update

Co-authored-by: Copilot <copilot@github.com>

README.md

@@ -1,25 +1,40 @@
+---
+title: GitConnect FastAPI Service
+emoji: "🚀"
+colorFrom: blue
+colorTo: green
+sdk: docker
+sdk_version: "1.0.0"
+python_version: "3.12"
+app_file: app.py
+pinned: false
+---
+
 # GitConnect FastAPI Service
 
-FastAPI backend with two endpoints:
-- Syllabus processing from PDF URLs with FAISS vector indexing and multilingual course summaries.
-- Chatbot endpoint using student performance data + semester-scoped syllabus RAG with MMR.
+FastAPI backend with two primary features:
+
+- Syllabus processing from PDF URLs with FAISS indexing and multilingual AI summaries.
+- Chatbot responses grounded with RAG from both syllabus content and student performance data.
 
-Embedding setup:
-- Uses local Hugging Face sentence embeddings (default: `sentence-transformers/all-MiniLM-L6-v2`).
-- Uses FAISS (`IndexFlatIP` with L2-normalized vectors) for similarity search.
-- Gemini is used for summarization and chatbot generation.
+## Core Stack
 
-## Setup
+- API: FastAPI + Uvicorn
+- Embeddings: sentence-transformers/all-MiniLM-L6-v2
+- Vector Search: FAISS (IndexFlatIP with normalized vectors)
+- LLM generation/summarization: Gemini
 
-1. Create a virtual environment and activate it.
+## Local Setup
+
+1. Create and activate a virtual environment.
 2. Install dependencies:
 
 ```bash
 pip install -r requirements.txt
 ```
 
-3. Create `.env` from `.env.example` and fill `GEMINI_API_KEY`.
-4. Run server:
+3. Create `.env` from `.env.example` and set `GEMINI_API_KEY`.
+4. Run the service:
 
 ```bash
 uvicorn app.main:app --reload
@@ -31,36 +46,39 @@ uvicorn app.main:app --reload
 - `POST /api/syllabus/process`
 - `POST /api/chat`
 
-## Deploy to Hugging Face Spaces
+Student performance source:
+
+- `STUDENT_PERFORMANCE_URL_TEMPLATE` (default)
+- `https://git-connect-backend-v2.vercel.app/api/student/{student_id}/performance`
+
+## Hugging Face Spaces Deployment
+
+This repository is set up for Docker Spaces deployment.
 
-This repo is configured for Docker Spaces deployment.
+Deployment-critical files:
 
-Files used for deployment:
 - `Dockerfile`
 - `requirements.txt`
 - `app/`
 - `.github/workflows/deploy-hf-space.yml`
 
-Files intentionally not pushed from local machine:
+Files excluded from git push:
+
 - `.env` and `app/.env`
-- `data/` generated files
+- generated `data/` files
 - local caches and `__pycache__/`
 
-GitHub Action deployment:
-- Trigger: push to `main` or manual run
-- Workflow file: `.github/workflows/deploy-hf-space.yml`
-
-Required GitHub repository secrets:
-- `HF_TOKEN`: Hugging Face write token
-- `HF_SPACE_REPO_ID`: in format `username/space-name`
+GitHub Action deployment workflow:
 
-After setting secrets, pushing to `main` will sync this repo to your Hugging Face Space `main` branch.
+- Trigger: push to `main` or manual run
+- Workflow: `.github/workflows/deploy-hf-space.yml`
+- Required repository secrets:
+  - `HF_TOKEN`
+  - `HF_SPACE_REPO_ID` (format: `username/space-name`)
 
-Student performance is fetched from:
-- `STUDENT_PERFORMANCE_URL_TEMPLATE` (default)
-- `https://git-connect-backend-v2.vercel.app/api/student/{student_id}/performance`
+## Sample Requests
 
-## Sample syllabus request
+Syllabus processing:
 
 ```json
 [
@@ -74,7 +92,7 @@ Student performance is fetched from:
 ]
 ```
 
-## Sample chat request
+Chat:
 
 ```json
 {
@@ -83,8 +101,12 @@ Student performance is fetched from:
     {"role": "user", "content": "Hi"},
     {"role": "assistant", "content": "Hello"}
   ],
-  "student_id": "STU123",
+  "student_id": 2,
   "lang_code": "en",
   "semester": 5
 }
 ```
+
+Configuration reference:
+
+- https://huggingface.co/docs/hub/spaces-config-reference