUqjP5u3rxOXavaxm7etEf9/BsDOv734bXrVlCP+dTJ8ziTf9ngUlpgMmKuDo9SVofrZE91ODLlqS3q7O3sUzU1Gu+10v1lsUihBs2U+QAAEABJREFUOgwmI+YLKGTrr0tNmT6WmnQA5gBtggCQo4n8eoJoOrdcHD5dMIkcdJ4giA2K+WAKYi4JcqgMWzJ8v4FpiLpjRLQd2wBgNnDzdTBTaOsA08DN18FM8fh4wSRwigwA5GgiDkGJBD8vtViKD5cBmIKIQ9DKisVHJzCwRPTl5pQb33BgCiIOQRdPq+AncQwszoNr4RIpK1zGKBeGAEhFxFeW7jjKL/xDUkICCoOW5spf7wsUs2MAJiHiq8iQj8Fx2xa+LFHFuWoTLwbi9/pJ1PEtweVru9T8Og8DMAlxhyB5/ybuj2WvEhN4KysuKTH96bmUZxdyiivXKe/irnykYXpNw2kYJ+XkMqb5JbQsiqV9ef1mVN1lns/gvOm+O22zc5xwNz99qWbP0GZUZ23NJckVN5jLX8z267667i0FYFiiD0HB4zthb4ISZImZ6FHk0jvnWssEEk5x+/cMLpNXpgHL4Gsp52IXL14sVaqkk5NTRublM3kyJad8d5nZnJSdGmdLbztLmKsHV/5LDwZgWhYSgjlB27ZtFyxYUKhQIQYAhiPyS2nlJElJSYa9YDUAMISgiCAEAYwBB5VoJCYmWltbMwAwKISgaKAkCGAMOKhEAyEIYAw4qEQDIQhgDDioRAMhCGAMOKhEQyaTIQQBDA4HlThQMVAqlTIAMDSEoDigLgxgJDiuxAEhCGAkOK7EAWdKAxgJQlAcUBIEMBIcV+KAEAQwEhxX4oAQBDASHFfigDZBACNBCIoDSoIARoLjShwQggBGguNKHBCCAEaC40ocEIIARoLjShzQMQJgJAhBcUBJEMBIcFyJA8/zXl5eDAAMDSEoDhSC79+/ZwBgaAhBcaC6MNWIGQAYGkJQHBCCAEaCEBQHhCCAkSAExQEhCGAkCEFxQAgCGAlCUBwQggBGghAUB4QggJEgBMUBIQhgJAhBcUAIAhgJQlAcEIIARoIQFAeEIICRIATFwdraOjExkQGAoSEExQElQQAjQQiKA0IQwEgQguJAISiTyRgAGJqEgUhIpVIUBgEMjuN5noEZa9SoERUDOY4LDg728vISotDX13ft2rUMALIM1WFz9/HjR0pAekB/3717Rw8cHR07derEAMAQUB02d1988YVcLlcf4ufnV79+fQYAhoAQNHfffvutu7u76qmNjU2HDh0YABgIQtDclS9fvmLFiqqnBQsWbNasGQMAA0EIikDv3r29vb2ZshjYrl07BgCGgxAUgRIlSlSoUIH68fPlyxcYGMgAwHCy5xSZ/atfvXsVn5TAJ6n9HFbCMXnKdaFOUWHtpBJOpjZOIuHkn54q+01ZyjfBC4OVD3lOwqnGKifkUk3JKf+jcQLVCwlrIpGwlF0UqdeW/qWaQH1VWfKLpVqHlCssLIel3RS8TMZzSsI0cnprqZeTeg11rDYnYbw8xWQ6CO9C02Qp1lzbaqgN5+XyFNOn+9JSCZMpF6X+Mel+Fabcxrb2nKOrpEkvb3dPewagXTaE4C8THkuseK8C9vbOUl6uXhRV288VQcGphsg5TqJ1PYWD6vPY5FmTH1NoqI/iOY5Te5pibNohcuWBprZuqY9EyhFO7R0o504xgdoSkteWpzRJr/ydJqyZcsF8iuUo1jXNjMrBKZaUvFJ82knV4ufT+1LfdnrQPnnayEpnSRrDNOUklPlaviQ1TMvTt8Tb5zERH2WB/fP6FnFgAFqY+jzB1eOCCpRwrNXahwGYxOaZD8vXca/RIjcD0MSkbYJb5j51yW2NBARTqt8p341ToQxAC5OGYNiHpIoN3RiACfkUtpdYsRM7gxmAJqarDocGJ1BDTd5CLgzAtOzsrcKCExiAJqYrCVILto6uVQDjiY+Tx8dmoMMHchRcQAEAcjSEIADkaKYLQcVZXrh0IQCYGdOFIM94Ds0yAGBmUB0Gyyehr18pA9AIIQiWT04NMbhLFWhhyhDEFWsAwOyYMgTl6BcBAHNj0uow+kUg22DnAy3QJgg5gOLKi6iHgGZoE4QcgGcpL7MI8JlJ2wQZAICZMWXpzCxqJGFhoV/Vr3zi5DFmlnbt3tagUTVmBI8fB9Eb/++/awwA1JguBBURiBpJ9smVy617t7558ngzkWvdpuHrN68YgIGY8mdzkJ3c3XP36jmAiVxw8BsqyzMAwzFtdTiDqG7Ypl3j02dO1m9YddmKhTQkJiZm5uwf2rZv0rhpjf4Duu7Z+7tq4nPn/p01+4cOnZo3bV5r5KgB165fVo06/veRrt1atWxVb+78qaGhIarhf+zZ8U3bRkFBD2guqoT2+bbjnTs3z5795+uWdWkhk6d8rzretC38wcN7VMf859+/aV56QCu2YuXidN/Xjt83t/qmwenTJ+nV6zWo0rV766NH/0w72ZMnj5b+NK9Hr7bCm927b6dqOL3W3Xu3J00eTQ/ad2z286olMplM9yj16vC06eOmzxhP75S2ScPG1YeN+Pbu3VvCwmn7jBn7XfOvaw8c1P3wkf1r162gFUj3HWlbVUKbtF//Ls1afDl2/NDbt/8bMqzPj0vmCKNCQj7OnDWxY+cWtDVmzZn04sUz9c/l+fOnvfq0p3WmbUtrQsNps3fq8jU96NI1kLYe05uE4zh0y4EWptw1MlwWtLGxiYmJ3rdv5/hx01sHtqch4yYMff365Yzpi3ZsO1i7dn068OiAp+FxcXGz5vwQHx8/buy02bOWFCjgN/GHEXSMMeXBT/nVqFGLzZv2NG7UYtnyBarlW1tbR0VFrt+4euH8lfv3nkxMTJw9d/Khw/vW/rJty6a9N29d375jk+6FW0kVRenNm9fNnLH4yKGzgweN2rvv9z8P7tH9vqRSq+joqON/H6ZX2fPH8fr1GlM6qyJAZcXKRZcunRs2dOzcOT81a9aK3uz5C2eE1aa/ixbPrF+/ydHD5yaOn0mpKrRy6hilzsrK6vad/479dXDVz5sO/Xna1sZ2zrwpwqj5C6c/f/F0wfyV9I4uXDhD/ySS9HcSbatKm27CDyPc3Nz/t3ZHn96DVvy8+P37t8IN/yiaR4zqf/3GlRHDJ/xv7Xa3XO6DBvd49fql6nP5adn870dN+vuvS3VqN5i/YPrbt8EVAirPmbWEJtiyeW+tWnWZ3uQ8z6NbDrQwZZsgy+iOSEcLHUUdO/ZoUL9JvnwF6Li6efM6HRglS5R2dc3VpXOvsmUDNmxcQ1Pa2dmtXbNt1MiJdJzQvwH9h8fGxlKK0ShKJa883tQc5uLsQqOaN2+t/hIUfD2698ufv6C9vX21qjXfvHk1Yvh4Ly9vqjwGlK/06NED3QsXfPllPR/vvBTZX9VtWKXKF8ePH073rSUlJX3TuiO9KK1Vzx79HR0cqbiaappJk+YsWLCyYoUq9KKBLdsWL1by4qWzqrEUDXXrNKC8KF++Yl4f3wcP7uozSiU2Jub70ZNpLAVi/XpNKIKplB0eHnb+/On27bqVKlkmd26PUSN/CA5+zfSgbVXPXzhNy+zfb5i3t0+xoiW+7fsdZZkwC32UVNabMH5Gtao1aGsPHDDcxTXXrl1bmdrnUqpUWdoH6KuLQiwo6D7LLGVJEA3SoJlJ2wQzVyUpUby08ODJkyDKo0KFCqtGFStakspTwmMqM65dt5xKFh8/fhCGCJXZV69e+KnNUqJE6VTL9yvoLzxwcHCgMgsdkMJTe3uHt++CdS9cULRIcdVj37z5/zp+iOmhWLGSwgM6QvPmzff8+ZPUU/D87t3bLlw8oyok+vj4pp2dODk5U9FJn1Eq+Qv40ftVTUN/IyMjXr1+QQ/KlCn/abhTxYpVqWDI0qVlVekjo4X4+xcRBlJEOjsn32SGvkUopik32aeNQN86N/67qlqk6pMSZtH4LvSkLAmiURo0M+V5gpn8KqYSlvCAAsjOzl59FB3GsbEx9IDKF8NG9K1YoeqkibOF4gM1dQnTRESEUylSNYt9yiUw5eGn8bGKjoUL1NeKYpqqukwPtra2nx+nmUsul4+bMCwxMYFKTwGUHU7O1JqmPoGOWqo+FViN01AO0l9HRyfVEBcXV5YeHasaGRXp4OCoPjF1UgsPKNSouEdNfhrHMi2fBYDBmTIEs/pV7OjoGBcXqz4kOibaI7cnPTh56lhCQgK12VEFk6UsptFhHBcfp3pKZTqWQToWLlAvpFD93S5NzmoUHR1N70h4HB8XR41i6mOpy+XevdsLF6ysVLGq6lU8PfIwY7K1taO/iQmfb8wWGhaS7lw6VtXO1i4hIcVt3j5+fC88oOo2bc9ZM39UHyuVGOWyf1QX5nA9QdDCrHuHUylerBRFzEO1tiHq0xSqulTco0qTEFLk1D/HVdN4efnQZPJPd7o7d/5flkE6Fi6garLqMTVd+RcqosdSqa/zkvCAulyoyqlezSfUlEZ/Van39Olj+seMjNpG6e+Tp4+Ep1FRUVevXkx3Lh2r6uubn74zhE4kpuzepZZH4XHhwsWoaTVPHm+hpZX+0SdVRK1hwYCoLszjeoKghYlPHMhSYbBq1RrUdrZ48ax79+/QcbXufysp3Tq060aj/P2LUmV53/5d1OFw4eJZOnSp5+SdskWvbt2GdBxSpzC1C9FBuGfPDpZBOhYuuHT5HA2nB6fPnKSXaNCgabrLpNooNaJRzwB1kv7v158pB6l3Qn0CaqmkLgvqno6IjKDJaP2rVK4e/PYNMybfvPkKFixEfU3US0sJuGTpHPVWSG10rGr1arWkUikNoWLvy1cvNm1a6+mZnJVUbKQPdOHCGdTaQDG6Z+/vAwZ2O3x4n+7XoqZM+nvy5DFV4yxAFpn4FJksFQbpSJs5fRFVbwcN7tG5a8srVy/OmL6QOohpVP16jbt17bNx0y/UWkc9jEOHjGnYoNnW39Yv/nE2HZAD+g+7ePFsvQZV5s2fSrVaxapk5J5POhYuTNC5Y89161ZQ89aUqWO++aZj82at0l0mNXi1b9d15OgBDRpV239g17gxU4VSmAr1UE+cMPPO3ZuBrepN+GFE3z6DW7ZsS6Gvz1l7WTFm9GQK6G7dW48Y2Y86WMqULm9tZa17Fh2rSnVe6m2n7o427RrRxu/cuRd1N1l9WuCcWUvq1Gkwfeb4Vt802P3HNvryoK2n+7Uopps0/vrX9av+u4nf/4FhcLypbgEXEpywdd7zHlP1qiqKxePHQX2+7bj0x1/Klaug/1y7dm9b+fPi48fSr2maHhXKqM2Bck14On7icCupFX3ZsMyiQiU1Jrgoe3hpZ2vRsk7vngPbtOnETOi3eY9d3Kw7fp+fAaSB6wlCCtOmjwsOfj1w4IhyZStQC8CVKxdS9V1kCEUqFduLFC7Wp89gNzd3Ki9LOAk1UDDT4iQMXc2gjQhOkREjKkDdunld46hmzVqZ81UMpkyZt2Dh9F/WLn///m3BAoWmTJpL7Qk3b16fMHG4tlk2b9pDjaQaR9HwubOX0tImTxmdEB9fsmSZFcvXUx2ZmRYvZ7jnNWhjyvhO5XgAABAASURBVOpw4pZ5z3paVnVYm/CI8KTERI2jbG3tnJycmNjo6Igwfahl1PYFT1zcrduPzMcA0sA9RozCVY9zjMXF/JNOB7mcl8tQFATNxHSyNEBmoUUQtELHCOQE+AIGrdAxAgA5mklDEF/HAGBuTNomiKIgAJgb04Ug7n4N2YXjGC6vD9rgRktg+Xie4fL6oI0pS4IAAGbHdCGYJJfhp0uQLZTVYex8oJnpQtDejklxdV/IDlbWnK0DqiKgmemai53c7aVW7OYZXAsTTC0uWuZXRq97HkAOZNI+s3zF7O+ej2AAJnR23xupjTTgSxH/9hmMyqQh2LyPr08hu63zghiASZza/frJreh+swoxAC1Mdyktld9/ev7uWYKdg0QiZUlJGlpqJBJOLuelEk6W5l6xEo6TK1dYMY3ixAfNYzlO8b6oOVz9zQkDhYWrDf188g6nnIHXsD7s022aaHJO9arCAj89/vxawr0i0y5JonxH6m9YMSXHUt0Sl1OOUJ9d45pznIbPjrYAn3aBXOqr6SnfKVPbfIqtoD5ZqteSSLmUV2HhUp7ylOKpasXSXW3VKOGlNY5K/RqK9yfROJnq01c8ZrzEiouPlVnZSPrO8GcA2mVDCJKQd1Hn/oyICk+UJWgIQU6iOKtLKuVkaS5/pDpQFdcKZmmOE0ny6WDCAcOljhLlkSZJccoYJ+FUkaGYQK7hXB6JVCKXpXOaWcoQVPxNu10VLy1LsXzhDN5Up7CFhoW4urhK1G4+qXnNOc0vQV4+f5XHK4+1dfKtPCQcS/VtopiMT5OM6psi5Wtp/CzSev7subu7u7OL06fPSLFAHatNb1Eu3ARO+YGl2IYSzWf2ccqvIY2TpXjM8XbOkoIlHCrWzc0AdMqeEARtHj9+PHbs2N9//51l1rVr177//vtcuXJ169YtMDCQmdCLFy8OHDgwcODAJ0+e5MuXT5XCAOYMPyYyOwsWLGBZIJVKJRLJ06dPly1bNmHChOjoDN9sPtPy589PCUgPZDLZl19+ef78eQZg9hCC5sXf39/Pz49lgZ2dnVR5QmZYWNixY8d69ux58uRJZlpFihShBHRxUdxhbvPmzffv32cA5gohaEaeP38+efJkljW2trZUEhQeU1sH1Uznz58/b948ZnKlSpWivyVLlpw2bdrHjx+TkpIYgPlBCJqRPXv2FC5cmGWNVEl9yLt37/bu3cuySaVKlbZu3erk5JSYmNihQ4cLFy4wAHOCEDQjnTt37tq1K8saqg6rl7moMFigQIGzZ8+ybEXlU3t7+1mzZt25c4eePnjwgAGYB4SgGfHw8JBm+ffVFDfCiYrUO0Hlr169eu3evZuZB2orpPWhBzExMVWrVhUCESB7IQTNxcKFC3/77TeWZc7OztQm6Orqeu3aNeoS2bVrV0SE2f1UMSAg4Ny5c8I5NOvWrXv8+DEDyCYIQXNx9erVpk2bMkPYv3//8ePHhcfDhw9fsmQJMz9U5i1atCg9KF68+NixY6kKHxcXxwBMDidLW742bdosWrQoi2feGJtcLqcOnHHjxo0ePbpMmTIMwFRQEjQLr169CgkJYcYxbNiwpUuXMvNGVXhvb+9Ro0Zdv36dnt66dYsBmARC0Cx06dLFeD8yq127dmRkJDURMrNXtmxZoX88NDT0yy+/fPr0KQMwMoRg9rt//3737t2pQ4MZjdm2DGpDCXjkyBHh8apVq4KDgxmAcSAEsx/1DPTu3ZsZE7WyeXl5qXpLRMHBwUFox8yfPz/V6JnyxBoGYGgIwey3Y8cOmUzGjEwULYMaNW/efPv27UzZctqvXz+cTwOGhRDMZqdOnTp//rzU+Peg8vX1/eKLL3bu3MlEq2jRov3797969So9/u+//xiAIeAUmWz277//UnXPNOevUHWycePG9IpM/Pbt20cF223btnl6ejKALEAI5izUyUClzm+//ZaJX1hYWFxcnLe397Jly6hnydXVlQFkHKrD2enWrVsG+amc/gYMGLB+/XrL+G1Grly5KAGZ8jfXQ4cOpQdRUVEMIIMQgtmJ8kg4jE1JvD0k2nTq1GnDhg304Pbt20OGDHnz5g0D0Buqw9mGtjy17pcvX56ZXIsWLX755RcfHx9mcc6ePRseHt60adPr168HBAQwgPSgJJhtOI7LlgRkIjx3Wn81atQQrkNx8+bN5s2bm/IWKyBSCMFsM3nyZOFsD9Nr0KAB1Rmp8sgsV7du3datW5eUlBQbG7ty5Ur6ywA0QQhmD2rCP3XqVMWKFVk2sbyWwbSovZW6jO3t7W1tbceMGUNDUDCEtNAmmD1kMhlteSsrK5Z9KAfbtWtXq1YtlmP8+eefJ0+eHDduXO7cn2/K/vHjR1MeBdSXzcCcoCSYPcyhdmbBLYPaUCshtRhScyFT3qWeASAEs0VISEjr1q2ztxhIChUqVKZMmf3797OcpF69enXr1mXK3+q0atUKNwIFVIezwdGjR6lfokePHiy7hYWFtWnTRlxXlzGgFy9eeHl5hYaGxsfHOzg4MJNAddjcIARzup9++ol6D8whkbMLtQlSPxW10rq4uNDhINyrz3gQguYG1WFTo0LHpUuXmNkYOnTosmXLcvh3oaOjIyUgPYiLi4uIiDDI1rh48WKTJk06derEwLwhBE1t+/bt2X4r9FRyYA+JNsL5NEJDYWJiIoMcACFoanK5vEOHDsycdO3a9dChQ1QrZKC8e71wvxcqFVKbKQNLl80dlDlQz549mfkRzp2ePn06A8aCgoI2btz48OFDqVRavXr1jh07Un2ZCon79u1buXIlDaFK7m+//Xbz5k0fH59+/fqVK1dOmHHt2rUnTpygr5MSJUo0aNCAgRigJGhSV65coaYiZn6aN29+//59OvhZjvfy5cvRo0fTx/TFF1+ULFnyzz///P777yMjI6nzxMbGhiagnv3Zs2dT/wZ1KNMWmzdvnlB9PnDgwM6dOykBa9euTWXJ//3vfwzEACFoUnTAqP9WwaygZVBw5MgRqgjXqFGDuowmTpz4zTffUOqdO3fOyclJ6Dh+9uzZuHHjvvvuuzlz5jBl57Jwa9CDBw/S38DAwAkTJixYsIAClIEYIARNh4oSgwcPLly4MDNLVPChkg4d7SxnE+77XqxYMeFp8eLFmfKaNKoJvL29ixYtSg/y5csnnF0YHh5Onf7CHaCqVq0qTNa4cWMGYoA2QdOhokSdOnWYGbt3756/vz/L2YTOkPVKqoHqF2ql4LOysqKvNFulmJgYmUym+h0ktR6megBmDiFoOlRYmDlz5owZM5hZmj9/fo8ePby8vFjO5uzsTJFHjaTUtKcaSGGXajLhEhiqp9RtIjyIiIgQHlAzIgMxQHXYdOhAun79+uvXr5n5oX6AJ0+emNu5O9mCOnaZsqWvvBIV+l68eJH2h95UrlcfSB9uoUKFmLLviykvG/7PP/8wEAOUBE2KOkbs7OyY+Rk5cuSxY8cYMNayZUvqET5//jx1CpcqVYq6O6hMN2nSpCJFiqhPlvZW0Y0aNVq9evXevXupMPju3Tvz/LaDtFASNCk6qNzd3ZmZ+eGHH6gbVFWhy+Gou2Pq1KmlS5emzpDt27f7+vpSb2/NmjVTTRYdHZ3qJyXUL9ykSRPqQT5x4oREIhkyZAgNxFVqzB8uoGBSly9fpkOrV69ezGz89ddfVAakIirLqTJ3UVUq7gkdIyyDcAEFc4OSoEnlypXr8OHDzGxQOYWKgTk5ATONOn+FX9eB2KFN0KSoXWn8+PHMbIwaNWrhwoUMMi5tmyCIFEqCpmY+N8P9448/PD09c9Q9RgwoJiYmISGBgfihJGhqK1eurFixYvXq1Vm2CgkJoTVBj3CmyeVymUzGQPxQEjQ1Ozs74VSy7EUV4UWLFjHILOHKgwzEDyVBU+vQoUO2/5Zgw4YNFSpUUF0AKofL3PX0s/0+WWAoOEUmx3n69CkVA3ft2sUgC7Zt2+bm5oarJFgAVIezQceOHePi4lg2GT16NCrCWfdWiYH4oUifDWxsbB49elS6dGlmcsuXL2/RooWfnx+DrKFmDZwlYxlQHc4GYWFh1KZu+p+p3bx5k8qA6leIAgCEYA7SqFGj3377zWwvbS0ue/fupWOnVatWDEQObYLZ4OrVq6b/3cjs2bP79++PBDSU9+/fq19pFcQLbYLZoECBApSDzITOnDkTHBw8YcIEBgYSGBgol8sZiB+qw9kjKirK0dExc2eoZUL16tX//fdf/OAfIC1Uh7OH6tZlJjBu3LgZM2YgAQ3ryJEj27ZtYyB+CMHssXjxYtOcrnz48GErK6uGDRsyMKjQ0NAXL14wED+0CWYPPz+/u3fvMiOLi4ubOXPm6dOnGRgafa/Ex8czED+0CVqywYMHd+vWLduvWANgzlAdzjbGvhrdjh07qBsaCWgkJ0+exGnnlgEhmG2++eYb451o9vbtWzpEx44dy8A4wsPDnz9/zkD80CaYbcqVK/f06VMfHx9mBLhcoLHVqVOnUqVKDMQPbYIWaO3atYmJiQMHDmQAkB5Uh7MN9S1GRUUxQwsKCvrrr7+QgMZ28eLFlStXMhA/lASzDaXVxIkT4+LiYmJiQkJCDHXN/cDAwBUrVuTLl4+BEXTv3p1K2XK5PCIiIjo6mrqe6DE92Lt3LwNxQpugqdFRdP/+fTqQmPLC7sLvRnLnzn3r1q0yZcqwrPnxxx/btWuHBDQeT0/PEydOSCTJVah79+7RX2xwUUN12NQ2btzo5eUlURISkArjTk5OWU/Aa9eu3b59u2vXrgyMplu3bu7u7upD6ONr0KABA9FCCGaDb7/91sHBQfWUorBKlSosy9AjbAIBAQGVK1dWH5I3b97WrVszEC2EYDb4+uuva9asqWqNtbe3p6csa6ZNmzZ8+HBXV1cGRtazZ09vb2/VU/rsfH19GYgWQjB7zJkzx9/fX8jBXLlyVahQgWXBqVOnwsPDW7ZsycD4SpQoQeVB4XH+/Pk7duzIQMwQgtlm1qxZ1B9COVikSBFnZ2eWBagImxgVBoWz3CtWrIi7VokdTpHJjNN73z+7F5UYzyUl8tS9IZdr+EuTUa8Hr7i3nCQhQXEJYk7C8cJwjglbPS4uNjY2ztHB0c7OlrPiZYoeY6aaPdVj5YyKz0sq4WRqA6OiomxsbW2srVNNTGztmZundYtvxdF3eWTj6w+vE+KiZbzad7PwlnnlxmSfNp0wkKXZPqqn1OUk5xUfBM+n2MGlEiZLeTVoTvl/+p+cT70c1cekWhNOwuQynv7ychYTE5OQkODi4iyRSFWvmHZNUpEoPzsuzUDFrGkOReqCFq5d/XmPSrlKGl9L2OvU2dgwO0dJ6RrOpau7M0gDIZhhv0wK4pM4x1xS2vtlScmHinBgqD9WUO6P1jaSxOQQTB6u2pXVh9Ahlryjq2ZP+ViFk0h4TRd2T3uEWEn5mCh5XIysaQ+vQmWzVNg0qrhY2fqpT6ysOEc3K9qkjE81jh0QAAAQAElEQVRTQfmUgsnvUXWgU/7IPk+ltmEV3zfCVWvVt4mmbOKV+ZYy74RPM02aJA9X/4BSvmKqKYXATrEETjmc07DYtD5/a6r2E8Y+fyFonT31FNY2LD5eHh2W5OZl3XFUQQYpIQQzZu3EIDcfm0bdCjDxCA+P3bfsVc1A9/K1zLEgEP4+dsu8V1987VEkIBcDY9q+KMjJ1abjKDHtvSaANsEM2DDjsbOHtbgSkLi62n8zvMDpP0KYWfpt0aty9VyRgCbQYVSRqPDEA2tfMlCDENSXTCaLCpM36y3K2oSjk429k3T/L2a391/66wPHs/I1PRmYROFyzq8fxTFQgxDU19XjYVIx/8jQOZck9F0SMzMvHsTY2GMnNJ0SVXMlJTJQh/1PX/JEXmbcS0EbV1KiJCHG7O6TmxTLJYp5q4qOVEq9eQzU4QIKOQan6G1kAJASQjDH4Bkvx5kAAKkhBHMKKgaaYUmQVkmC8ilkK4Sg/kR+rJrlCaFUOJWjfGpCnNh3YyNACOpP3MeqXK74yReDnI1HBqaBEMwpFL/MM79zAVAdNjX8QiwNhKDeOJFXiDlmjm+AY8hAyF4IwZxCeY0GsysF8DI+CZV0E+I4sbfrGB5CUG+8uPceXq75UiWQs/DoGkkNIZhjmO3J0jgmTQgdI2khBPUm9jZBszxZOvX19sDY0DGSBkJQbyKvDlPXsBmWBCXKq8kygOyDCyiYtV27tzVoVI0ZhFlWhORUOs1g2eTx46Cx44Y0bFx9y9ZfafvUb1iVZUGrbxps3LSWKTd1FhclDoprWzNQhxDUG5fhFuUnTx517NyCmQeel8vNr2OEY1xG62fH/z78381r06bMr1+vSamSZbp17csMwYCL0tO06eMOHtqb7mQG3osUV/xnoA7VYb3R3pPBw/X+gzvMjFhIGSA6OsrbO2+NGrXpsbe3T8mSZZgh0HIMtSg93b9/p0qVL9KfzKB7Edoe0kIIGsuxvw7Nmz+NHnxVv/KggSPate0SExOzeMns69cvR0ZG+BX0b9o0sFVgO2FiHaNUnj9/+uv6VddvXKH6Y+nS5Tq27162bID+66O8WZo5niydobUaMqzPrVs3mHKr9u0z2M7OfuXPi48fu8iUFdtePQeEh4dt2LjG3t6+SuUvvhs8OnduD6YsTO3bv/PqtUvBwa9p8zZr1iqwZdtUS6bqsLCoM2dO/TB5VKqxmzbszpevQFJS0rr/rTx/4fS7d8FlygS0DmxfvXqtdNf5/IUz27dvvHf/tru7R5ky5fv1HUJrRetPoxYsnPHzqh/37z0ZFRX1+87NFy+de/r0UW53jxo16vTuNdDOzo4+caG2rtqLbt/+j97gvXu3XXO5fVH9yx7d+zk6OjK9oV8kLVSH9ZbB6nDDBk07duju5eV94vhl2ndpyLgJQ1+/fjlj+qId2w7Wrl1/6U/z7t67LUysY5QgISFh+Mh+Uql03txlixb8bCW1mvjDiLi4DFwnPdXNJ81Gxoqny5auo/zy8/Onrdqlcy/1UdbW1pQ1Eolkzx/HN/y66+at6+s3rBZGrVi56NKlc8OGjp075ydKQNq8FEzaXoJyavGiVap/hQsX9fbyyZ1bcQOAn5bN37lra+tWHbZu2V+ndv0p08ac+ue47hV+8PDe+AnDKlSosv5/O4cOGfPo0YN586fS8MMHFSvw/ehJlID0YPcf27b+tr5D+26zZy3p33/YyVPHKOloOMW6+l708tWL0WMGxcXHLV/264xpCx8/fjhiZD+KZgZZgJKgidBRd/Pm9f+t3V6oUGF6SgfwhYtnaEefO3upjlGq2V+8eBYaGtLmm07Fipagp1Mmz73x39WM7f2cWZ4la9Bs9vXN37VLb8UjJ2cqCT54cFcYPmnSnJiYaB/vvPS4QkDlw4f3Xbx0tnq1mhoX4uqai6YRHu/dt/PVqxfLf/qVipbx8fFHjh7o3Klny6/b0KhmTQOpTLpx0y+UhjpW6dbN61Sgo7WidKYsK1G81OMnQWkna9+uKy2nYMFCyXPdukFr2L/f0FST/fXXIWsra4o/Wkl6OnrUpE5dvj595mTdOg2YntAZnwZCUG8ZbxNU9+RJEB0MQswJihUtSW38ukepUF0sVy63ufOnNmzQLKB8JSqtqA5UPXGK7mHzKwoqfjtssKOyWLGSqsfOzi7Uepj8hOd3795GXy30XSIM8PHxTXdpQUEPlq9YOHHCTCoM0lOKVCqPU7aqJqAP4tDhfeER4a4urtoWUqZsABXYx08cXrlStS++qJ3PN7/GD46KsZcun5s7b0rQowfCd5ubm4b7o96+faNEidJCAjJlk2jevPmom0j/EOR4dA6nhhDUW9ZKUh8/fqAGLPUhDg4OsbExukep2NraLv3xlz8P7qHqGDVL0a7fs3u/hg2bMb0pMtwMfzbHM7nhSoIaSznUKT5uwrDExIRv+34XEFDZ2cmZGhbTWxKLiIz4YfLIwJbtVPkSFRXJlI2SqaYMDfmoIwSp5E518H/+Ob7ml2Urf/6xUsWqPXv0p++wVJPR2IMH91BFmEKWCoxr163Q2HFM63Dv/h2hPVF9BZjekIFpIQT1lrWSILVex8XFqg+Jjon2ULY06RilrkABv4EDhlMj0dWrF6kAMnvu5IJ+/kLtWB/m2TFigmZKapWjboSFC1ZSAAlDKEo8PfLonmvmzAleXj60wVVDcnsoPpFRIydSpVt9yjx5vHUvqlrVGvSPPrgrVy7s2v3bhInDd+86pj4BNQjsP7CrbZvOLZq3Vq2hxkW55/ag3jBalPpAV5cM3LIZleG0EIJ6y1pJsHixUlQtehh0v2iR4sKQu3dv+SmrwDpGqVDX8O07/zVt0pIqzjVq1K5WrWaTZjWpgqZ/CPJmWRGSWHESqXF756i/mP6qUu/p08f0r5BfYR2zUB8Ftdyt+2Ub9USpBubzLUDlcaZsVRSGUCst5RcV23Us6vr1K/EJ8RSCHh6ejRu38PbOSx1cwW/fqKdwYmJibGysx6chVOk+e+4fjUsr7F/06LE/y5erSC2MqrdDTSVMb+gdTgu9w3rLeEmQ9k6q6p4+fZKaoqpWrUF12MWLZ1F1JiTkI1VpKek6tOtGk+kYpRIRET5/wfSfVy2h/kFa2patv1LLUZnS5TOwNrwyB80ML+PlMuPW0v0K+ltZWW3fsYlquPRdsmz5giqVq1MMaZv+xo2rv6xdTn2ylIPXrl8W/r1795bCjmqy1BNCvViUU9QvTB21S5bO1f3qt27fmDptzP4Du8PCQu/cvUW9wJSG1N1Meerpmefy5fO0cEo0KuZT6f7V65cU2fMXTi9bJiAyMiI6Opql3Ivatu1CtfvlKxfRtyY9Xb3mp959O2jsadEG15BJCyVBI6perRbtzZOmjO7RvV/PHv1mTl+0avWSQYN72NjY+PsXnTF9oXCiHx2i2kapUCvSyBET1m9YveP3zfSUWtkXL1rl5+ev/8ooEtwM2wSVlzlkxkRNbNS5Qb3tga3qUU124vgZH0M+TJo8ukevtht+3Zl2euoCZoqzaharD/xu8Og233SkZCxcuNjWbeupRcLR0al0qXKjRv2g+9Wp25fijzpYFv84mz7cel81/nHxGvrEmeI0gN6/rl9FvcC/bT0waeLsFSsX9ezVlkr6gwaOpLbLixfPtm7TYMP6Xan2onVrt2/btqH/wK4U6NRJ8v3oSfrXBhjaBDXhzPPkMTN04c+Pl4+Hdp9ShInTgTUvosOT+s4sxMzJjkUvwj4mdhqbkTSHLIiNkm1f8GTIErHuxsaAkqD+xP0lyplnTcigp8hAurCx00II6s08TzbWm6LIb37XE1TeDZmJGjURUoevtrGbN+1RndZnDlDxSwshmFMoTpGRml+Ky0XfHkOtt2vWbNU21qwSkKFjRBOEYE6h+Hma+d3SSFE8Ff/N14Uf5IkCOkbSQgjqjcf+YwS45aaJoVEwDYSg/sS995jpzdcZh8PSpNAomAZCUG9iv9GSWb4BxcmLOCohWyEE9YbqsBFwqA6bFjpG0kII6k38p8iY4S035TJzvPOJBcM3eVr47bDexF4S5MzxjDyJVHUpADAFNMCmhZKg3sS++yhKgszcUOHUAk6RERH0i6SFEMwIfIsaHNoEIbshBPWGjhFjMMff8kHOghDUl9Sal9qIuPlKYiW3tje7QpeNHW8l5q0qOjImE/uPtQ0O20NfpWs4yZNE3JEZHS7P5WHNzIxXIfvEeBkDU7l/McLaloE6hKC+7J3s7Z25I5ueMxFKSEiIjZIFDsjHzMwXzTypw+bWuQ8MTOLx9XDvgnYM1CAEM6DX1MIfXyWc2CW+HNyx4HmlBuZ1OROVVgN8rx0Pe/M0moGR/f7jYxt7qRl+F2YvXFk6w1ZPCJJKJE5uUhs7a3mi2giJ8ldgynt5MMWV8pS3uORYcneKRO3q9lKeWmaUj3hOwglnrvDKx4qJ+U/z0iMaIlfeLJbjhNk5Cc/LueQvL3nyYpXz0gMu+VU+vRYnSYoMk0WHyxp29ixWyZWZq6iwhA0zn9s5cM5uNpyU4+SfvpvpXafdP9W3JJe8tVU45Y8D1U8GSrWMT59L6hkVC5byclnqgcmzS9LcnED4ZCWablqgYSDPpz3HSvXZfTrtQPGIV72uYo4UZzUpp+cUh6zaDqY2lpd/WpRqrxPGWPNx0UkRHxOd3a27jC3IICWEYGYc3/b61ePYhGiJTO3iVJwyBFWbM1UIqu+yEgn79DMJ9RBUJpvykFOFIKfY5ZOPHmHJwryqIaojnFObUTXQ1k7i4iEJHOirftc0s7V/zcuQt0mx0UmfMj7VsfzpPaqFmoaQVF6QId0Q1Jyunz8XXS8qUN7HWUYbNu3xkzqemOYM1LgOaqOVn7489WIl9B2hnC3Vqyi+JeW8xjsvW9tJ7OxZ4YqO1Rp6MkgDIQiQGdevX1+2bNm6desYiBxOkQHIjKSkJOGmcSB2+BQBMiMxMdHa2uxOOYJMQAgCZAZKghYDnyJAZiAELQY+RYDMQAhaDHyKAJmBELQY+BQBMgMdIxYDIQiQGSgJWgx8igCZgRC0GPgUATIDIWgx8CkCZAbaBC0GQhAgM1AStBj4FAEyAyFoMXBRVYDMQAhaDHyKAJmBELQY+BQBMgMdIxYDIQiQGSgJWgx8igCZgRC0GPgUATIDIWgx8CkCZAbaBC0GQhAgM1AStBj4FAEyAyFoMfApAmQGQtBi4FMEyAwHBweEoGXApwiQGfFKDMQPIQiQGVQMpBoxA/FDCAJkBkLQYiAEATIDIWgxEIIAmYEQtBgIQYDMQAhaDIQgQGYgBC0GQhAgMxCCFgMhCJAZCEGLgRAEyAyEoMVACAJkhrW1dWJiIgPxw93mADIDJUGLgZIgQGYgBC0GQhAgMxCCFgMhCJAZCEGLgRAEyAyEoMVACAJkBkLQYnA8zzMA0E/79u0fPXrEK3FK9MDHx+fPP/9kIE44RQYgA/r06ePozgHkOgAAB7VJREFU6CiRSKRSKf2lEKSB1atXZyBaCEGADGjcuLG/v7/6ECoGdu7cmYFoIQQBMqZnz56urq6qp+XKlStcuDAD0UIIAmRM3bp1ixYtKjzOnTt3165dGYgZQhAgw6hl0NnZmR6ULFmydOnSDMQMvcNg4WJjZTf/CQt9Gx8Xw8tlnGq4okuD9n0p42XK53QgcJxEyuQyxSheziunUD6myTg6VBSTqx48fPAwIjKiWLGizs4uwqKEA4mT8rzqVZTDhddRxymGcupHntSK5yTM0dUqX1H7YhVcGJgQQhAs08PrEZeOhIR/lCUl8RKJIssUPbnJO7sil5T/55LzTplTiuiiSeVyIaE4YRgn5KNyLj45GZniDBkm53mphPu0QGEZtABOLk/Ow0/zcp//qiYWRn0ikSqORBn9P1F4ygqWdmjeKy8D40MIgqW5cz7szP6QhDi5jb3U1ccpj787E5XY8Ng3D0PjIxJkSby7j3XnMQUZGBNCECzKpllPIkJlTrntCwZ4M5GLDot9fuOtLJ6v1CjXF009GBgHQhAsx8/fB1nZWxX9Ij+zICFvIl7f/ujmZdVljB8DI0AIgoVYPiIoT1G3PIVyMUt099STfIUdvv4WrYSGhxAES7BiZFDhWj529nbMct09+dTeQdpzih8Dg8J5giB6K0cH5SvnadkJSErW9YtP4H9f+oKBQSEEQdz+N/mxQy5bVy8nlgMUr1Xg/YuEm2fCGBgOQhBE7MSu4NgYuV+lHNRSlruQ6+k9HxgYDkIQROze+SgPC+0J0cbL342TSvb/8oqBgSAEQaxO/P6WevUoFFgOk7ugy4sHsQwMBCEIYhV0PcrBzXw7Q67f/Gv0pGpR0aHM0Dz93BjPLh79yMAQEIIgVvExfP7yeViOZONgc+9iJANDQAiCKJ3Z915ixUmlUpYjOeWxi4nEbZ4MA3ebA1F68zROYs0xo3n6/L+jJ9a+eHnHydGtZPFajb7qa2fnSMM3bZ/AGFexfJPtu6fHx8cUzF+2eePvCuYvI8x14PCyyzcO2to4VCjXOI9HAWY07vmdPzyKYGAIKAmCKMVEJFlZG+sr/MPHF6vXD0lMjP+u39oenee9efvw5/8NlMkUJS+JxOrZi5tXrh8aNmD97MmnrKxttu2eLsx19uKusxd3ftP8+2H9f83tlvfYiXXMaGxsbDiOPb6FGrEBIARBlJISeYmNsfbeqzcOW0mte3aa5+Xp553Hv13gxFdv7t+6e0oYSwXADq1/yO3uK5VaVSzX+P2HZzSEhp8+t6Nc6frlytRzcHCpUrFFEf/KzJgoBMM/okZsAAhBECUqlnFG+9U71YXz5yvl6Jh8BqK7m09u93xPnl0Xnubx9LO1dRAe29kpLrIfExvB8/yHkBdeeQqpFpIvbwlmTPTu+SQjNgjkHGgTBFGyseWSZHJmHLFxUS9e3Rk9qZr6wIjI5FNSOE5D0SEuPloul6nCUbGGNvbMmHg5s3VkkHUIQRAlK2suLlLGjMPZOXehggGN6/VTH+jo6KpjFjtbR4lEmpgYpxoSnxDDjCx/MVsGWYYQBFFy87YN+xDNjCOvV9ErNw76+1WQSJILfcHvHnvm1tXby3GcWy6fp89v1qmZPOTu/TPMaMKCIxnHXNyNW9jMIdAmCKJU/ktX3li1YVa7Rie5XL7v0I8JCXHv3j87cGT5ouWd37wN0j1X+TINbt45cf3mX/T47383Pnt5ixlN6MtIGzs0CBoGQhBEybeIovXtTZBRrqdC3bujv9tqY22/ZFWP+T+1f/z0artWE9Pt6GhQp1e1SoF7Di6ixkQqBrZsOpwpb0vHjCAuMsHHz8Kvn2gyuLI0iNX2H5+FvksqUduP5TAymezu8eff/ViEgSGgJAhi1XZovqS4nPgV/uRisKNrDv29oDGgYwTESiqVuuSW3v/3efEvNXdZvAkOWrGuv5a5OcY0ByhVab9uMpQZzg+z6mscLpcrbrYulWo4BgPKNGwbOI5pQXXhbuN9GRgIqsMgbstHBOULyJ0rj0vaUTJZUnS05ivRx8fHqJ/Tp87axs7ezpAX64+I0NpwmShLsJbasIysw91TT3Llseo00o+BgaAkCOJWrZn7hUMfczXUEIJUyHJxyf57lhtwHV7dfccnMSSgYaFNEMStSkN3H3+7u6eeMUsXFR4V+jJ60EL0hxgYqsNgCc7++fHa36GlGxRiFio0OOL1rY+DFyEBDQ8hCBZiz88vXz+OL1TVx97J0n5M9uTy69iw+EFIQONACILlOLv//bWT4fauNv5VLKTzNOx15Ou7H62sWb85hRkYB0IQLM2GGU+jwpLsnG28irk5uTkwcXp9933o6yhexopWcmzc1YeB0SAEwQK9fBD1944PkaFJnIST2khsHKxt7Kyl1lKJVYqeQI7R3p/qF7g8l/JChRrPJ+SVXYqphiuWlXJhwjT6HGAcJ5clyBLjZXFRiUlxMlminJOw/MXtWvbLx8DIEIJgyc4fev/ifmxEqCwhVi5L4lNfh5VTxmCqIZRa6aZgWhyTU+qlXr7yb6qBEpo09RI5K4prJrVm1jaS3HltKjd08/ETaxlWdBCCAJCj4WRpAMjREIIAkKMhBAEgR0MIAkCOhhAEgBwNIQgAOdr/AQAA//+t2zc5AAAABklEQVQDAAfU67jZBd+iAAAAAElFTkSuQmCC", + "image/png": "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", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -1773,7 +1706,7 @@ }, { "cell_type": "code", - "execution_count": 69, + "execution_count": 47, "id": "0edf8d59", "metadata": {}, "outputs": [], @@ -1802,7 +1735,7 @@ }, { "cell_type": "code", - "execution_count": 60, + "execution_count": 48, "id": "da3df5a4", "metadata": {}, "outputs": [], @@ -1843,7 +1776,7 @@ }, { "cell_type": "code", - "execution_count": 70, + "execution_count": 79, "id": "a95b4db7", "metadata": {}, "outputs": [], @@ -1861,24 +1794,27 @@ " \n", "}\n", "import uuid\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "id": "09b48e2a", + "metadata": {}, + "outputs": [], + "source": [ "\n", "\n", "checkpointer = MemorySaver() \n", - "graph = builder.compile(checkpointer=checkpointer)\n", + "graph = builder.compile(checkpointer=checkpointer,debug=True)\n", "\n", - "THREAD_ID = str(uuid.uuid4())\n", - "\n", - "\n", - "\n", - "config = {\"configurable\": {\"thread_id\": THREAD_ID,\"langgraph_user_id\": \"Chirayu Jain\"}}\n", - "\n", - "# final_state = graph.invoke(initial_input, config=config)\n", - "\n" + "THREAD_ID = str(uuid.uuid4())\n" ] }, { "cell_type": "code", - "execution_count": 90, + "execution_count": 60, "id": "093bdd6e", "metadata": {}, "outputs": [], @@ -1937,17 +1873,26 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 152, "id": "db595a54", "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "SyntaxError", + "evalue": "invalid syntax (1106862335.py, line 1)", + "output_type": "error", + "traceback": [ + " \u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[152]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[31m \u001b[39m\u001b[31m///break\u001b[39m\n ^\n\u001b[31mSyntaxError\u001b[39m\u001b[31m:\u001b[39m invalid syntax\n" + ] + } + ], "source": [ "///break" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 80, "id": "7a36ecb1", "metadata": {}, "outputs": [ @@ -1955,58 +1900,417 @@ "name": "stdout", "output_type": "stream", "text": [ - "🚀 Starting Graph Stream...\n", - "\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': None, 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [], 'skill_gap_analysis_data': None, 'resume_data': None, 'extraction_error': None, 'JobDescriptionExtract_data': None}\n", "📂 File path received: C:\\Users\\ATHARVA\\Downloads\\my codes\\web\\AdaptiveEngineService\\AI_Engine_Evaluation\\Testcases\\Testresume\\ChirayuResume.pdf\n", "📂 File exists: True\n", "📄 Pages loaded: 1\n", "📄 Text length: 3156\n", - "--- 📍 Node: input_node ---\n", - "\n", - "==================================================\n", - "\n", + "\u001b[1m[updates]\u001b[0m {'input_node': {'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'extraction_error': None}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [], 'skill_gap_analysis_data': None, 'resume_data': None, 'extraction_error': None, 'JobDescriptionExtract_data': None}\n", "DEBUGGER: Sending 525 characters to JD Agent...\n", "📄 Resume text length: 3156 chars\n", "DEBUGGER SUCCESS: Extracted Backend Developer\n", - "✅ Resume extracted: Software Developer\n", - "--- 📍 Node: jd_data_extraction ---\n", - "✅ Extracted JD: Backend Developer\n", + "✅ Resume extracted: SOFTWARE DEVELOPER\n", + "\u001b[1m[updates]\u001b[0m {'jd_data_extraction': {'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}}\n", + "\u001b[1m[updates]\u001b[0m {'resume_data_extraction': {'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False)}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [], 'skill_gap_analysis_data': None, 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}\n", "\n", - "==================================================\n", + "================================================================================\n", + "🔍 SKILL GAP NODE - DEBUG INFO\n", + "================================================================================\n", + "✅ Candidate Name: Chirayu Jain\n", + "✅ Resume Data Type: \n", + "✅ JD Data Type: \n", "\n", - "--- 📍 Node: resume_data_extraction ---\n", - "✅ Extracted Resume for: Chirayu Jain\n", + "--------------------------------------------------------------------------------\n", + "📄 LEAN RESUME DICT (before JSON):\n", + "--------------------------------------------------------------------------------\n", + "{\n", + " \"candidate_name\": \"Chirayu Jain\",\n", + " \"job_title\": \"SOFTWARE DEVELOPER\",\n", + " \"skills\": [\n", + " {\n", + " \"name\": \"C/C++\"\n", + " },\n", + " {\n", + " \"name\": \"Java\"\n", + " },\n", + " {\n", + " \"name\": \"Python\"\n", + " },\n", + " {\n", + " \"name\": \"JavaScript\"\n", + " },\n", + " {\n", + " \"name\": \"Dart\"\n", + " },\n", + " {\n", + " \"name\": \"Flutter\"\n", + " },\n", + " {\n", + " \"name\": \"HTML/CSS\"\n", + " },\n", + " {\n", + " \"name\": \"ReactJS\"\n", + " },\n", + " {\n", + " \"name\": \"Firebase\"\n", + " },\n", + " {\n", + " \"name\": \"REST APIs\"\n", + " },\n", + " {\n", + " \"name\": \"Flask\"\n", + " },\n", + " {\n", + " \"name\": \"Django\"\n", + " },\n", + " {\n", + " \"name\": \"NodeJS\"\n", + " },\n", + " {\n", + " \"name\": \"ExpressJS\"\n", + " },\n", + " {\n", + " \"name\": \"MySQL\"\n", + " },\n", + " {\n", + " \"name\": \"MongoDB\"\n", + " },\n", + " {\n", + " \"name\": \"SQLite\"\n", + " }\n", + " ],\n", + " \"experience\": [\n", + " {\n", + " \"job_title\": \"Technology Intern\",\n", + " \"technologies\": [\n", + " \"Flask\",\n", + " \"PyMuPDF\",\n", + " \"Docling\",\n", + " \"OCR extraction\",\n", + " \"Cron-based background workers\"\n", + " ],\n", + " \"responsibilities\": [\n", + " \"Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20\\u201330 minutes to 2\\u20133 minutes.\",\n", + " \"Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.\",\n", + " \"Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.\"\n", + " ]\n", + " },\n", + " {\n", + " \"job_title\": \"Software Development intern\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"MVVM\",\n", + " \"SOLID\",\n", + " \"modular design\"\n", + " ],\n", + " \"responsibilities\": [\n", + " \"Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.\",\n", + " \"Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\",\n", + " \"Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\"\n", + " ]\n", + " }\n", + " ],\n", + " \"projects\": [\n", + " {\n", + " \"name\": \"Hostel Bites \\u2013 IIITK Canteen App\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"Dart\",\n", + " \"Firebase\",\n", + " \"Cloud Firestore\",\n", + " \"Mapbox API\"\n", + " ]\n", + " },\n", + " {\n", + " \"name\": \"JobShield - Fake Job Detector\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"Dart\",\n", + " \"Python\",\n", + " \"Flask\",\n", + " \"SQLite\"\n", + " ]\n", + " }\n", + " ],\n", + " \"is_fresher\": false\n", + "}\n", "\n", - "==================================================\n", + "--------------------------------------------------------------------------------\n", + "📄 LEAN JD DICT (before JSON):\n", + "--------------------------------------------------------------------------------\n", + "{\n", + " \"job_title\": \"Backend Developer\",\n", + " \"company_name\": \"CodeForge\",\n", + " \"skills_required\": [\n", + " {\n", + " \"name\": \"Python\"\n", + " },\n", + " {\n", + " \"name\": \"FastAPI\"\n", + " },\n", + " {\n", + " \"name\": \"Django\"\n", + " },\n", + " {\n", + " \"name\": \"SQL\"\n", + " },\n", + " {\n", + " \"name\": \"PostgreSQL\"\n", + " },\n", + " {\n", + " \"name\": \"Docker\"\n", + " }\n", + " ]\n", + "}\n", "\n", - "--- 📍 Node: skill_gap_analysis ---\n", - "🧠 AI THOUGHT: Skill Gap Analysis Completed for Chirayu Jain. Gaps Identified: { \"job_title\": \"Backend Developer\", \"candidate_name\": \"C...\n", - "🎯 Skill Gap Analysis Completed.\n", + "--------------------------------------------------------------------------------\n", + "📄 LEAN RESUME JSON (for prompt):\n", + "--------------------------------------------------------------------------------\n", + "{\n", + " \"candidate_name\": \"Chirayu Jain\",\n", + " \"job_title\": \"SOFTWARE DEVELOPER\",\n", + " \"skills\": [\n", + " {\n", + " \"name\": \"C/C++\"\n", + " },\n", + " {\n", + " \"name\": \"Java\"\n", + " },\n", + " {\n", + " \"name\": \"Python\"\n", + " },\n", + " {\n", + " \"name\": \"JavaScript\"\n", + " },\n", + " {\n", + " \"name\": \"Dart\"\n", + " },\n", + " {\n", + " \"name\": \"Flutter\"\n", + " },\n", + " {\n", + " \"name\": \"HTML/CSS\"\n", + " },\n", + " {\n", + " \"name\": \"ReactJS\"\n", + " },\n", + " {\n", + " \"name\": \"Firebase\"\n", + " },\n", + " {\n", + " \"name\": \"REST APIs\"\n", + " },\n", + " {\n", + " \"name\": \"Flask\"\n", + " },\n", + " {\n", + " \"name\": \"Django\"\n", + " },\n", + " {\n", + " \"name\": \"NodeJS\"\n", + " },\n", + " {\n", + " \"name\": \"ExpressJS\"\n", + " },\n", + " {\n", + " \"name\": \"MySQL\"\n", + " },\n", + " {\n", + " \"name\": \"MongoDB\"\n", + " },\n", + " {\n", + " \"name\": \"SQLite\"\n", + " }\n", + " ],\n", + " \"experience\": [\n", + " {\n", + " \"job_title\": \"Technology Intern\",\n", + " \"technologies\": [\n", + " \"Flask\",\n", + " \"PyMuPDF\",\n", + " \"Docling\",\n", + " \"OCR extraction\",\n", + " \"Cron-based background workers\"\n", + " ],\n", + " \"responsibilities\": [\n", + " \"Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20\\u201330 minutes to 2\\u20133 minutes.\",\n", + " \"Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.\",\n", + " \"Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.\"\n", + " ]\n", + " },\n", + " {\n", + " \"job_title\": \"Software Development intern\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"MVVM\",\n", + " \"SOLID\",\n", + " \"modular design\"\n", + " ],\n", + " \"responsibilities\": [\n", + " \"Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.\",\n", + " \"Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\",\n", + " \"Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\"\n", + " ]\n", + " }\n", + " ],\n", + " \"projects\": [\n", + " {\n", + " \"name\": \"Hostel Bites \\u2013 IIITK Canteen App\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"Dart\",\n", + " \"Firebase\",\n", + " \"Cloud Firestore\",\n", + " \"Mapbox API\"\n", + " ]\n", + " },\n", + " {\n", + " \"name\": \"JobShield - Fake Job Detector\",\n", + " \"technologies\": [\n", + " \"Flutter\",\n", + " \"Dart\",\n", + " \"Python\",\n", + " \"Flask\",\n", + " \"SQLite\"\n", + " ]\n", + " }\n", + " ],\n", + " \"is_fresher\": false\n", + "}\n", "\n", - "==================================================\n", + "--------------------------------------------------------------------------------\n", + "📄 LEAN JD JSON (for prompt):\n", + "--------------------------------------------------------------------------------\n", + "{\n", + " \"job_title\": \"Backend Developer\",\n", + " \"company_name\": \"CodeForge\",\n", + " \"skills_required\": [\n", + " {\n", + " \"name\": \"Python\"\n", + " },\n", + " {\n", + " \"name\": \"FastAPI\"\n", + " },\n", + " {\n", + " \"name\": \"Django\"\n", + " },\n", + " {\n", + " \"name\": \"SQL\"\n", + " },\n", + " {\n", + " \"name\": \"PostgreSQL\"\n", + " },\n", + " {\n", + " \"name\": \"Docker\"\n", + " }\n", + " ]\n", + "}\n", "\n", - "--- 📍 Node: roadmap_planning_agent ---\n", - "🧠 AI THOUGHT: The learning roadmap for **Chirayu Jain** has been finalized and visualized. **Roadmap Summary** - **Target Role:** Backend Developer - **Onboardin...\n", - "\n", - "==================================================\n", - "\n", - "--- 📍 Node: finalize_state ---\n", - "🏁 Final Roadmap Constructed.\n", - "\n", - "==================================================\n", - "\n", - "✨ Stream Finished. Final state captured.\n" + "================================================================================\n", + "\u001b[1m[updates]\u001b[0m {'skill_gap_analysis': {'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb')]}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb')], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}\n", + "\u001b[1m[updates]\u001b[0m {'roadmap_planning_agent': {'messages': [AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}})]}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb'), AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}})], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}\n", + "\u001b[1m[updates]\u001b[0m {'tools': {'messages': [ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\n---\", name='search_courses', id='81dc0c18-afd0-48cf-93e2-3f84aeb4697d', tool_call_id='tk112hq0c'), ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\n---', name='search_courses', id='7d61cda6-fd9d-4f36-8b71-8df2e24b95fb', tool_call_id='z12xgzqbr'), ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\n---', name='search_courses', id='eda8cd08-a93d-4b9e-8ed4-c2af30a4b4fc', tool_call_id='z2ccjm3w2')]}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb'), AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}}), ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\n---\", name='search_courses', id='81dc0c18-afd0-48cf-93e2-3f84aeb4697d', tool_call_id='tk112hq0c'), ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\n---', name='search_courses', id='7d61cda6-fd9d-4f36-8b71-8df2e24b95fb', tool_call_id='z12xgzqbr'), ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\n---', name='search_courses', id='eda8cd08-a93d-4b9e-8ed4-c2af30a4b4fc', tool_call_id='z2ccjm3w2')], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}\n", + "\u001b[1m[updates]\u001b[0m {'roadmap_planning_agent': {'messages': [AIMessage(content='', additional_kwargs={'reasoning_content': \"Okay, let's start by looking at the user's problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the skill gaps identified. The gaps are in FastAPI, PostgreSQL, and Docker. The user has provided the search results for each of these skills, and now I need to sequence them into a logical order.\\n\\nFirst, I need to check if any foundational courses are required. The user mentioned that is_fresher_adaptation_needed is False, so we don't need to add any professional fundamentals first. That means we can start directly with the identified gaps.\\n\\nLooking at the FastAPI courses, there's CS-FAST-101 and CS-FAST-201. Since the target competency is to develop high-performance asynchronous APIs, the first course (CS-FAST-101) is the foundation. The advanced course (CS-FAST-201) would come after mastering the basics.\\n\\nFor PostgreSQL, the relevant courses are CS-DB-101 and CS-DB-201. The candidate has experience with MySQL and SQLite, so starting with CS-DB-101 makes sense to build a solid foundation in SQL fundamentals. Then, moving to CS-DB-201 for advanced topics like indexing and transactions.\\n\\nFor Docker, the course CS-DOCKER-101 is the fundamental one. The other Docker-related courses are either part of other tracks (like CS-CICD-201 for CI/CD) or part of MLOps, which isn't the focus here. So CS-DOCKER-101 is the right choice here.\\n\\nNow, sequencing these courses. The order should allow Chirayu to build skills progressively. Starting with FastAPI makes sense because it's a framework he's somewhat familiar with (Python and Flask), so transitioning to FastAPI would be logical. Then, moving to PostgreSQL to handle database management, followed by Docker for containerization. Each of these can be spread over weeks, maybe one course per week.\\n\\nI need to assign sequence_order numbers. Let's see:\\n\\n1. FastAPI Fundamentals (CS-FAST-101) - Week 1\\n2. PostgreSQL Fundamentals (CS-DB-101) - Week 2\\n3. Docker Fundamentals (CS-DOCKER-101) - Week 3\\n4. Advanced FastAPI (CS-FAST-201) - Week 4\\n5. Advanced PostgreSQL (CS-DB-201) - Week 5\\n\\nThis order ensures that foundational skills are built first before moving to advanced topics. Each course is a prerequisite for the next in their respective tracks. The Mermaid diagram should reflect this sequence with subgraphs for each week.\\n\\nI also need to make sure that the reasoning for each course choice is clear. For example, CS-FAST-101 is chosen because it covers the basics needed for developing APIs with FastAPI, which is a high-priority gap. Similarly, CS-DB-101 provides the necessary SQL fundamentals before moving to advanced PostgreSQL topics.\\n\\nFinally, compiling all this into the required JSON format for the final roadmap and the Mermaid visualization. Double-checking that all course IDs are from the search results and that the sequence makes logical sense for skill progression.\\n\", 'tool_calls': [{'id': 'mm78w2e88', 'function': {'arguments': '{\"candidate_name\":\"Chirayu Jain\",\"onboarding_summary\":\"4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.\",\"roadmap\":[{\"course_id\":\"CS-FAST-101\",\"is_foundation\":true,\"reasoning\":\"Foundational course to build FastAPI skills required for high-performance API development\",\"sequence_order\":1,\"title\":\"REST API Development with FastAPI\"},{\"course_id\":\"CS-DB-101\",\"is_foundation\":true,\"reasoning\":\"Establish PostgreSQL foundation before advanced database work\",\"sequence_order\":2,\"title\":\"SQL Fundamentals for Backend Developers\"},{\"course_id\":\"CS-DOCKER-101\",\"is_foundation\":true,\"reasoning\":\"Core containerization skills needed for consistent deployment\",\"sequence_order\":3,\"title\":\"Docker \\\\u0026 Containerization Fundamentals\"},{\"course_id\":\"CS-FAST-201\",\"is_foundation\":false,\"reasoning\":\"Build on FastAPI fundamentals with async database integration\",\"sequence_order\":4,\"title\":\"Advanced API Design with FastAPI\"},{\"course_id\":\"CS-DB-201\",\"is_foundation\":false,\"reasoning\":\"Deepen PostgreSQL expertise for production-grade database work\",\"sequence_order\":5,\"title\":\"Advanced SQL - Indexing, Transactions \\\\u0026 Query Optimization\"}],\"target_role\":\"Backend Developer\"}', 'name': 'submit_final_roadmap'}, 'type': 'function'}, {'id': 'h9phazqpb', 'function': {'arguments': '{\"mermaid_code\":\"flowchart TD\\\\n A([Start]):::start\\\\n subgraph W1[\\\\\"Week 1\\\\\"]\\\\n B[CS-FAST-101]:::gap\\\\n end\\\\n subgraph W2[\\\\\"Week 2\\\\\"]\\\\n C[CS-DB-101]:::gap\\\\n end\\\\n subgraph W3[\\\\\"Week 3\\\\\"]\\\\n D[CS-DOCKER-101]:::gap\\\\n end\\\\n subgraph W4[\\\\\"Week 4\\\\\"]\\\\n E[CS-FAST-201]:::gap\\\\n end\\\\n subgraph W5[\\\\\"Week 5\\\\\"]\\\\n F[CS-DB-201]:::gap\\\\n end\\\\n Z([Ready]):::done\\\\n A --\\\\u003e B --\\\\u003e C --\\\\u003e D --\\\\u003e E --\\\\u003e F --\\\\u003e Z\\\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\\\n classDef start fill:#1D9E75,stroke:#0F6E56\\\\n classDef done fill:#534AB7,stroke:#3C3489\"}', 'name': 'submit_mermaid_visualization'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 1350, 'prompt_tokens': 3008, 'total_tokens': 4358, 'completion_time': 2.38863248, 'completion_tokens_details': {'reasoning_tokens': 685}, 'prompt_time': 0.136514084, 'prompt_tokens_details': None, 'queue_time': 0.044030126, 'total_time': 2.525146564}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-be3d-7de2-9310-9fbcc34ce8b8-0', tool_calls=[{'name': 'submit_final_roadmap', 'args': {'candidate_name': 'Chirayu Jain', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'is_foundation': True, 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'sequence_order': 1, 'title': 'REST API Development with FastAPI'}, {'course_id': 'CS-DB-101', 'is_foundation': True, 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'sequence_order': 2, 'title': 'SQL Fundamentals for Backend Developers'}, {'course_id': 'CS-DOCKER-101', 'is_foundation': True, 'reasoning': 'Core containerization skills needed for consistent deployment', 'sequence_order': 3, 'title': 'Docker & Containerization Fundamentals'}, {'course_id': 'CS-FAST-201', 'is_foundation': False, 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'sequence_order': 4, 'title': 'Advanced API Design with FastAPI'}, {'course_id': 'CS-DB-201', 'is_foundation': False, 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'sequence_order': 5, 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization'}], 'target_role': 'Backend Developer'}, 'id': 'mm78w2e88', 'type': 'tool_call'}, {'name': 'submit_mermaid_visualization', 'args': {'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489'}, 'id': 'h9phazqpb', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 3008, 'output_tokens': 1350, 'total_tokens': 4358, 'output_token_details': {'reasoning': 685}})]}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb'), AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}}), ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\n---\", name='search_courses', id='81dc0c18-afd0-48cf-93e2-3f84aeb4697d', tool_call_id='tk112hq0c'), ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\n---', name='search_courses', id='7d61cda6-fd9d-4f36-8b71-8df2e24b95fb', tool_call_id='z12xgzqbr'), ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\n---', name='search_courses', id='eda8cd08-a93d-4b9e-8ed4-c2af30a4b4fc', tool_call_id='z2ccjm3w2'), AIMessage(content='', additional_kwargs={'reasoning_content': \"Okay, let's start by looking at the user's problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the skill gaps identified. The gaps are in FastAPI, PostgreSQL, and Docker. The user has provided the search results for each of these skills, and now I need to sequence them into a logical order.\\n\\nFirst, I need to check if any foundational courses are required. The user mentioned that is_fresher_adaptation_needed is False, so we don't need to add any professional fundamentals first. That means we can start directly with the identified gaps.\\n\\nLooking at the FastAPI courses, there's CS-FAST-101 and CS-FAST-201. Since the target competency is to develop high-performance asynchronous APIs, the first course (CS-FAST-101) is the foundation. The advanced course (CS-FAST-201) would come after mastering the basics.\\n\\nFor PostgreSQL, the relevant courses are CS-DB-101 and CS-DB-201. The candidate has experience with MySQL and SQLite, so starting with CS-DB-101 makes sense to build a solid foundation in SQL fundamentals. Then, moving to CS-DB-201 for advanced topics like indexing and transactions.\\n\\nFor Docker, the course CS-DOCKER-101 is the fundamental one. The other Docker-related courses are either part of other tracks (like CS-CICD-201 for CI/CD) or part of MLOps, which isn't the focus here. So CS-DOCKER-101 is the right choice here.\\n\\nNow, sequencing these courses. The order should allow Chirayu to build skills progressively. Starting with FastAPI makes sense because it's a framework he's somewhat familiar with (Python and Flask), so transitioning to FastAPI would be logical. Then, moving to PostgreSQL to handle database management, followed by Docker for containerization. Each of these can be spread over weeks, maybe one course per week.\\n\\nI need to assign sequence_order numbers. Let's see:\\n\\n1. FastAPI Fundamentals (CS-FAST-101) - Week 1\\n2. PostgreSQL Fundamentals (CS-DB-101) - Week 2\\n3. Docker Fundamentals (CS-DOCKER-101) - Week 3\\n4. Advanced FastAPI (CS-FAST-201) - Week 4\\n5. Advanced PostgreSQL (CS-DB-201) - Week 5\\n\\nThis order ensures that foundational skills are built first before moving to advanced topics. Each course is a prerequisite for the next in their respective tracks. The Mermaid diagram should reflect this sequence with subgraphs for each week.\\n\\nI also need to make sure that the reasoning for each course choice is clear. For example, CS-FAST-101 is chosen because it covers the basics needed for developing APIs with FastAPI, which is a high-priority gap. Similarly, CS-DB-101 provides the necessary SQL fundamentals before moving to advanced PostgreSQL topics.\\n\\nFinally, compiling all this into the required JSON format for the final roadmap and the Mermaid visualization. Double-checking that all course IDs are from the search results and that the sequence makes logical sense for skill progression.\\n\", 'tool_calls': [{'id': 'mm78w2e88', 'function': {'arguments': '{\"candidate_name\":\"Chirayu Jain\",\"onboarding_summary\":\"4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.\",\"roadmap\":[{\"course_id\":\"CS-FAST-101\",\"is_foundation\":true,\"reasoning\":\"Foundational course to build FastAPI skills required for high-performance API development\",\"sequence_order\":1,\"title\":\"REST API Development with FastAPI\"},{\"course_id\":\"CS-DB-101\",\"is_foundation\":true,\"reasoning\":\"Establish PostgreSQL foundation before advanced database work\",\"sequence_order\":2,\"title\":\"SQL Fundamentals for Backend Developers\"},{\"course_id\":\"CS-DOCKER-101\",\"is_foundation\":true,\"reasoning\":\"Core containerization skills needed for consistent deployment\",\"sequence_order\":3,\"title\":\"Docker \\\\u0026 Containerization Fundamentals\"},{\"course_id\":\"CS-FAST-201\",\"is_foundation\":false,\"reasoning\":\"Build on FastAPI fundamentals with async database integration\",\"sequence_order\":4,\"title\":\"Advanced API Design with FastAPI\"},{\"course_id\":\"CS-DB-201\",\"is_foundation\":false,\"reasoning\":\"Deepen PostgreSQL expertise for production-grade database work\",\"sequence_order\":5,\"title\":\"Advanced SQL - Indexing, Transactions \\\\u0026 Query Optimization\"}],\"target_role\":\"Backend Developer\"}', 'name': 'submit_final_roadmap'}, 'type': 'function'}, {'id': 'h9phazqpb', 'function': {'arguments': '{\"mermaid_code\":\"flowchart TD\\\\n A([Start]):::start\\\\n subgraph W1[\\\\\"Week 1\\\\\"]\\\\n B[CS-FAST-101]:::gap\\\\n end\\\\n subgraph W2[\\\\\"Week 2\\\\\"]\\\\n C[CS-DB-101]:::gap\\\\n end\\\\n subgraph W3[\\\\\"Week 3\\\\\"]\\\\n D[CS-DOCKER-101]:::gap\\\\n end\\\\n subgraph W4[\\\\\"Week 4\\\\\"]\\\\n E[CS-FAST-201]:::gap\\\\n end\\\\n subgraph W5[\\\\\"Week 5\\\\\"]\\\\n F[CS-DB-201]:::gap\\\\n end\\\\n Z([Ready]):::done\\\\n A --\\\\u003e B --\\\\u003e C --\\\\u003e D --\\\\u003e E --\\\\u003e F --\\\\u003e Z\\\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\\\n classDef start fill:#1D9E75,stroke:#0F6E56\\\\n classDef done fill:#534AB7,stroke:#3C3489\"}', 'name': 'submit_mermaid_visualization'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 1350, 'prompt_tokens': 3008, 'total_tokens': 4358, 'completion_time': 2.38863248, 'completion_tokens_details': {'reasoning_tokens': 685}, 'prompt_time': 0.136514084, 'prompt_tokens_details': None, 'queue_time': 0.044030126, 'total_time': 2.525146564}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-be3d-7de2-9310-9fbcc34ce8b8-0', tool_calls=[{'name': 'submit_final_roadmap', 'args': {'candidate_name': 'Chirayu Jain', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'is_foundation': True, 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'sequence_order': 1, 'title': 'REST API Development with FastAPI'}, {'course_id': 'CS-DB-101', 'is_foundation': True, 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'sequence_order': 2, 'title': 'SQL Fundamentals for Backend Developers'}, {'course_id': 'CS-DOCKER-101', 'is_foundation': True, 'reasoning': 'Core containerization skills needed for consistent deployment', 'sequence_order': 3, 'title': 'Docker & Containerization Fundamentals'}, {'course_id': 'CS-FAST-201', 'is_foundation': False, 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'sequence_order': 4, 'title': 'Advanced API Design with FastAPI'}, {'course_id': 'CS-DB-201', 'is_foundation': False, 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'sequence_order': 5, 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization'}], 'target_role': 'Backend Developer'}, 'id': 'mm78w2e88', 'type': 'tool_call'}, {'name': 'submit_mermaid_visualization', 'args': {'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489'}, 'id': 'h9phazqpb', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 3008, 'output_tokens': 1350, 'total_tokens': 4358, 'output_token_details': {'reasoning': 685}})], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')])}\n", + "\u001b[1m[updates]\u001b[0m {'tools': [{'final_roadmap': {'candidate_name': 'Chirayu Jain', 'target_role': 'Backend Developer', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'title': 'REST API Development with FastAPI', 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'is_foundation': True, 'sequence_order': 1}, {'course_id': 'CS-DB-101', 'title': 'SQL Fundamentals for Backend Developers', 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'is_foundation': True, 'sequence_order': 2}, {'course_id': 'CS-DOCKER-101', 'title': 'Docker & Containerization Fundamentals', 'reasoning': 'Core containerization skills needed for consistent deployment', 'is_foundation': True, 'sequence_order': 3}, {'course_id': 'CS-FAST-201', 'title': 'Advanced API Design with FastAPI', 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'is_foundation': False, 'sequence_order': 4}, {'course_id': 'CS-DB-201', 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization', 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'is_foundation': False, 'sequence_order': 5}]}}, {'messages': [ToolMessage(content='SUCCESS: Final roadmap has been submitted and saved to state.', name='submit_final_roadmap', id='195a42f9-9bf9-4df4-a864-93dd6c497b98', tool_call_id='mm78w2e88')]}, {'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489'}, {'messages': [ToolMessage(content='SUCCESS: Mermaid visualization saved successfully.', name='submit_mermaid_visualization', id='e54942a8-a7e4-4ba2-adae-0df4d2fd46bd', tool_call_id='h9phazqpb')]}]}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb'), AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}}), ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\n---\", name='search_courses', id='81dc0c18-afd0-48cf-93e2-3f84aeb4697d', tool_call_id='tk112hq0c'), ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\n---', name='search_courses', id='7d61cda6-fd9d-4f36-8b71-8df2e24b95fb', tool_call_id='z12xgzqbr'), ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\n---', name='search_courses', id='eda8cd08-a93d-4b9e-8ed4-c2af30a4b4fc', tool_call_id='z2ccjm3w2'), AIMessage(content='', additional_kwargs={'reasoning_content': \"Okay, let's start by looking at the user's problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the skill gaps identified. The gaps are in FastAPI, PostgreSQL, and Docker. The user has provided the search results for each of these skills, and now I need to sequence them into a logical order.\\n\\nFirst, I need to check if any foundational courses are required. The user mentioned that is_fresher_adaptation_needed is False, so we don't need to add any professional fundamentals first. That means we can start directly with the identified gaps.\\n\\nLooking at the FastAPI courses, there's CS-FAST-101 and CS-FAST-201. Since the target competency is to develop high-performance asynchronous APIs, the first course (CS-FAST-101) is the foundation. The advanced course (CS-FAST-201) would come after mastering the basics.\\n\\nFor PostgreSQL, the relevant courses are CS-DB-101 and CS-DB-201. The candidate has experience with MySQL and SQLite, so starting with CS-DB-101 makes sense to build a solid foundation in SQL fundamentals. Then, moving to CS-DB-201 for advanced topics like indexing and transactions.\\n\\nFor Docker, the course CS-DOCKER-101 is the fundamental one. The other Docker-related courses are either part of other tracks (like CS-CICD-201 for CI/CD) or part of MLOps, which isn't the focus here. So CS-DOCKER-101 is the right choice here.\\n\\nNow, sequencing these courses. The order should allow Chirayu to build skills progressively. Starting with FastAPI makes sense because it's a framework he's somewhat familiar with (Python and Flask), so transitioning to FastAPI would be logical. Then, moving to PostgreSQL to handle database management, followed by Docker for containerization. Each of these can be spread over weeks, maybe one course per week.\\n\\nI need to assign sequence_order numbers. Let's see:\\n\\n1. FastAPI Fundamentals (CS-FAST-101) - Week 1\\n2. PostgreSQL Fundamentals (CS-DB-101) - Week 2\\n3. Docker Fundamentals (CS-DOCKER-101) - Week 3\\n4. Advanced FastAPI (CS-FAST-201) - Week 4\\n5. Advanced PostgreSQL (CS-DB-201) - Week 5\\n\\nThis order ensures that foundational skills are built first before moving to advanced topics. Each course is a prerequisite for the next in their respective tracks. The Mermaid diagram should reflect this sequence with subgraphs for each week.\\n\\nI also need to make sure that the reasoning for each course choice is clear. For example, CS-FAST-101 is chosen because it covers the basics needed for developing APIs with FastAPI, which is a high-priority gap. Similarly, CS-DB-101 provides the necessary SQL fundamentals before moving to advanced PostgreSQL topics.\\n\\nFinally, compiling all this into the required JSON format for the final roadmap and the Mermaid visualization. Double-checking that all course IDs are from the search results and that the sequence makes logical sense for skill progression.\\n\", 'tool_calls': [{'id': 'mm78w2e88', 'function': {'arguments': '{\"candidate_name\":\"Chirayu Jain\",\"onboarding_summary\":\"4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.\",\"roadmap\":[{\"course_id\":\"CS-FAST-101\",\"is_foundation\":true,\"reasoning\":\"Foundational course to build FastAPI skills required for high-performance API development\",\"sequence_order\":1,\"title\":\"REST API Development with FastAPI\"},{\"course_id\":\"CS-DB-101\",\"is_foundation\":true,\"reasoning\":\"Establish PostgreSQL foundation before advanced database work\",\"sequence_order\":2,\"title\":\"SQL Fundamentals for Backend Developers\"},{\"course_id\":\"CS-DOCKER-101\",\"is_foundation\":true,\"reasoning\":\"Core containerization skills needed for consistent deployment\",\"sequence_order\":3,\"title\":\"Docker \\\\u0026 Containerization Fundamentals\"},{\"course_id\":\"CS-FAST-201\",\"is_foundation\":false,\"reasoning\":\"Build on FastAPI fundamentals with async database integration\",\"sequence_order\":4,\"title\":\"Advanced API Design with FastAPI\"},{\"course_id\":\"CS-DB-201\",\"is_foundation\":false,\"reasoning\":\"Deepen PostgreSQL expertise for production-grade database work\",\"sequence_order\":5,\"title\":\"Advanced SQL - Indexing, Transactions \\\\u0026 Query Optimization\"}],\"target_role\":\"Backend Developer\"}', 'name': 'submit_final_roadmap'}, 'type': 'function'}, {'id': 'h9phazqpb', 'function': {'arguments': '{\"mermaid_code\":\"flowchart TD\\\\n A([Start]):::start\\\\n subgraph W1[\\\\\"Week 1\\\\\"]\\\\n B[CS-FAST-101]:::gap\\\\n end\\\\n subgraph W2[\\\\\"Week 2\\\\\"]\\\\n C[CS-DB-101]:::gap\\\\n end\\\\n subgraph W3[\\\\\"Week 3\\\\\"]\\\\n D[CS-DOCKER-101]:::gap\\\\n end\\\\n subgraph W4[\\\\\"Week 4\\\\\"]\\\\n E[CS-FAST-201]:::gap\\\\n end\\\\n subgraph W5[\\\\\"Week 5\\\\\"]\\\\n F[CS-DB-201]:::gap\\\\n end\\\\n Z([Ready]):::done\\\\n A --\\\\u003e B --\\\\u003e C --\\\\u003e D --\\\\u003e E --\\\\u003e F --\\\\u003e Z\\\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\\\n classDef start fill:#1D9E75,stroke:#0F6E56\\\\n classDef done fill:#534AB7,stroke:#3C3489\"}', 'name': 'submit_mermaid_visualization'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 1350, 'prompt_tokens': 3008, 'total_tokens': 4358, 'completion_time': 2.38863248, 'completion_tokens_details': {'reasoning_tokens': 685}, 'prompt_time': 0.136514084, 'prompt_tokens_details': None, 'queue_time': 0.044030126, 'total_time': 2.525146564}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-be3d-7de2-9310-9fbcc34ce8b8-0', tool_calls=[{'name': 'submit_final_roadmap', 'args': {'candidate_name': 'Chirayu Jain', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'is_foundation': True, 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'sequence_order': 1, 'title': 'REST API Development with FastAPI'}, {'course_id': 'CS-DB-101', 'is_foundation': True, 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'sequence_order': 2, 'title': 'SQL Fundamentals for Backend Developers'}, {'course_id': 'CS-DOCKER-101', 'is_foundation': True, 'reasoning': 'Core containerization skills needed for consistent deployment', 'sequence_order': 3, 'title': 'Docker & Containerization Fundamentals'}, {'course_id': 'CS-FAST-201', 'is_foundation': False, 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'sequence_order': 4, 'title': 'Advanced API Design with FastAPI'}, {'course_id': 'CS-DB-201', 'is_foundation': False, 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'sequence_order': 5, 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization'}], 'target_role': 'Backend Developer'}, 'id': 'mm78w2e88', 'type': 'tool_call'}, {'name': 'submit_mermaid_visualization', 'args': {'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489'}, 'id': 'h9phazqpb', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 3008, 'output_tokens': 1350, 'total_tokens': 4358, 'output_token_details': {'reasoning': 685}}), ToolMessage(content='SUCCESS: Final roadmap has been submitted and saved to state.', name='submit_final_roadmap', id='195a42f9-9bf9-4df4-a864-93dd6c497b98', tool_call_id='mm78w2e88'), ToolMessage(content='SUCCESS: Mermaid visualization saved successfully.', name='submit_mermaid_visualization', id='e54942a8-a7e4-4ba2-adae-0df4d2fd46bd', tool_call_id='h9phazqpb')], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')]), 'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489', 'final_roadmap': {'candidate_name': 'Chirayu Jain', 'target_role': 'Backend Developer', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'title': 'REST API Development with FastAPI', 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'is_foundation': True, 'sequence_order': 1}, {'course_id': 'CS-DB-101', 'title': 'SQL Fundamentals for Backend Developers', 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'is_foundation': True, 'sequence_order': 2}, {'course_id': 'CS-DOCKER-101', 'title': 'Docker & Containerization Fundamentals', 'reasoning': 'Core containerization skills needed for consistent deployment', 'is_foundation': True, 'sequence_order': 3}, {'course_id': 'CS-FAST-201', 'title': 'Advanced API Design with FastAPI', 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'is_foundation': False, 'sequence_order': 4}, {'course_id': 'CS-DB-201', 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization', 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'is_foundation': False, 'sequence_order': 5}]}}\n", + "\u001b[1m[updates]\u001b[0m {'roadmap_planning_agent': {'messages': [AIMessage(content='✅ **Onboarding Roadmap Finalized for Chirayu Jain** \\n**Target Role:** Backend Developer \\n**Duration:** 5 Weeks \\n\\n### 📌 Key Components \\n1. **Week 1:** FastAPI Fundamentals (CS-FAST-101) \\n2. **Week 2:** PostgreSQL Foundations (CS-DB-101) \\n3. **Week 3:** Docker Core Skills (CS-DOCKER-101) \\n4. **Week 4:** Advanced FastAPI (CS-FAST-201) \\n5. **Week 5:** PostgreSQL Optimization (CS-DB-201) \\n\\n### 📚 Course Rationale \\n- **CS-FAST-101** establishes core API development patterns required for CodeForge’s backend stack. \\n- **CS-DB-101** builds foundational PostgreSQL proficiency before advanced optimization. \\n- **CS-DOCKER-101** ensures containerization skills for deployment consistency. \\n- Advanced courses (CS-FAST-201, CS-DB-201) deepen expertise in async workflows and database performance. \\n\\n### 📊 Visual Roadmap \\nA Mermaid flowchart has been generated to visualize the sequence. \\n\\nLet me know if you need adjustments to the timeline or course selections!', additional_kwargs={'reasoning_content': \"Okay, let's break down what needs to be done here. The user provided a skill gap analysis for Chirayu Jain, who is a Backend Developer. The gaps identified are in FastAPI, PostgreSQL, and Docker. The task is to create a learning roadmap based on these gaps.\\n\\nFirst, I need to check if there are any courses available for each of these skills. The user has already called the search_courses function for each skill and received responses. Now, I need to select the most appropriate courses from the search results.\\n\\nFor FastAPI, the courses CS-FAST-101 and CS-FAST-201 are available. Since the candidate has Python and Flask experience but no FastAPI, starting with the foundational course CS-FAST-101 makes sense. The advanced course can come later once the basics are covered.\\n\\nFor PostgreSQL, the candidate has experience with MySQL and SQLite, so the SQL Fundamentals course (CS-DB-101) would be a good starting point to transition to PostgreSQL. Then, moving to the advanced SQL course (CS-DB-201) would build on that foundation.\\n\\nDocker is entirely new, so the fundamentals course (CS-DOCKER-101) is essential to get started with containerization. The other Docker-related courses are either part of other tracks (like MLOps) or more advanced, so they might not be necessary here.\\n\\nNext, sequencing the courses. Since there's no mention of fresher adaptation needed, the sequence can start directly with the foundational courses. The order should be FastAPI first, then PostgreSQL, followed by Docker. After the foundations, the advanced courses can follow.\\n\\nThe roadmap should be structured over weeks, with each course taking a week. The summary should highlight the 4-5 week plan focusing on the critical skills. The Mermaid diagram needs to reflect this sequence with weeks as subgraphs.\\n\\nFinally, ensure that all the correct course IDs are used and that the reasoning for each course selection is clear. Also, check that the Mermaid code correctly maps the sequence and formatting.\\n\"}, response_metadata={'token_usage': {'completion_tokens': 703, 'prompt_tokens': 3715, 'total_tokens': 4418, 'completion_time': 1.556481651, 'completion_tokens_details': {'reasoning_tokens': 426}, 'prompt_time': 0.180619391, 'prompt_tokens_details': None, 'queue_time': 0.045325729, 'total_time': 1.737101042}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'stop', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-c878-7740-b9e7-2776e494fe50-0', tool_calls=[], invalid_tool_calls=[], usage_metadata={'input_tokens': 3715, 'output_tokens': 703, 'total_tokens': 4418, 'output_token_details': {'reasoning': 426}})]}}\n", + "\u001b[1m[values]\u001b[0m {'candidate_name': 'Chirayu Jain', 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.', 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf', 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ', 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires FastAPI; candidate\\'s resume shows Python and Flask experience but no record of using FastAPI framework.\",\\n \"target_competency\": \"Develop high-performance asynchronous APIs using FastAPI\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.\",\\n \"target_competency\": \"Design and manage relational databases with PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD lists Docker as a required technology; candidate\\'s profile contains no Docker usage or containerization experience.\",\\n \"target_competency\": \"Containerize applications using Docker for consistent deployment\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.\"\\n}\\n\\n ', additional_kwargs={}, response_metadata={}, id='5048b99a-0ef9-45fd-9dde-153379f3e1fb'), AIMessage(content='', additional_kwargs={'reasoning_content': 'Okay, let\\'s start by understanding the user\\'s problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the provided skill gap analysis. The gaps identified are FastAPI, PostgreSQL, and Docker, all with high priority. The user is an expert technical onboarding architect, so the solution needs to be efficient and logically sequenced.\\n\\nFirst, I need to follow the strict workflow provided. The first step is to search for courses for each gap using the search_courses function. The user emphasized using only the course IDs returned by the tool, so I can\\'t guess any IDs. \\n\\nFor each skill gap (FastAPI, PostgreSQL, Docker), I\\'ll call search_courses. Let\\'s start with FastAPI. The function requires a query parameter, which should be the skill name. So, I\\'ll use \"FastAPI\" as the query. Then do the same for PostgreSQL and Docker. \\n\\nAssuming the tool returns valid course IDs, the next step is to sequence them. Since is_fresher_adaptation_needed is False, we don\\'t need to add professional fundamentals first. The sequence_order should be 1, 2, 3, etc. Each course will be in a separate week. \\n\\nAfter sequencing, I need to create the Mermaid diagram. Each course will be in a subgraph for the respective week, labeled as W1, W2, W3. The start and end nodes will be marked with the appropriate classes. \\n\\nFinally, submit the final roadmap and the Mermaid visualization. The roadmap should include the candidate\\'s name, target role, and the sequenced courses with their details. The Mermaid code should correctly map the sequence and group the weeks.\\n\\nI need to make sure that each step is followed in order and that the tools are called correctly. Also, check that the JSON structures are properly formatted when submitting the final roadmap and visualization.\\n', 'tool_calls': [{'id': 'tk112hq0c', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z12xgzqbr', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}, {'id': 'z2ccjm3w2', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 456, 'prompt_tokens': 1559, 'total_tokens': 2015, 'completion_time': 0.929203584, 'completion_tokens_details': {'reasoning_tokens': 389}, 'prompt_time': 0.064193024, 'prompt_tokens_details': None, 'queue_time': 0.044726596, 'total_time': 0.993396608}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-aed2-77c0-a431-2f2f4ae627a9-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'tk112hq0c', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'z12xgzqbr', 'type': 'tool_call'}, {'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'z2ccjm3w2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1559, 'output_tokens': 456, 'total_tokens': 2015, 'output_token_details': {'reasoning': 389}}), ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\n---\", name='search_courses', id='81dc0c18-afd0-48cf-93e2-3f84aeb4697d', tool_call_id='tk112hq0c'), ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\n---', name='search_courses', id='7d61cda6-fd9d-4f36-8b71-8df2e24b95fb', tool_call_id='z12xgzqbr'), ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\n---', name='search_courses', id='eda8cd08-a93d-4b9e-8ed4-c2af30a4b4fc', tool_call_id='z2ccjm3w2'), AIMessage(content='', additional_kwargs={'reasoning_content': \"Okay, let's start by looking at the user's problem. They need to create a learning roadmap for Chirayu Jain, a Backend Developer candidate, based on the skill gaps identified. The gaps are in FastAPI, PostgreSQL, and Docker. The user has provided the search results for each of these skills, and now I need to sequence them into a logical order.\\n\\nFirst, I need to check if any foundational courses are required. The user mentioned that is_fresher_adaptation_needed is False, so we don't need to add any professional fundamentals first. That means we can start directly with the identified gaps.\\n\\nLooking at the FastAPI courses, there's CS-FAST-101 and CS-FAST-201. Since the target competency is to develop high-performance asynchronous APIs, the first course (CS-FAST-101) is the foundation. The advanced course (CS-FAST-201) would come after mastering the basics.\\n\\nFor PostgreSQL, the relevant courses are CS-DB-101 and CS-DB-201. The candidate has experience with MySQL and SQLite, so starting with CS-DB-101 makes sense to build a solid foundation in SQL fundamentals. Then, moving to CS-DB-201 for advanced topics like indexing and transactions.\\n\\nFor Docker, the course CS-DOCKER-101 is the fundamental one. The other Docker-related courses are either part of other tracks (like CS-CICD-201 for CI/CD) or part of MLOps, which isn't the focus here. So CS-DOCKER-101 is the right choice here.\\n\\nNow, sequencing these courses. The order should allow Chirayu to build skills progressively. Starting with FastAPI makes sense because it's a framework he's somewhat familiar with (Python and Flask), so transitioning to FastAPI would be logical. Then, moving to PostgreSQL to handle database management, followed by Docker for containerization. Each of these can be spread over weeks, maybe one course per week.\\n\\nI need to assign sequence_order numbers. Let's see:\\n\\n1. FastAPI Fundamentals (CS-FAST-101) - Week 1\\n2. PostgreSQL Fundamentals (CS-DB-101) - Week 2\\n3. Docker Fundamentals (CS-DOCKER-101) - Week 3\\n4. Advanced FastAPI (CS-FAST-201) - Week 4\\n5. Advanced PostgreSQL (CS-DB-201) - Week 5\\n\\nThis order ensures that foundational skills are built first before moving to advanced topics. Each course is a prerequisite for the next in their respective tracks. The Mermaid diagram should reflect this sequence with subgraphs for each week.\\n\\nI also need to make sure that the reasoning for each course choice is clear. For example, CS-FAST-101 is chosen because it covers the basics needed for developing APIs with FastAPI, which is a high-priority gap. Similarly, CS-DB-101 provides the necessary SQL fundamentals before moving to advanced PostgreSQL topics.\\n\\nFinally, compiling all this into the required JSON format for the final roadmap and the Mermaid visualization. Double-checking that all course IDs are from the search results and that the sequence makes logical sense for skill progression.\\n\", 'tool_calls': [{'id': 'mm78w2e88', 'function': {'arguments': '{\"candidate_name\":\"Chirayu Jain\",\"onboarding_summary\":\"4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.\",\"roadmap\":[{\"course_id\":\"CS-FAST-101\",\"is_foundation\":true,\"reasoning\":\"Foundational course to build FastAPI skills required for high-performance API development\",\"sequence_order\":1,\"title\":\"REST API Development with FastAPI\"},{\"course_id\":\"CS-DB-101\",\"is_foundation\":true,\"reasoning\":\"Establish PostgreSQL foundation before advanced database work\",\"sequence_order\":2,\"title\":\"SQL Fundamentals for Backend Developers\"},{\"course_id\":\"CS-DOCKER-101\",\"is_foundation\":true,\"reasoning\":\"Core containerization skills needed for consistent deployment\",\"sequence_order\":3,\"title\":\"Docker \\\\u0026 Containerization Fundamentals\"},{\"course_id\":\"CS-FAST-201\",\"is_foundation\":false,\"reasoning\":\"Build on FastAPI fundamentals with async database integration\",\"sequence_order\":4,\"title\":\"Advanced API Design with FastAPI\"},{\"course_id\":\"CS-DB-201\",\"is_foundation\":false,\"reasoning\":\"Deepen PostgreSQL expertise for production-grade database work\",\"sequence_order\":5,\"title\":\"Advanced SQL - Indexing, Transactions \\\\u0026 Query Optimization\"}],\"target_role\":\"Backend Developer\"}', 'name': 'submit_final_roadmap'}, 'type': 'function'}, {'id': 'h9phazqpb', 'function': {'arguments': '{\"mermaid_code\":\"flowchart TD\\\\n A([Start]):::start\\\\n subgraph W1[\\\\\"Week 1\\\\\"]\\\\n B[CS-FAST-101]:::gap\\\\n end\\\\n subgraph W2[\\\\\"Week 2\\\\\"]\\\\n C[CS-DB-101]:::gap\\\\n end\\\\n subgraph W3[\\\\\"Week 3\\\\\"]\\\\n D[CS-DOCKER-101]:::gap\\\\n end\\\\n subgraph W4[\\\\\"Week 4\\\\\"]\\\\n E[CS-FAST-201]:::gap\\\\n end\\\\n subgraph W5[\\\\\"Week 5\\\\\"]\\\\n F[CS-DB-201]:::gap\\\\n end\\\\n Z([Ready]):::done\\\\n A --\\\\u003e B --\\\\u003e C --\\\\u003e D --\\\\u003e E --\\\\u003e F --\\\\u003e Z\\\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\\\n classDef start fill:#1D9E75,stroke:#0F6E56\\\\n classDef done fill:#534AB7,stroke:#3C3489\"}', 'name': 'submit_mermaid_visualization'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 1350, 'prompt_tokens': 3008, 'total_tokens': 4358, 'completion_time': 2.38863248, 'completion_tokens_details': {'reasoning_tokens': 685}, 'prompt_time': 0.136514084, 'prompt_tokens_details': None, 'queue_time': 0.044030126, 'total_time': 2.525146564}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-be3d-7de2-9310-9fbcc34ce8b8-0', tool_calls=[{'name': 'submit_final_roadmap', 'args': {'candidate_name': 'Chirayu Jain', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'is_foundation': True, 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'sequence_order': 1, 'title': 'REST API Development with FastAPI'}, {'course_id': 'CS-DB-101', 'is_foundation': True, 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'sequence_order': 2, 'title': 'SQL Fundamentals for Backend Developers'}, {'course_id': 'CS-DOCKER-101', 'is_foundation': True, 'reasoning': 'Core containerization skills needed for consistent deployment', 'sequence_order': 3, 'title': 'Docker & Containerization Fundamentals'}, {'course_id': 'CS-FAST-201', 'is_foundation': False, 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'sequence_order': 4, 'title': 'Advanced API Design with FastAPI'}, {'course_id': 'CS-DB-201', 'is_foundation': False, 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'sequence_order': 5, 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization'}], 'target_role': 'Backend Developer'}, 'id': 'mm78w2e88', 'type': 'tool_call'}, {'name': 'submit_mermaid_visualization', 'args': {'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489'}, 'id': 'h9phazqpb', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 3008, 'output_tokens': 1350, 'total_tokens': 4358, 'output_token_details': {'reasoning': 685}}), ToolMessage(content='SUCCESS: Final roadmap has been submitted and saved to state.', name='submit_final_roadmap', id='195a42f9-9bf9-4df4-a864-93dd6c497b98', tool_call_id='mm78w2e88'), ToolMessage(content='SUCCESS: Mermaid visualization saved successfully.', name='submit_mermaid_visualization', id='e54942a8-a7e4-4ba2-adae-0df4d2fd46bd', tool_call_id='h9phazqpb'), AIMessage(content='✅ **Onboarding Roadmap Finalized for Chirayu Jain** \\n**Target Role:** Backend Developer \\n**Duration:** 5 Weeks \\n\\n### 📌 Key Components \\n1. **Week 1:** FastAPI Fundamentals (CS-FAST-101) \\n2. **Week 2:** PostgreSQL Foundations (CS-DB-101) \\n3. **Week 3:** Docker Core Skills (CS-DOCKER-101) \\n4. **Week 4:** Advanced FastAPI (CS-FAST-201) \\n5. **Week 5:** PostgreSQL Optimization (CS-DB-201) \\n\\n### 📚 Course Rationale \\n- **CS-FAST-101** establishes core API development patterns required for CodeForge’s backend stack. \\n- **CS-DB-101** builds foundational PostgreSQL proficiency before advanced optimization. \\n- **CS-DOCKER-101** ensures containerization skills for deployment consistency. \\n- Advanced courses (CS-FAST-201, CS-DB-201) deepen expertise in async workflows and database performance. \\n\\n### 📊 Visual Roadmap \\nA Mermaid flowchart has been generated to visualize the sequence. \\n\\nLet me know if you need adjustments to the timeline or course selections!', additional_kwargs={'reasoning_content': \"Okay, let's break down what needs to be done here. The user provided a skill gap analysis for Chirayu Jain, who is a Backend Developer. The gaps identified are in FastAPI, PostgreSQL, and Docker. The task is to create a learning roadmap based on these gaps.\\n\\nFirst, I need to check if there are any courses available for each of these skills. The user has already called the search_courses function for each skill and received responses. Now, I need to select the most appropriate courses from the search results.\\n\\nFor FastAPI, the courses CS-FAST-101 and CS-FAST-201 are available. Since the candidate has Python and Flask experience but no FastAPI, starting with the foundational course CS-FAST-101 makes sense. The advanced course can come later once the basics are covered.\\n\\nFor PostgreSQL, the candidate has experience with MySQL and SQLite, so the SQL Fundamentals course (CS-DB-101) would be a good starting point to transition to PostgreSQL. Then, moving to the advanced SQL course (CS-DB-201) would build on that foundation.\\n\\nDocker is entirely new, so the fundamentals course (CS-DOCKER-101) is essential to get started with containerization. The other Docker-related courses are either part of other tracks (like MLOps) or more advanced, so they might not be necessary here.\\n\\nNext, sequencing the courses. Since there's no mention of fresher adaptation needed, the sequence can start directly with the foundational courses. The order should be FastAPI first, then PostgreSQL, followed by Docker. After the foundations, the advanced courses can follow.\\n\\nThe roadmap should be structured over weeks, with each course taking a week. The summary should highlight the 4-5 week plan focusing on the critical skills. The Mermaid diagram needs to reflect this sequence with weeks as subgraphs.\\n\\nFinally, ensure that all the correct course IDs are used and that the reasoning for each course selection is clear. Also, check that the Mermaid code correctly maps the sequence and formatting.\\n\"}, response_metadata={'token_usage': {'completion_tokens': 703, 'prompt_tokens': 3715, 'total_tokens': 4418, 'completion_time': 1.556481651, 'completion_tokens_details': {'reasoning_tokens': 426}, 'prompt_time': 0.180619391, 'prompt_tokens_details': None, 'queue_time': 0.045325729, 'total_time': 1.737101042}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'stop', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7606-c878-7740-b9e7-2776e494fe50-0', tool_calls=[], invalid_tool_calls=[], usage_metadata={'input_tokens': 3715, 'output_tokens': 703, 'total_tokens': 4418, 'output_token_details': {'reasoning': 426}})], 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning=\"JD requires FastAPI; candidate's resume shows Python and Flask experience but no record of using FastAPI framework.\", target_competency='Develop high-performance asynchronous APIs using FastAPI'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate has worked with MySQL and SQLite but has no experience with PostgreSQL specifically.', target_competency='Design and manage relational databases with PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning=\"JD lists Docker as a required technology; candidate's profile contains no Docker usage or containerization experience.\", target_competency='Containerize applications using Docker for consistent deployment')], is_fresher_adaptation_needed=False, executive_summary='Chirayu has solid Python backend experience with Flask and Django, and familiarity with SQL databases like MySQL and SQLite. However, critical backend stack components required by CodeForge—FastAPI, PostgreSQL, and Docker—are absent, indicating immediate focus areas for onboarding.'), 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category=None), Skill(name='Java', category=None), Skill(name='Python', category=None), Skill(name='JavaScript', category=None), Skill(name='Dart', category=None), Skill(name='Flutter', category=None), Skill(name='HTML/CSS', category=None), Skill(name='ReactJS', category=None), Skill(name='Firebase', category=None), Skill(name='REST APIs', category=None), Skill(name='Flask', category=None), Skill(name='Django', category=None), Skill(name='NodeJS', category=None), Skill(name='ExpressJS', category=None), Skill(name='MySQL', category=None), Skill(name='MongoDB', category=None), Skill(name='SQLite', category=None)], experience=[ExperienceItem(job_title='Technology Intern', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction', 'Cron-based background workers'], responsibilities=['Built Flask API for RTA investor verification team, implementing 2 confidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and extract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.', 'Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR, semantic chunking, and LLM-based extraction to process 60+ page financial documents and identify investor/investee details, reducing extraction time by 35%.', 'Implementing Cron-based background workers to generate automated weekly email analytics reports tracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing overall document processing latency by 40%.']), ExperienceItem(job_title='Software Development intern', technologies=['Flutter', 'MVVM', 'SOLID', 'modular design'], responsibilities=['Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management and Applied clean code practices (SOLID, modular design) for scalability.', 'Implemented secure user authentication and role-based access, ensuring smooth login and data protection.', 'Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False), 'extraction_error': None, 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')]), 'mermaid_code': 'flowchart TD\\n A([Start]):::start\\n subgraph W1[\"Week 1\"]\\n B[CS-FAST-101]:::gap\\n end\\n subgraph W2[\"Week 2\"]\\n C[CS-DB-101]:::gap\\n end\\n subgraph W3[\"Week 3\"]\\n D[CS-DOCKER-101]:::gap\\n end\\n subgraph W4[\"Week 4\"]\\n E[CS-FAST-201]:::gap\\n end\\n subgraph W5[\"Week 5\"]\\n F[CS-DB-201]:::gap\\n end\\n Z([Ready]):::done\\n A --> B --> C --> D --> E --> F --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7\\n classDef known fill:#E1F5EE,stroke:#0F6E56\\n classDef start fill:#1D9E75,stroke:#0F6E56\\n classDef done fill:#534AB7,stroke:#3C3489', 'final_roadmap': {'candidate_name': 'Chirayu Jain', 'target_role': 'Backend Developer', 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.', 'roadmap': [{'course_id': 'CS-FAST-101', 'title': 'REST API Development with FastAPI', 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development', 'is_foundation': True, 'sequence_order': 1}, {'course_id': 'CS-DB-101', 'title': 'SQL Fundamentals for Backend Developers', 'reasoning': 'Establish PostgreSQL foundation before advanced database work', 'is_foundation': True, 'sequence_order': 2}, {'course_id': 'CS-DOCKER-101', 'title': 'Docker & Containerization Fundamentals', 'reasoning': 'Core containerization skills needed for consistent deployment', 'is_foundation': True, 'sequence_order': 3}, {'course_id': 'CS-FAST-201', 'title': 'Advanced API Design with FastAPI', 'reasoning': 'Build on FastAPI fundamentals with async database integration', 'is_foundation': False, 'sequence_order': 4}, {'course_id': 'CS-DB-201', 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization', 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work', 'is_foundation': False, 'sequence_order': 5}]}}\n" ] } ], "source": [ - "config = {\"configurable\": {\"thread_id\": \"gyujj\"}}\n", - "final_result = run_graph_with_stream(graph, initial_input, config)" + "config = {\"configurable\": {\"thread_id\": THREAD_ID}}\n", + "\n", + "# Change THREAD_ID to config\n", + "final_result = graph.invoke(initial_input, config=config)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "id": "d536c172", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "dict_keys(['candidate_name', 'resume_text', 'file_path', 'job_description', 'messages', 'skill_gap_analysis_data', 'resume_data', 'extraction_error', 'JobDescriptionExtract_data', 'mermaid_code', 'final_roadmap'])" + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "final_result.keys()" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "id": "e1441f1f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'candidate_name': 'Chirayu Jain',\n", + " 'target_role': 'Backend Developer',\n", + " 'onboarding_summary': '4-week intensive track covering FastAPI, PostgreSQL, and Docker. Weeks 1-3 focus on foundational skills, followed by advanced implementation in Weeks 4-5. Completes critical backend stack requirements for CodeForge.',\n", + " 'roadmap': [{'course_id': 'CS-FAST-101',\n", + " 'title': 'REST API Development with FastAPI',\n", + " 'reasoning': 'Foundational course to build FastAPI skills required for high-performance API development',\n", + " 'is_foundation': True,\n", + " 'sequence_order': 1},\n", + " {'course_id': 'CS-DB-101',\n", + " 'title': 'SQL Fundamentals for Backend Developers',\n", + " 'reasoning': 'Establish PostgreSQL foundation before advanced database work',\n", + " 'is_foundation': True,\n", + " 'sequence_order': 2},\n", + " {'course_id': 'CS-DOCKER-101',\n", + " 'title': 'Docker & Containerization Fundamentals',\n", + " 'reasoning': 'Core containerization skills needed for consistent deployment',\n", + " 'is_foundation': True,\n", + " 'sequence_order': 3},\n", + " {'course_id': 'CS-FAST-201',\n", + " 'title': 'Advanced API Design with FastAPI',\n", + " 'reasoning': 'Build on FastAPI fundamentals with async database integration',\n", + " 'is_foundation': False,\n", + " 'sequence_order': 4},\n", + " {'course_id': 'CS-DB-201',\n", + " 'title': 'Advanced SQL - Indexing, Transactions & Query Optimization',\n", + " 'reasoning': 'Deepen PostgreSQL expertise for production-grade database work',\n", + " 'is_foundation': False,\n", + " 'sequence_order': 5}]}" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "final_result['final_roadmap']" ] }, { "cell_type": "code", - "execution_count": 73, + "execution_count": null, + "id": "eadcbe43", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 155, "id": "4e502949", "metadata": {}, "outputs": [ @@ -2017,44 +2321,17 @@ " 'resume_text': 'Chirayu Jain\\nSOFTWARE DEVELOPER\\n+91-9462128878 | chirayujain93@gmail.com | LinkedIn | GitHub | CodeChef | Leetcode\\nEDUCATION\\nIndian Institute of Information Technology, Kota (CGPA-8.1)\\nKota, Rajasthan\\nB.Tech in Electronics and Communication Engineering\\n2022 - Present\\nWORK EXPERIENCE\\nNAV India\\nJan 2026 - Present\\nTechnology Intern\\nOnsite – Jaipur, Rajasthan\\n• As part of the AI/ML team, built Flask API for the RTA investor verification team, implementing 2\\nconfidence-scoring pipelines using OCR extraction (PyMuPDF, Docling) to parse PDF/forms and\\nextract 3 key KYC investor attributes, reducing verification time from 20–30 minutes to 2–3 minutes.\\n• Developed a scalable document intelligence pipeline with parallel CPU processing using Docling OCR,\\nsemantic chunking, and LLM-based extraction to process 60+ page financial documents and identify\\ninvestor/investee details, reducing extraction time by 35%.\\n• Implementing Cron-based background workers to generate automated weekly email analytics reports\\ntracking API accuracy and confidence match-mismatch scores, improving scoring precision and reducing\\noverall document processing latency by 40%.\\nVestbox\\nApril 2025 - May 2025\\nSoftware Development intern\\nRemote\\n• Developed Groceazy app in Flutter (MVVM), integrating 10+ modules for grocery service , order management\\nand Applied clean code practices (SOLID, modular design) for scalability.\\n• Implemented secure user authentication and role-based access, ensuring smooth login and data protection.\\n• Built image-to-item price matcher using APIs across 5+ platforms, enabling best-price suggestions.\\nPROJECTS\\nHostel Bites – IIITK Canteen App | Flutter, Dart, Firebase, Cloud Firestore, Mapbox API\\n• Developed a Flutter app for hostel residents to order food, increasing canteen efficiency by 35%.\\n• Implemented role-based access for students, staff, and admin, increasing operational efficiency by 40%.\\n• Integrated Firebase Auth, Firestore, Storage, and Mapbox API for secure logins, and live order tracking.\\n• GitHub: Live link\\nJobShield - Fake Job Detector | Flutter, Dart, Python, Flask, SQLite\\n• Developed a Flask+Python fake job detection API with a custom NLP model, with 95% classification accuracy.\\n• Built a responsive web interface using Flutter (Web), integrated with the backend, enabling seamless real-time\\ndetection for 500+ job postings.\\n• Github: Live Link\\nTECHNICAL SKILLS\\nLanguages: C/C++ , Java , Python , JavaScript, Dart\\nFrontend: Flutter, HTML/CSS, ReactJS\\nBackend: Firebase, REST APIs, Flask, Django, NodeJS, ExpressJS\\nDatabase Management: MySQL, MongoDB, SQLite\\nTools and Frameworks: GitHub, Android Studio, Visual Studio Code, MATLAB, Cursor, Github Copilot\\nLibraries: Provider, Bloc, Scikit-learn, tensorflow\\nACHIEVEMENTS & CERTIFICATIONS\\n• Ranked 81 in Inter IIIT Coding Contest Optigo, competing against top-tier programmers - View credential.\\n• Obtained Certification in Graph Algorithms from AlgoUniversity - View credential.\\n• Achieved a 4-star CodeChef rating and earned the Knight(Max. 1888) badge on LeetCode.\\n• Developed an e-waste facility locator application for SIH’23, successfully advancing to the regionals.',\n", " 'file_path': 'C:\\\\Users\\\\ATHARVA\\\\Downloads\\\\my codes\\\\web\\\\AdaptiveEngineService\\\\AI_Engine_Evaluation\\\\Testcases\\\\Testresume\\\\ChirayuResume.pdf',\n", " 'job_description': 'Job Title: Backend Developer\\n\\nCompany name: CodeForge\\nWe are hiring a Backend Developer to build scalable APIs and backend systems.\\n\\nResponsibilities:\\n- Develop REST APIs using FastAPI\\n- Design and manage PostgreSQL databases\\n- Implement authentication and authorization systems\\n- Optimize performance and scalability\\n\\nRequirements:\\n- Strong knowledge of Python\\n- Experience with FastAPI or Django\\n- Good understanding of SQL and database design\\n- Familiarity with Docker\\n\\nConstraints:\\n- Location: Pune only\\n- Full-time role ',\n", - " 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"Backend Developer\",\\n \"candidate_name\": \"Chirayu Jain\",\\n \"analyzed_gaps\": [\\n {\\n \"skill_name\": \"FastAPI\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD explicitly lists FastAPI; resume shows Flask/Django but no exposure to FastAPI, creating a core framework gap.\",\\n \"target_competency\": \"Build async REST endpoints with FastAPI, Pydantic models and dependency injection\"\\n },\\n {\\n \"skill_name\": \"PostgreSQL\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"JD requires PostgreSQL; candidate only lists MySQL, SQLite and MongoDB, so no evidence of PostgreSQL-specific features or deployment experience.\",\\n \"target_competency\": \"Design relational schemas, write optimized queries and manage transactions in PostgreSQL\"\\n },\\n {\\n \"skill_name\": \"Docker\",\\n \"gap_type\": \"missing_foundation\",\\n \"priority\": \"high\",\\n \"reasoning\": \"Docker appears in JD but is absent from skills, experience and projects, indicating no containerization background.\",\\n \"target_competency\": \"Containerize FastAPI services, write Dockerfiles and orchestrate multi-container dev environments\"\\n }\\n ],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.\"\\n}\\n\\n Please proceed to search for courses and build the learning roadmap now.\\n ', additional_kwargs={}, response_metadata={}, id='61350c0a-f333-4b0b-bce8-b002d5c13832'),\n", - " AIMessage(content='', additional_kwargs={'reasoning_content': \"We need to follow workflow.\\n\\nStep 1: For each gap skill, call search_courses with query.\\n\\nWe have three gaps: FastAPI, PostgreSQL, Docker.\\n\\nWe need to get course IDs.\\n\\nLet's call search_courses for FastAPI.\", 'tool_calls': [{'id': 'fc_6c1f8c83-94ad-438c-8ff4-772fc7e3a5a2', 'function': {'arguments': '{\"query\":\"FastAPI\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 78, 'prompt_tokens': 1285, 'total_tokens': 1363, 'completion_time': 0.167971032, 'completion_tokens_details': {'reasoning_tokens': 50}, 'prompt_time': 0.061565999, 'prompt_tokens_details': None, 'queue_time': 0.04593067, 'total_time': 0.229537031}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_a09bde29de', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206b-c546-75f2-9bee-3a75dc5dc28a-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'FastAPI'}, 'id': 'fc_6c1f8c83-94ad-438c-8ff4-772fc7e3a5a2', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1285, 'output_tokens': 78, 'total_tokens': 1363, 'output_token_details': {'reasoning': 50}}),\n", - " ToolMessage(content=\"ID: CS-FAST-101\\nCourse Title: REST API Development with FastAPI\\nCategory: Backend\\nDescription: A project-driven course for building production-quality REST APIs with Python's FastAPI framework. Students learn to define typed routes with path and query parameters, leverage Pydantic models for automatic request validation and serialization, implement dependency injection, and secure endpoints using JWT-based Bearer token authentication.\\nLearning Outcomes: Create REST endpoints with path and query params, Validate request/response with Pydantic models, Implement JWT-based authentication\\nPrerequisites: CS-PY-101\\n---\\nID: CS-FAST-201\\nCourse Title: Advanced API Design with FastAPI\\nCategory: Backend\\nDescription: An advanced course for engineers building high-performance, secure backend services with FastAPI. Students implement full OAuth2 authorization code and client credentials flows, build async database CRUD endpoints using SQLAlchemy 2.0 with asyncpg, design layered dependency injection architectures, create custom middleware for logging and rate limiting, and run Celery background task queues.\\nLearning Outcomes: Implement OAuth2 authentication flows, Build async database endpoints with SQLAlchemy, Use dependency injection and middleware patterns\\nPrerequisites: CS-PY-101, CS-DB-101, CS-FAST-101\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\nPrerequisites: CS-ML-101, CS-DOCKER-101, CS-FAST-101\\n---\\nID: OPS-K8S-101\\nCourse Title: Kubernetes for AI Workloads\\nCategory: MLOps\\nDescription: An introduction to K8s specifically for ML engineers. Covers pod orchestration, GPU resource allocation, and scaling FastAPI backends on clusters.\\nLearning Outcomes: Deploy ML models as K8s services, Configure GPU-enabled worker nodes, Manage cluster auto-scaling for inference bursts\\nPrerequisites: None\\n---\", name='search_courses', id='be522420-9402-497c-b37a-55f859017f39', tool_call_id='fc_6c1f8c83-94ad-438c-8ff4-772fc7e3a5a2'),\n", - " AIMessage(content='', additional_kwargs={'reasoning_content': 'We have FastAPI courses. Need also PostgreSQL and Docker courses. Search for PostgreSQL.', 'tool_calls': [{'id': 'fc_cfcddbeb-b919-4f79-98e2-2000cdf9c354', 'function': {'arguments': '{\"query\":\"PostgreSQL\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 45, 'prompt_tokens': 1809, 'total_tokens': 1854, 'completion_time': 0.09460185, 'completion_tokens_details': {'reasoning_tokens': 20}, 'prompt_time': 0.614039222, 'prompt_tokens_details': {'cached_tokens': 768}, 'queue_time': 0.045160052, 'total_time': 0.708641072}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_626f3fc5e0', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206b-dc84-7312-8d72-172aa51c0a1b-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'PostgreSQL'}, 'id': 'fc_cfcddbeb-b919-4f79-98e2-2000cdf9c354', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 1809, 'output_tokens': 45, 'total_tokens': 1854, 'input_token_details': {'cache_read': 768}, 'output_token_details': {'reasoning': 20}}),\n", - " ToolMessage(content='ID: CS-DB-101\\nCourse Title: SQL Fundamentals for Backend Developers\\nCategory: Database\\nDescription: A hands-on introduction to relational database theory and practice using SQLite and PostgreSQL. Students learn to model data with schemas, enforce referential integrity through primary and foreign keys, and interact with data using full CRUD operations and multi-table JOINs.\\nLearning Outcomes: Write basic SELECT queries with filters, Understand Primary and Foreign Keys, Perform data insertion, updates, and deletions\\nPrerequisites: None\\n---\\nID: CS-DB-201\\nCourse Title: Advanced SQL — Indexing, Transactions & Query Optimization\\nCategory: Database\\nDescription: A deep dive into production-grade SQL performance and reliability. Students master analytical window functions, Common Table Expressions (CTEs), query execution plan analysis using EXPLAIN/ANALYZE, B-tree and partial index strategies, and ACID-compliant transaction management including deadlock detection and prevention.\\nLearning Outcomes: Use window functions and CTEs, Analyze and optimize slow queries with EXPLAIN, Manage ACID transactions and deadlock prevention\\nPrerequisites: CS-DB-101\\n---\\nID: BUS-SQL-201\\nCourse Title: SQL for Workforce Analytics\\nCategory: Data Science\\nDescription: Learn to query internal talent databases. Covers JOINs, aggregations, and subqueries to find hiring trends and predict churn.\\nLearning Outcomes: Write SQL queries to extract talent metrics, Analyze historical hiring data for trends, Build basic labor supply reports\\nPrerequisites: BUS-DATA-101\\n---\\nID: CS-DB-301\\nCourse Title: NoSQL Databases — MongoDB & Redis\\nCategory: Database\\nDescription: Practical training in document and key-value store paradigms for modern applications. Covers MongoDB schema design, flexible document modeling, the aggregation pipeline for complex data transformations, and Redis as both a high-speed caching layer and a pub/sub message broker with TTL-based eviction strategies.\\nLearning Outcomes: Design document schemas in MongoDB, Build aggregation pipelines, Implement caching with Redis TTL strategies\\nPrerequisites: CS-DB-101\\n---', name='search_courses', id='5f602c21-b2c8-4611-9f68-1e4f127958cb', tool_call_id='fc_cfcddbeb-b919-4f79-98e2-2000cdf9c354'),\n", - " AIMessage(content='', additional_kwargs={'reasoning_content': 'We have three gaps: FastAPI, PostgreSQL, Docker.\\n\\nWe need to search for Docker courses.', 'tool_calls': [{'id': 'fc_68440688-509a-4a4d-ae5f-b46d16b4a8fc', 'function': {'arguments': '{\"query\":\"Docker\"}', 'name': 'search_courses'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 45, 'prompt_tokens': 2260, 'total_tokens': 2305, 'completion_time': 0.095418158, 'completion_tokens_details': {'reasoning_tokens': 22}, 'prompt_time': 0.28257033, 'prompt_tokens_details': {'cached_tokens': 1280}, 'queue_time': 0.045485127, 'total_time': 0.377988488}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_a09bde29de', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206b-e355-7100-8e37-9e09f7cf0a97-0', tool_calls=[{'name': 'search_courses', 'args': {'query': 'Docker'}, 'id': 'fc_68440688-509a-4a4d-ae5f-b46d16b4a8fc', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2260, 'output_tokens': 45, 'total_tokens': 2305, 'input_token_details': {'cache_read': 1280}, 'output_token_details': {'reasoning': 22}}),\n", - " ToolMessage(content='ID: CS-DOCKER-101\\nCourse Title: Docker & Containerization Fundamentals\\nCategory: DevOps\\nDescription: A practical guide to application containerization using Docker. Students learn to write optimized multi-stage Dockerfiles, manage images and container lifecycles, configure bridge and overlay networking, use named volumes for data persistence, and orchestrate multi-service applications with Docker Compose for local and staging environments.\\nLearning Outcomes: Write efficient multi-stage Dockerfiles, Manage container lifecycle and networking, Orchestrate multi-service apps with Docker Compose\\nPrerequisites: None\\n---\\nID: CS-CICD-201\\nCourse Title: CI/CD Pipelines with GitHub Actions\\nCategory: DevOps\\nDescription: A hands-on course in automating the full software delivery lifecycle using GitHub Actions. Students define multi-job workflows with matrix builds, integrate linting and pytest test suites as required CI checks, automate Docker image builds and pushes to registries, and manage environment secrets and deployment approvals for staging and production environments.\\nLearning Outcomes: Create GitHub Actions workflows for CI/CD, Automate Docker image builds and pushes, Manage secrets and environment variables securely\\nPrerequisites: CS-DOCKER-101\\n---\\nID: CS-MLOPS-301\\nCourse Title: MLOps — Model Deployment & Monitoring\\nCategory: AI Engineering\\nDescription: An end-to-end MLOps course covering the full lifecycle of production machine learning systems. Students track experiments and version datasets and models using MLflow, build model serving APIs with FastAPI, containerize inference services with Docker, set up automated retraining pipelines triggered by data drift detection using Evidently AI, and monitor prediction quality and infrastructure health with Grafana dashboards.\\nLearning Outcomes: Track experiments and version models with MLflow, Serve ML models via FastAPI and Docker, Monitor model drift and set up retraining triggers\\nPrerequisites: CS-ML-101, CS-DOCKER-101, CS-FAST-101\\n---\\nID: CS-K8S-301\\nCourse Title: Kubernetes — Container Orchestration at Scale\\nCategory: DevOps\\nDescription: A comprehensive course on running containerized workloads in production with Kubernetes. Students deploy stateless and stateful applications using Deployments and StatefulSets, expose services through ClusterIP, NodePort, and Ingress controllers, manage configuration and secrets with ConfigMaps and Secrets, autoscale workloads with HPA, and package applications for repeatable releases using Helm charts.\\nLearning Outcomes: Deploy applications using Deployments and StatefulSets, Configure Services, Ingress, and ConfigMaps, Manage releases with Helm charts\\nPrerequisites: CS-DOCKER-101, CS-CICD-201\\n---', name='search_courses', id='00e1a0f1-f97e-46b6-9f4d-ee55fc23c17d', tool_call_id='fc_68440688-509a-4a4d-ae5f-b46d16b4a8fc'),\n", - " AIMessage(content='', additional_kwargs={'reasoning_content': 'We have identified gaps: FastAPI, PostgreSQL, Docker. Need to search for courses for each. Already have courses:\\n\\nFastAPI: CS-FAST-101 (prereq CS-PY-101). Also CS-FAST-201 (prereq CS-PY-101, CS-DB-101, CS-FAST-101). Likely choose CS-FAST-101 as foundation.\\n\\nPostgreSQL: CS-DB-101 covers SQLite and PostgreSQL fundamentals. No explicit prerequisite. Also CS-DB-201 advanced. Choose CS-DB-101.\\n\\nDocker: CS-DOCKER-101 fundamentals, no prereq.\\n\\nNow need to resolve prerequisites: For CS-FAST-101, prerequisite CS-PY-101 (Python Fundamentals). Candidate has solid Python, Django experience. Likely resume shows Python mastery, so we can consider that as known. The instruction: \"Skip courses the candidate already demonstrates via projects or experience.\" So we can treat CS-PY-101 as known, not needed to include.\\n\\nCheck other courses for prerequisites: none else.\\n\\nThus roadmap includes three courses: CS-FAST-101, CS-DB-101, CS-DOCKER-101. Sequence: prerequisites before target modules. Since no dependencies among these three (except maybe Docker before FastAPI? Not required). Could order logically: start with Docker fundamentals (foundation for containerizing FastAPI later), then PostgreSQL fundamentals, then FastAPI. Or any order. We\\'ll assign sequence_order 1,2,3.\\n\\nis_fresher_adaptation_needed false, so no professional fundamentals module.\\n\\nNow need to build roadmap array with fields: course_id, is_foundation (boolean). Probably true for foundation courses? Let\\'s set is_foundation true for all three as they are foundational.\\n\\nReasoning: brief.\\n\\nNow need to create mermaid visualization following rules: gap courses ::gap, known prerequisites ::known, start node ::start, end node ::done. Since we are not adding known courses (CS-PY-101) as nodes, but we could include as known? The rules: known prerequisites should be marked ::known. Since we are skipping CS-PY-101, maybe we don\\'t include it. But we could include it as known to show prerequisite satisfied. Let\\'s include a node for CS-PY-101 as known.\\n\\nAlso start node: candidate\\'s current skills.\\n\\nEnd node: Role-ready — Backend Developer.\\n\\nGroup by week using subgraph. Let\\'s assign weeks: Week 1 Docker, Week 2 PostgreSQL, Week 3 FastAPI.\\n\\nMermaid code accordingly.\\n\\nNow need to call submit_final_roadmap with candidate_name, onboarding_summary (maybe executive summary), roadmap array, target_role \"Backend Developer\".\\n\\nThen submit_mermaid_visualization with code.\\n\\nProceed.', 'tool_calls': [{'id': 'fc_e1fad88b-3a4b-4877-a3df-369362707126', 'function': {'arguments': '{\"candidate_name\":\"Chirayu Jain\",\"onboarding_summary\":\"Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.\",\"roadmap\":[{\"course_id\":\"CS-DOCKER-101\",\"is_foundation\":true,\"reasoning\":\"Provides essential containerization skills required to package FastAPI services for deployment.\",\"sequence_order\":1,\"title\":\"Docker \\\\u0026 Containerization Fundamentals\"},{\"course_id\":\"CS-DB-101\",\"is_foundation\":true,\"reasoning\":\"Covers PostgreSQL fundamentals, enabling design of relational schemas and optimized queries for the target role.\",\"sequence_order\":2,\"title\":\"SQL Fundamentals for Backend Developers\"},{\"course_id\":\"CS-FAST-101\",\"is_foundation\":true,\"reasoning\":\"Introduces FastAPI, the primary framework listed in the JD, building async REST endpoints and Pydantic models.\",\"sequence_order\":3,\"title\":\"REST API Development with FastAPI\"}],\"target_role\":\"Backend Developer\"}', 'name': 'submit_final_roadmap'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 864, 'prompt_tokens': 2825, 'total_tokens': 3689, 'completion_time': 1.891397937, 'completion_tokens_details': {'reasoning_tokens': 564}, 'prompt_time': 0.145777084, 'prompt_tokens_details': {'cached_tokens': 1792}, 'queue_time': 0.045268224, 'total_time': 2.037175021}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_626f3fc5e0', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206b-ee19-7900-a734-70259374603f-0', tool_calls=[{'name': 'submit_final_roadmap', 'args': {'candidate_name': 'Chirayu Jain', 'onboarding_summary': 'Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.', 'roadmap': [{'course_id': 'CS-DOCKER-101', 'is_foundation': True, 'reasoning': 'Provides essential containerization skills required to package FastAPI services for deployment.', 'sequence_order': 1, 'title': 'Docker & Containerization Fundamentals'}, {'course_id': 'CS-DB-101', 'is_foundation': True, 'reasoning': 'Covers PostgreSQL fundamentals, enabling design of relational schemas and optimized queries for the target role.', 'sequence_order': 2, 'title': 'SQL Fundamentals for Backend Developers'}, {'course_id': 'CS-FAST-101', 'is_foundation': True, 'reasoning': 'Introduces FastAPI, the primary framework listed in the JD, building async REST endpoints and Pydantic models.', 'sequence_order': 3, 'title': 'REST API Development with FastAPI'}], 'target_role': 'Backend Developer'}, 'id': 'fc_e1fad88b-3a4b-4877-a3df-369362707126', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2825, 'output_tokens': 864, 'total_tokens': 3689, 'input_token_details': {'cache_read': 1792}, 'output_token_details': {'reasoning': 564}}),\n", - " ToolMessage(content='{\"candidate_name\": \"Chirayu Jain\", \"target_role\": \"Backend Developer\", \"onboarding_summary\": \"Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.\", \"roadmap\": [{\"course_id\": \"CS-DOCKER-101\", \"title\": \"Docker & Containerization Fundamentals\", \"reasoning\": \"Provides essential containerization skills required to package FastAPI services for deployment.\", \"is_foundation\": true, \"sequence_order\": 1}, {\"course_id\": \"CS-DB-101\", \"title\": \"SQL Fundamentals for Backend Developers\", \"reasoning\": \"Covers PostgreSQL fundamentals, enabling design of relational schemas and optimized queries for the target role.\", \"is_foundation\": true, \"sequence_order\": 2}, {\"course_id\": \"CS-FAST-101\", \"title\": \"REST API Development with FastAPI\", \"reasoning\": \"Introduces FastAPI, the primary framework listed in the JD, building async REST endpoints and Pydantic models.\", \"is_foundation\": true, \"sequence_order\": 3}]}', name='submit_final_roadmap', id='5fb8c861-d353-4034-a0c8-d1c17aeabcd6', tool_call_id='fc_e1fad88b-3a4b-4877-a3df-369362707126'),\n", - " AIMessage(content='', additional_kwargs={'reasoning_content': \"We have submitted final roadmap. Need to also submit mermaid visualization. Must follow rules: gap courses ::gap, known prerequisites ::known, start ::start, end ::done. In this case all three are gaps (they are missing foundations). However they have prerequisites: CS-FAST-101 prerequisite CS-PY-101, CS-DB-101 has none, CS-DOCKER-101 none. Candidate already has Python foundation, so we can treat CS-PY-101 as known prerequisite. Need to include it as known node. Sequence: start -> CS-DOCKER-101 (gap) -> CS-DB-101 (gap) -> CS-FAST-101 (gap) -> end. Also include CS-PY-101 as known prerequisite for FastAPI, placed before FastAPI maybe in same week or earlier. Since FastAPI depends on Python fundamentals, we should include known node before FastAPI. Could be in same week as FastAPI but as known. We'll create weeks: Week1 Docker, Week2 PostgreSQL, Week3 Python fundamentals (known) and FastAPI (gap). Or maybe include known before gap in same week.\\n\\nMermaid format: flowchart TD. Use subgraph W1, W2, W3.\\n\\nAdd class definitions.\\n\\nNow call submit_mermaid_visualization.\", 'tool_calls': [{'id': 'fc_ea8b8113-e478-45dd-a8b4-bf2eae927d9a', 'function': {'arguments': '{\"mermaid_code\":\"flowchart TD\\\\n A([Start — Current Skills]):::start\\\\n subgraph W1[\\\\\"Week 1 — Containerization\\\\\"]\\\\n B[CS-DOCKER-101\\\\\\\\nDocker \\\\u0026 Containerization Fundamentals]:::gap\\\\n end\\\\n subgraph W2[\\\\\"Week 2 — Relational DB\\\\\"]\\\\n C[CS-DB-101\\\\\\\\nSQL Fundamentals for Backend Developers]:::gap\\\\n end\\\\n subgraph W3[\\\\\"Week 3 — API Development\\\\\"]\\\\n D[CS-PY-101\\\\\\\\nPython Fundamentals]:::known\\\\n E[CS-FAST-101\\\\\\\\nREST API Development with FastAPI]:::gap\\\\n end\\\\n Z([Backend Developer — Role Ready]):::done\\\\n A --\\\\u003e B --\\\\u003e C --\\\\u003e D --\\\\u003e E --\\\\u003e Z\\\\n classDef gap fill:#EEEDFE,stroke:#534AB7,color:#26215C\\\\n classDef known fill:#E1F5EE,stroke:#0F6E56,color:#085041\\\\n classDef start fill:#1D9E75,stroke:#0F6E56,color:#E1F5EE\\\\n classDef done fill:#534AB7,stroke:#3C3489,color:#EEEDFE\"}', 'name': 'submit_mermaid_visualization'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 557, 'prompt_tokens': 3339, 'total_tokens': 3896, 'completion_time': 1.196030062, 'completion_tokens_details': {'reasoning_tokens': 266}, 'prompt_time': 0.160108793, 'prompt_tokens_details': None, 'queue_time': 0.046081046, 'total_time': 1.356138855}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_8a618bed98', 'service_tier': 'on_demand', 'finish_reason': 'tool_calls', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206b-f96f-7ad0-9a9e-fc4e668a8516-0', tool_calls=[{'name': 'submit_mermaid_visualization', 'args': {'mermaid_code': 'flowchart TD\\n A([Start — Current Skills]):::start\\n subgraph W1[\"Week 1 — Containerization\"]\\n B[CS-DOCKER-101\\\\nDocker & Containerization Fundamentals]:::gap\\n end\\n subgraph W2[\"Week 2 — Relational DB\"]\\n C[CS-DB-101\\\\nSQL Fundamentals for Backend Developers]:::gap\\n end\\n subgraph W3[\"Week 3 — API Development\"]\\n D[CS-PY-101\\\\nPython Fundamentals]:::known\\n E[CS-FAST-101\\\\nREST API Development with FastAPI]:::gap\\n end\\n Z([Backend Developer — Role Ready]):::done\\n A --> B --> C --> D --> E --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7,color:#26215C\\n classDef known fill:#E1F5EE,stroke:#0F6E56,color:#085041\\n classDef start fill:#1D9E75,stroke:#0F6E56,color:#E1F5EE\\n classDef done fill:#534AB7,stroke:#3C3489,color:#EEEDFE'}, 'id': 'fc_ea8b8113-e478-45dd-a8b4-bf2eae927d9a', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 3339, 'output_tokens': 557, 'total_tokens': 3896, 'output_token_details': {'reasoning': 266}}),\n", - " ToolMessage(content='Mermaid visualization saved successfully.', name='submit_mermaid_visualization', id='e07fe033-a45e-41ee-b421-caa15afa997d', tool_call_id='fc_ea8b8113-e478-45dd-a8b4-bf2eae927d9a'),\n", - " AIMessage(content='The learning roadmap for **Chirayu Jain** has been finalized and visualized.\\n\\n**Roadmap Summary**\\n- **Target Role:** Backend Developer \\n- **Onboarding Summary:** Near‑ready backend candidate with solid Python, Django and SQL experience; needs FastAPI, PostgreSQL, and Docker to meet CodeForge’s stack. \\n\\n**Course Sequence**\\n1. **CS-DOCKER-101 – Docker & Containerization Fundamentals** (Foundation) \\n2. **CS-DB-101 – SQL Fundamentals for Backend Developers** (Foundation) \\n3. **CS-FAST-101 – REST API Development with FastAPI** (Foundation) \\n\\n**Mermaid Visualization**\\n```mermaid\\nflowchart TD\\n A([Start — Current Skills]):::start\\n subgraph W1[\"Week 1 — Containerization\"]\\n B[CS-DOCKER-101\\\\nDocker & Containerization Fundamentals]:::gap\\n end\\n subgraph W2[\"Week 2 — Relational DB\"]\\n C[CS-DB-101\\\\nSQL Fundamentals for Backend Developers]:::gap\\n end\\n subgraph W3[\"Week 3 — API Development\"]\\n D[CS-PY-101\\\\nPython Fundamentals]:::known\\n E[CS-FAST-101\\\\nREST API Development with FastAPI]:::gap\\n end\\n Z([Backend Developer — Role Ready]):::done\\n A --> B --> C --> D --> E --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7,color:#26215C\\n classDef known fill:#E1F5EE,stroke:#0F6E56,color:#085041\\n classDef start fill:#1D9E75,stroke:#0F6E56,color:#E1F5EE\\n classDef done fill:#534AB7,stroke:#3C3489,color:#EEEDFE\\n```\\n\\nAll steps are complete.', additional_kwargs={}, response_metadata={'token_usage': {'completion_tokens': 406, 'prompt_tokens': 3646, 'total_tokens': 4052, 'completion_time': 1.438615073, 'completion_tokens_details': None, 'prompt_time': 0.141632128, 'prompt_tokens_details': {'cached_tokens': 2816}, 'queue_time': 0.04638064, 'total_time': 1.5802472010000002}, 'model_name': 'openai/gpt-oss-120b', 'system_fingerprint': 'fp_626f3fc5e0', 'service_tier': 'on_demand', 'finish_reason': 'stop', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d206c-010d-7133-92a9-18ed936df441-0', tool_calls=[], invalid_tool_calls=[], usage_metadata={'input_tokens': 3646, 'output_tokens': 406, 'total_tokens': 4052, 'input_token_details': {'cache_read': 2816}})],\n", - " 'skill_gap_analysis_data': SkillGapAnalysis(job_title='Backend Developer', candidate_name='Chirayu Jain', analyzed_gaps=[SkillGap(skill_name='FastAPI', gap_type='missing_foundation', priority='high', reasoning='JD explicitly lists FastAPI; resume shows Flask/Django but no exposure to FastAPI, creating a core framework gap.', target_competency='Build async REST endpoints with FastAPI, Pydantic models and dependency injection'), SkillGap(skill_name='PostgreSQL', gap_type='missing_foundation', priority='high', reasoning='JD requires PostgreSQL; candidate only lists MySQL, SQLite and MongoDB, so no evidence of PostgreSQL-specific features or deployment experience.', target_competency='Design relational schemas, write optimized queries and manage transactions in PostgreSQL'), SkillGap(skill_name='Docker', gap_type='missing_foundation', priority='high', reasoning='Docker appears in JD but is absent from skills, experience and projects, indicating no containerization background.', target_competency='Containerize FastAPI services, write Dockerfiles and orchestrate multi-container dev environments')], is_fresher_adaptation_needed=False, executive_summary='Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.'),\n", - " 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='Software Developer', skills=[Skill(name='C/C++', category='Other'), Skill(name='Java', category='Other'), Skill(name='Python', category='Backend'), Skill(name='JavaScript', category='Frontend'), Skill(name='Dart', category='Frontend'), Skill(name='Flutter', category='Frontend'), Skill(name='HTML/CSS', category='Frontend'), Skill(name='ReactJS', category='Frontend'), Skill(name='Firebase', category='Backend'), Skill(name='REST APIs', category='Backend'), Skill(name='Flask', category='Backend'), Skill(name='Django', category='Backend'), Skill(name='NodeJS', category='Backend'), Skill(name='ExpressJS', category='Backend'), Skill(name='MySQL', category='Other'), Skill(name='MongoDB', category='Other'), Skill(name='SQLite', category='Other'), Skill(name='GitHub', category='Other'), Skill(name='Android Studio', category='Other'), Skill(name='Visual Studio Code', category='Other'), Skill(name='MATLAB', category='Other'), Skill(name='Cursor', category='Other'), Skill(name='Github Copilot', category='Other'), Skill(name='Provider', category='Other'), Skill(name='Bloc', category='Other'), Skill(name='Scikit-learn', category='ML'), Skill(name='tensorflow', category='ML')], experience=[ExperienceItem(job_title='Technology Intern', experience_type='internship', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR', 'Python'], responsibilities=['Built Flask API for RTA investor verification with confidence-scoring pipelines', 'Developed document intelligence pipeline with parallel CPU processing', 'Implementing Cron-based background workers for weekly email analytics reports']), ExperienceItem(job_title='Software Development Intern', experience_type='internship', technologies=['Flutter', 'MVVM', 'Dart'], responsibilities=['Developed Grocezy app in Flutter with 10+ modules', 'Implemented secure user authentication and role-based access', 'Built image-to-item price matcher using APIs'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], certifications=[CertificationItem(name='Graph Algorithms Certification from AlgoUniversity', topics_covered=['Graph Algorithms'])], is_fresher=False),\n", + " 'messages': [HumanMessage(content='\\n Skill Gap Analysis Completed for Chirayu Jain.\\n\\n Gaps Identified:\\n {\\n \"job_title\": \"\",\\n \"candidate_name\": null,\\n \"analyzed_gaps\": [],\\n \"is_fresher_adaptation_needed\": false,\\n \"executive_summary\": \"No job description provided; unable to assess skill gaps.\"\\n}\\n\\n Please proceed to search for courses and build the learning roadmap now.\\n ', additional_kwargs={}, response_metadata={}, id='1358e145-f0ff-48d5-976b-b46273380e64'),\n", + " AIMessage(content='The provided skill gap analysis lacks both a job description and any identified skill gaps, making it impossible to generate a targeted learning roadmap. Per the executive summary, no gaps were assessed due to missing input data.\\n\\nTo proceed, please provide:\\n1. A valid job description or target role specifications\\n2. A properly populated skill gap analysis with specific technical requirements\\n\\nOnly then can I execute the required workflow steps (search_courses → resolve prerequisites → sequence → submit).', additional_kwargs={'reasoning_content': \"Okay, let's see. The user provided a Skill Gap Analysis for Chirayu Jain, but it looks like there's no job title or candidate name, and the analyzed gaps are empty. The executive summary says no job description was provided, so they couldn't assess the gaps. \\n\\nHmm, the user wants me to proceed to search for courses and build a learning roadmap. But wait, according to the strict workflow, I need to start with STEP 1 — SEARCH for every gap. But there are no gaps identified here. That's a problem. Without knowing the specific skill gaps, how can I search for relevant courses?\\n\\nMaybe the user made a mistake in the input. The Skill Gap Analysis didn't have any gaps, so there's nothing to build a roadmap from. The tools I have require me to call search_courses for each gap, but there are no gaps here. So I can't proceed with the workflow as instructed. \\n\\nI should inform the user that the Skill Gap Analysis is incomplete or missing necessary information. Without knowing the specific skills Chirayu needs to learn, I can't generate a roadmap. The executive summary mentions that no job description was provided, which is probably why the gaps aren't identified. \\n\\nTherefore, the correct step here is to ask the user to provide a job description or more details about the target role so that the Skill Gap Analysis can be properly conducted. Once the gaps are identified, then I can proceed with the workflow steps as outlined. Until then, there's nothing to act on.\\n\"}, response_metadata={'token_usage': {'completion_tokens': 407, 'prompt_tokens': 1153, 'total_tokens': 1560, 'completion_time': 0.951808963, 'completion_tokens_details': {'reasoning_tokens': 311}, 'prompt_time': 0.051115782, 'prompt_tokens_details': None, 'queue_time': 0.045027329, 'total_time': 1.002924745}, 'model_name': 'qwen/qwen3-32b', 'system_fingerprint': 'fp_5cf921caa2', 'service_tier': 'on_demand', 'finish_reason': 'stop', 'logprobs': None, 'model_provider': 'groq'}, id='lc_run--019d7464-c89b-7213-8504-2fc1fa58e450-0', tool_calls=[], invalid_tool_calls=[], usage_metadata={'input_tokens': 1153, 'output_tokens': 407, 'total_tokens': 1560, 'output_token_details': {'reasoning': 311}})],\n", + " 'skill_gap_analysis_data': SkillGapAnalysis(job_title='', candidate_name=None, analyzed_gaps=[], is_fresher_adaptation_needed=False, executive_summary='No job description provided; unable to assess skill gaps.'),\n", + " 'resume_data': ResumeExtract(candidate_name='Chirayu Jain', job_title='SOFTWARE DEVELOPER', skills=[Skill(name='C/C++', category='Languages'), Skill(name='Java', category='Languages'), Skill(name='Python', category='Languages'), Skill(name='JavaScript', category='Languages'), Skill(name='Dart', category='Languages'), Skill(name='Flutter', category='Frontend'), Skill(name='HTML/CSS', category='Frontend'), Skill(name='ReactJS', category='Frontend'), Skill(name='Firebase', category='Backend'), Skill(name='REST APIs', category='Backend'), Skill(name='Flask', category='Backend'), Skill(name='Django', category='Backend'), Skill(name='NodeJS', category='Backend'), Skill(name='ExpressJS', category='Backend'), Skill(name='MySQL', category='Database Management'), Skill(name='MongoDB', category='Database Management'), Skill(name='SQLite', category='Database Management')], experience=[ExperienceItem(job_title='Technology Intern', experience_type='internship', technologies=['Flask', 'PyMuPDF', 'Docling', 'OCR extraction'], responsibilities=['Built Flask API for RTA investor verification team', 'Developed scalable document intelligence pipeline', 'Implemented Cron-based background workers']), ExperienceItem(job_title='Software Development intern', experience_type='internship', technologies=['Flutter', 'MVVM', 'Firebase'], responsibilities=['Developed Groceazy app in Flutter', 'Implemented secure user authentication', 'Built image-to-item price matcher'])], projects=[ProjectItem(name='Hostel Bites – IIITK Canteen App', technologies=['Flutter', 'Dart', 'Firebase', 'Cloud Firestore', 'Mapbox API']), ProjectItem(name='JobShield - Fake Job Detector', technologies=['Flutter', 'Dart', 'Python', 'Flask', 'SQLite'])], is_fresher=False),\n", " 'extraction_error': None,\n", - " 'JobDescriptionExtract_data': JobDescriptionExtract(job_title='Backend Developer', company_name='CodeForge', location='Pune', employment_type='Full-time role', duration_months=None, is_fresher_allowed=None, skills_required=[SkillRequirement(name='Python', level=None), SkillRequirement(name='FastAPI', level=None), SkillRequirement(name='Django', level=None), SkillRequirement(name='SQL', level=None), SkillRequirement(name='PostgreSQL', level=None), SkillRequirement(name='Docker', level=None)], tools_technologies=None, responsibilities=[ResponsibilityItem(description='Develop REST APIs using FastAPI'), ResponsibilityItem(description='Design and manage PostgreSQL databases'), ResponsibilityItem(description='Implement authentication and authorization systems'), ResponsibilityItem(description='Optimize performance and scalability')], requirements=[RequirementItem(description='Strong knowledge of Python'), RequirementItem(description='Experience with FastAPI or Django'), RequirementItem(description='Good understanding of SQL and database design'), RequirementItem(description='Familiarity with Docker')], constraints=[ConstraintItem(type='location', value='Pune only'), ConstraintItem(type='employment type', value='Full-time role')]),\n", - " 'mermaid_code': 'flowchart TD\\n A([Start — Current Skills]):::start\\n subgraph W1[\"Week 1 — Containerization\"]\\n B[CS-DOCKER-101\\\\nDocker & Containerization Fundamentals]:::gap\\n end\\n subgraph W2[\"Week 2 — Relational DB\"]\\n C[CS-DB-101\\\\nSQL Fundamentals for Backend Developers]:::gap\\n end\\n subgraph W3[\"Week 3 — API Development\"]\\n D[CS-PY-101\\\\nPython Fundamentals]:::known\\n E[CS-FAST-101\\\\nREST API Development with FastAPI]:::gap\\n end\\n Z([Backend Developer — Role Ready]):::done\\n A --> B --> C --> D --> E --> Z\\n classDef gap fill:#EEEDFE,stroke:#534AB7,color:#26215C\\n classDef known fill:#E1F5EE,stroke:#0F6E56,color:#085041\\n classDef start fill:#1D9E75,stroke:#0F6E56,color:#E1F5EE\\n classDef done fill:#534AB7,stroke:#3C3489,color:#EEEDFE',\n", - " 'final_roadmap': {'candidate_name': 'Chirayu Jain',\n", - " 'onboarding_summary': 'Chirayu is a near-ready backend candidate with solid Python, Django and SQL experience, but must quickly add FastAPI, PostgreSQL and Docker to meet CodeForge’s stack requirements.',\n", - " 'roadmap': [{'course_id': 'CS-DOCKER-101',\n", - " 'is_foundation': True,\n", - " 'reasoning': 'Provides essential containerization skills required to package FastAPI services for deployment.',\n", - " 'sequence_order': 1,\n", - " 'title': 'Docker & Containerization Fundamentals'},\n", - " {'course_id': 'CS-DB-101',\n", - " 'is_foundation': True,\n", - " 'reasoning': 'Covers PostgreSQL fundamentals, enabling design of relational schemas and optimized queries for the target role.',\n", - " 'sequence_order': 2,\n", - " 'title': 'SQL Fundamentals for Backend Developers'},\n", - " {'course_id': 'CS-FAST-101',\n", - " 'is_foundation': True,\n", - " 'reasoning': 'Introduces FastAPI, the primary framework listed in the JD, building async REST endpoints and Pydantic models.',\n", - " 'sequence_order': 3,\n", - " 'title': 'REST API Development with FastAPI'}],\n", - " 'target_role': 'Backend Developer'}}" + " 'JobDescriptionExtract_data': JobDescriptionExtract(job_title=None, company_name=None, location=None, employment_type=None, duration_months=None, is_fresher_allowed=None, skills_required=None, tools_technologies=None, responsibilities=None, requirements=None),\n", + " 'mermaid_code': None,\n", + " 'final_roadmap': None}" ] }, - "execution_count": 73, + "execution_count": 155, "metadata": {}, "output_type": "execute_result" }