Upload 5 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,81 @@
 ---
-license: apache-2.0
+title: GenAI Career Agent
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 5.42.0
+app_file: app.py
+pinned: false
+hf_oauth: true
+hf_oauth_scopes:
+- inference-api
+short_description: A generative AI model that acts as a career coach
 ---
+
+A Resume–Job Fit Analysis chatbot built using **Gradio**, **FAISS Vector Search**, and the **Hugging Face Inference API**.  
+This Space hosts the **GenAI Career Agent**, a generative AI that analyzes user resumes, retrieves structured resume data through a vectorstore (FAISS), and evaluates how well a candidate fits any provided job description.
+
+### 🚀 Features
+
+- **AI Career Coach** – Helps users understand job fit, strengths, and areas for improvement.
+- **RAG Pipeline** – Uses FAISS to retrieve relevant resume chunks.
+- **LLM-Powered Analysis** – Uses a remote Hugging Face model via `InferenceClient`.
+- **Structured JSON Output** including:
+  - `job_fit_score`
+  - `fit_summary`
+  - `strengths`
+  - `missing_skills`
+  - `recommendations`
+- **Secure Token Handling** with Hugging Face Space Secrets.
+
+### 📌 Current Capability
+
+✔ **Resume Parsing & Analysis**  
+The system currently parses the user's resume (pre-embedded with MiniLM) and produces job-fit analytics using RAG + LLM inference.
+
+### 🛠️ Upcoming Features
+
+🔜 **GitHub Repo Intelligence**  
+- Automatic retrieval of repositories  
+- Summarization of project impact  
+- Extraction of tech stack & coding patterns  
+- Integration into the job-fit score  
+
+🔜 **LinkedIn Profile Integration**  
+- Work history extraction  
+- Skill inference  
+- Keyword alignment  
+- Soft-skill assessment  
+
+These features will be integrated into the same RAG pipeline so the model can reason across **Resume + GitHub + LinkedIn** for a unified career profile.
+
+### 🧠 How It Works
+
+1. Resume data is pre-embedded using  
+   `sentence-transformers/all-MiniLM-L6-v2`.
+2. Embeddings are stored inside  
+   `data/vectorstores/`.
+3. The FAISS retriever fetches the most relevant resume sections based on the job description.
+4. A custom prompt formats the retrieved text and sends it to the LLM.
+5. The LLM generates structured JSON insights.
+
+### 🗂️ Tech Stack
+
+- **Gradio 5** (ChatInterface front-end)
+- **LangChain Runnables**
+- **FAISS** Vector Search
+- **HuggingFace Embeddings**
+- **Hugging Face Inference API**
+
+### 🔒 Token Handling
+
+Set secrets in your Space
+
+
+### 📜 Model Licensing & Notices
+
+🧍 Personal / Educational Use
+
+This is a personal project, intended solely for educational and career-analysis purposes.
+Users are solely responsible for how they use the outputs.

app.py

@@ -0,0 +1,150 @@
+import os
+import sys
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from rag.logger import get_logger
+from rag.analysis_chain import retriever, hf_llm, analyze_resume_against_job
+
+logger = get_logger(__name__)
+
+# -----------------------------------
+# Load HuggingFace API key
+# -----------------------------------
+HF_API_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
+if not HF_API_TOKEN:
+    raise RuntimeError("Environment variable HUGGINGFACE_API_TOKEN is missing!")
+
+client = InferenceClient(
+    token=HF_API_TOKEN,
+    model=""       # When in use insert model name as parameter here
+)
+
+# -----------------------------------
+# System Prompt
+# -----------------------------------
+DEFAULT_SYSTEM_MESSAGE = """
+You are a helpful resume-analysis chatbot.
+
+You can perform the following tasks on the data you have:
+1. Job description analysis using the RAG pipeline.
+2. Candidate summarization using the vectorstore *WHICH YOU ALREADY HAVE*.
+3. General conversation.
+
+Always respond clearly and professionally as if you were a talent aquisition specialist.
+"""
+
+# -----------------------------------
+# INTENT DETECTOR
+# -----------------------------------
+def detect_intent(user_message: str):
+    """Lightweight rule-based intent classifier."""
+    message = user_message.lower()
+
+    # --- JOB DESCRIPTION ANALYSIS ---
+    jd_keywords = [
+        "responsibilities", "requirements", "we are looking for",
+        "qualifications", "role description", "job description",
+        "candidate must", "skills required", "apply", "position",
+        "looking for a", "experience required"
+    ]
+    if any(k in message for k in jd_keywords):
+        return "job_analysis"
+
+    # --- CANDIDATE SUMMARY ---
+    candidate_keywords = [
+        "candidate", "tell me about him", "tell me about her", "profile summary",
+        "summary", "skills", "experience", "background", "what can he do",
+        "what is his experience", "what is his background", "about the candidate", "about his resume"
+    ]
+    if any(k in message for k in candidate_keywords):
+        return "candidate_info"
+
+    # --- DEFAULT ---
+    return "general"
+
+
+# -----------------------------------
+# BOT RESPONSE
+# -----------------------------------
+def bot_response(message, history):
+    system_msg = DEFAULT_SYSTEM_MESSAGE
+    max_tokens = 500
+    temperature = 0.7
+    top_p = 0.95
+    intent = detect_intent(message)
+
+    # -----------------------------------
+    # INTENT 1 → JOB ANALYSIS USING RAG
+    # -----------------------------------
+    if intent == "job_analysis":
+        rag_output = analyze_resume_against_job(
+            job_description=message,
+            retriever=retriever,
+            llm_callable=hf_llm
+        )
+        prompt = f"{system_msg}\n\n{rag_output}"
+
+    # -----------------------------------
+    # INTENT 2 → CANDIDATE SUMMARY
+    # -----------------------------------
+    elif intent == "candidate_info":
+        # Use LCEL retriever interface (correct for VectorStoreRetriever)
+        retrieved_docs = retriever.invoke("candidate overall profile")
+        combined = "\n".join([doc.page_content for doc in retrieved_docs])
+
+        prompt = f"""
+You are a professional candidate summarization assistant.
+
+Using the resume data below, create a detailed profile summary.
+
+Resume Data:
+{combined}
+
+Provide:
+- background
+- key experiences
+- technical + soft skills
+- strengths
+- ideal job roles
+"""
+
+    # -----------------------------------
+    # INTENT 3 → GENERAL CHAT
+    # -----------------------------------
+    else:
+        prompt = f"{system_msg}\nUser: {message}"
+
+    # -----------------------------------
+    # STREAMING HF LLM OUTPUT
+    # -----------------------------------
+    response = ""
+    for chunk in client.chat_completion(
+        messages=[{"role": "user", "content": prompt}],
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        stream=True
+    ):
+        token = chunk.choices[0].delta.content or ""
+        response += token
+        yield response
+
+
+# -----------------------------------
+# UI: ChatGPT-style interface
+# -----------------------------------
+chatbot = gr.ChatInterface(
+    fn=bot_response,
+    title="GenAI Career Agent"
+)
+
+
+# -----------------------------------
+# Layout (NO LOGIN)
+# -----------------------------------
+with gr.Blocks() as demo:
+    gr.Markdown("## Resume Analyst RAG Chatbot")
+    gr.Markdown("Uses FAISS + HuggingFace LLM + custom RAG analysis pipeline.")
+    chatbot.render()

requirements.txt

@@ -0,0 +1,12 @@
+gradio>=5.0
+huggingface_hub>=0.22.0
+langchain>=0.2.0
+langchain-community>=0.2.0
+langchain-huggingface>=0.1.0
+langchain-text-splitters>=0.0.1
+
+faiss-cpu
+sentence-transformers
+
+requests
+python-dotenv