add to ig

.gitignore

@@ -5,6 +5,8 @@ google-credentials.json
 !composer.json  # If you use composer (optional)
 /venv
 
+
+/Notebooks
 # --- Python Environment ---
 __pycache__/
 *.py[cod]

Dockerfile

@@ -0,0 +1,31 @@
+
+FROM python:3.12-slim
+
+# Set the working directory to /code
+WORKDIR /code
+
+# Copy the requirements.txt file into the container
+COPY requirements.txt .
+
+# Install the dependencies
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app
+COPY --chown=user . $HOME/app
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

app/core/config.py

@@ -1,16 +1,16 @@
 from pathlib import Path
 from pydantic_settings import BaseSettings, SettingsConfigDict
  
-BASE_DIR = Path(__file__).resolve().parent.parent
+BASE_DIR = Path(__file__).resolve().parent.parent.parent
  
 class Settings(BaseSettings):
     PROJECT_NAME: str = "Adaptive Onboarding Engine"
  
     GROQ_API_KEY: str
     PINECONE_API_KEY: str
-    CLOUDINARY_CLOUD_NAME: str
-    CLOUDINARY_API_KEY: str
-    CLOUDINARY_API_SECRET: str
+    # CLOUDINARY_CLOUD_NAME: str
+    # CLOUDINARY_API_KEY: str
+    # CLOUDINARY_API_SECRET: str
  
     model_config = SettingsConfigDict(
         env_file=str(BASE_DIR / ".env"),

app/graph.py

@@ -1,4 +1,3 @@
-
 from app.state.state import OnboardingState
 from app.nodes.graphnodes import *
 from langgraph.prebuilt import ToolNode ,tools_condition

app/main.py

@@ -0,0 +1,118 @@
+import uuid
+import tempfile
+import os
+from pathlib import Path
+from fastapi import FastAPI, UploadFile, File, Form, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from langgraph.checkpoint.memory import MemorySaver
+
+from app.graph import graph
+
+app = FastAPI(title="Adaptive Onboarding Engine")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],   # tighten this in production
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+checkpointer = MemorySaver()
+
+# -----------------------------
+# Payload Builder
+# (inline from your export_ui_payload logic)
+# -----------------------------
+
+REQUIRED_KEYS = ["candidate_name", "skill_gap_analysis_data", "mermaid_code", "final_roadmap"]
+
+def build_ui_payload(state: dict) -> dict:
+    ui_data = {}
+    for key in REQUIRED_KEYS:
+        val = state.get(key)
+        if val is None:
+            continue
+        if hasattr(val, "model_dump"):
+            ui_data[key] = val.model_dump()
+        else:
+            ui_data[key] = val
+    return ui_data
+
+
+# -----------------------------
+# POST /analyze
+# Accepts: resume PDF (file upload) + job description (form field)
+# Returns: UI payload JSON
+# -----------------------------
+
+@app.post("/analyze")
+async def analyze(
+    resume: UploadFile = File(..., description="Resume PDF file"),
+    job_description: str = Form(..., description="Job description text"),
+    candidate_name: str = Form(default="Candidate"),
+):
+    # 1. Save uploaded PDF to a temp file
+    tmp_path = None
+    try:
+        suffix = Path(resume.filename).suffix or ".pdf"
+        with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
+            content = await resume.read()
+            tmp.write(content)
+            tmp_path = tmp.name
+
+        # 2. Build initial graph state
+        initial_input = {
+            "candidate_name": candidate_name,
+            "resume_text": None,
+            "job_description": job_description,
+            "file_path": tmp_path,          # local temp path for PyMuPDF
+            "resume_data": None,
+            "extraction_error": None,
+            "JobDescriptionExtract_data": None,
+            "skill_gap_analysis_data": None,
+            "messages": [],
+            "mermaid_code": None,
+            "final_roadmap": None,
+        }
+
+        # 3. Run the graph
+        thread_id = str(uuid.uuid4())
+        config = {"configurable": {"thread_id": thread_id}}
+
+        final_state = graph.invoke(initial_input, config=config)
+
+        # 4. Check for extraction errors
+        if final_state.get("extraction_error"):
+            raise HTTPException(
+                status_code=422,
+                detail=f"Extraction failed: {final_state['extraction_error']}"
+            )
+
+        # 5. Build and return UI payload
+        return build_ui_payload(final_state)
+
+    except HTTPException:
+        raise
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+    finally:
+        # 6. Clean up temp file
+        if tmp_path and os.path.exists(tmp_path):
+            os.remove(tmp_path)
+
+
+# -----------------------------
+# GET /health
+# -----------------------------
+
+@app.get("/health")
+def health():
+    return {"status": "ok", "service": "Adaptive Onboarding Engine"}
+
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="127.0.0.1", port=8000)

app/tools/tools.py

@@ -4,6 +4,8 @@ from app.utils.vectordatabase import retriever
 from app.schemas.pydanticschema import LearningRoadmap
 import json
 from typing import Dict, List,Any
+from pathlib import Path
+BASE_DIR = Path(__file__).resolve().parent
 
 @tool
 def search_courses(query: str, level: str, category: str):
@@ -111,8 +113,16 @@ class CourseLookup:
         """Retrieves full details of a course by its ID."""
         return self.courses_map.get(course_id)
 
+DATA_PATH = BASE_DIR / "Catalog.json"
+
+if DATA_PATH.exists():
+    lookup_service = CourseLookup(DATA_PATH)
+
+else:
+    raise FileNotFoundError(f"Catalog file not found: {DATA_PATH}")
+
+     
 
-lookup_service = CourseLookup("Catalog.json")
 
 @tool
 def get_course_by_id(course_id: str) -> str:

app/utils/bm25.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ee33742ce995054481aaba1f309536b1b8991754c1a1627743076d64aba478
+size 5752

app/utils/vectordatabase.py

@@ -1,14 +1,14 @@
 import json
 import pickle
-import torch
+import requests
 from pathlib import Path
 from typing import List
 
 from pinecone import Pinecone, ServerlessSpec
 from pinecone_text.sparse import BM25Encoder
-from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.retrievers import PineconeHybridSearchRetriever
 from langchain_core.documents import Document
+from langchain_core.embeddings import Embeddings
 
 from app.core.config import settings
 
@@ -23,25 +23,38 @@ BM25_PKL_PATH = BASE_DIR / "bm25.pkl"
 
 
 # -----------------------------
-# Device
+# General Remote Embeddings
+# aviods cold starts
 # -----------------------------
 
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(f"Using device: {device}")
+class GeneralRemoteEmbeddings(Embeddings):
+    def __init__(self, endpoint: str):
+        self.endpoint = endpoint
 
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        response = requests.post(
+            f"{self.endpoint}/embed_docs",
+            json={"texts": texts}
+        )
+        response.raise_for_status()
+        return response.json()["embeddings"]
+
+    def embed_query(self, text: str) -> List[float]:
+        response = requests.post(
+            f"{self.endpoint}/embed_query",
+            json={"text": text}
+        )
+        response.raise_for_status()
+        return response.json()["embedding"]
 
-# -----------------------------
-# Embeddings
-# -----------------------------
 
-embeddings = HuggingFaceEmbeddings(
-    model_name="sentence-transformers/all-MiniLM-L6-v2",
-    model_kwargs={"device": str(device)}
+embeddings = GeneralRemoteEmbeddings(
+    endpoint="https://gaykar-generalembeddings.hf.space"
 )
 
 
 # -----------------------------
-# Load Documents from JSON
+# Load Documents
 # -----------------------------
 
 def load_documents(data_path: Path) -> List[Document]:

requirements.txt

@@ -7,3 +7,4 @@ langchain_community==0.4.1
 fastapi==0.118.1
 uvicorn
 pinecone-text
+sentence-transformers