update the README.md file

README.md

@@ -35,7 +35,7 @@
 
 **IntegraChat** is an enterprise-ready, multi-tenant AI platform built to demonstrate the full capabilities of the **Model Context Protocol (MCP)** in a real production-style environment.
 
-It combines **autonomous tool-using agents**, **RAG retrieval**, **live web search**, and **admin governance** under strict **tenant isolation**, powered by Groq's **Llama-3.1-8B**.
+It combines **autonomous tool-using agents**, **RAG retrieval**, **live web search**, and **admin governance** under strict **tenant isolation**, powered by **Ollama** (local) or **Groq** (cloud) LLM inference.
 
 IntegraChat is a complete **"MCP in Action"** ecosystem — ideal for enterprise demos, research, production scaffolds, and governance-focused AI deployments.
 
@@ -66,15 +66,16 @@ Agents can intelligently:
 - ✅ Retrieve tenant-private knowledge
 - ✅ Pull real-time data from the internet
 - ✅ Trigger admin alerts when needed
-- ✅ Respond using Groq's **Llama-3.1-8B**
+- ✅ Respond using **Ollama** (local) or **Groq** (cloud) LLM
 
 ### 2. 📚 Enterprise RAG System
 
-- **MiniLM embeddings** for semantic search
+- **MiniLM embeddings** (384-dim) for semantic search
 - **Supabase + pgvector** for vector storage
-- **Strict multi-tenant RLS enforcement** for security
-- **Multiple format support**: PDF / DOCX / TXT / URL ingestion
-- **Intelligent chunking** + semantic search
+- **Automatic database schema initialization** on server startup
+- **Strict multi-tenant isolation** with tenant_id filtering
+- **Intelligent text chunking** (~300 words per chunk)
+- **Vector similarity search** using cosine distance
 
 ### 3. 🌐 Live Web Search Tool
 
@@ -126,8 +127,9 @@ Isolation is guaranteed via **Supabase Row-Level Security (RLS)**.
 | **FastAPI** | High-performance API framework |
 | **MCP Client + Servers** | Model Context Protocol implementation |
 | **Supabase** | Auth + Storage + pgvector database |
-| **MiniLM Embeddings** | Semantic search embeddings |
-| **Groq Llama-3.1-8B** | LLM inference engine |
+| **PostgreSQL + pgvector** | Vector database for embeddings |
+| **MiniLM Embeddings** | Semantic search embeddings (384-dim) |
+| **Ollama / Groq** | LLM inference engine (configurable) |
 | **DuckDuckGo Search** | Web search provider |
 | **Slack / Email** | Alerting system |
 
@@ -215,41 +217,14 @@ IntegraChat/
 │   │   │   ├── logging.py
 │   │   │   ├── supabase_client.py
 │   │   │   ├── tenant_context.py
-│   │   │   └── security.py
+│   │   │   ├── security.py
+│   │   │   └── text_extractor.py   
 │   │   └── config.py
 │   │
 │   ├── mcp_servers/
-│   │   ├── rag_server/
-│   │   │   ├── main.py
-│   │   │   ├── chunker.py
-│   │   │   ├── search.py
-│   │   │   ├── embeddings.py
-│   │   │   ├── ingestion/
-│   │   │   │   ├── ingest_pdf.py
-│   │   │   │   ├── ingest_docx.py
-│   │   │   │   ├── ingest_txt.py
-│   │   │   │   └── ingest_url.py
-│   │   │   ├── db/
-│   │   │   │   ├── documents_repo.py
-│   │   │   │   └── embeddings_repo.py
-│   │   │   └── config.py
-│   │   │
-│   │   ├── web_server/
-│   │   │   ├── main.py
-│   │   │   ├── providers/
-│   │   │   │   ├── ddg.py
-│   │   │   │   ├── serpapi.py (optional)
-│   │   │   │   └── bing.py (optional)
-│   │   │   └── utils.py
-│   │   │
-│   │   └── admin_server/
-│   │       ├── main.py
-│   │       ├── redflag_rules.py
-│   │       ├── alerts/
-│   │       │   ├── slack.py
-│   │       │   ├── email.py
-│   │       │   └── webhook.py
-│   │       └── audit_logs.py
+│   │   ├── main.py              # RAG MCP Server (FastAPI)
+│   │   ├── database.py          # Supabase/PostgreSQL connection
+│   │   └── embeddings.py        # Sentence transformers embeddings
 │   │
 │   ├── workers/
 │   │   ├── ingestion_worker.py
@@ -341,9 +316,10 @@ IntegraChat/
 Before you begin, ensure you have the following installed:
 
 - ✅ **Python 3.10+**
-- ✅ **Node.js 18+**
-- ✅ **Supabase project** (with pgvector extension)
-- ✅ **Groq API key**
+- ✅ **Node.js 18+** (for frontend)
+- ✅ **Supabase project** (with pgvector extension enabled)
+- ✅ **PostgreSQL connection string** (from Supabase)
+- ✅ **Ollama** (for local LLM) or **Groq API key** (for cloud LLM)
 - ✅ **DuckDuckGo Search key** (optional, if configured)
 - ✅ **Slack/Email webhook** for alerts (optional)
 
@@ -360,16 +336,65 @@ Before you begin, ensure you have the following installed:
    ```
 
 3. **Configure environment variables**
+   
+   Create a `.env` file in the project root with the following:
+   ```env
+   # Database Configuration
+   POSTGRESQL_URL=postgresql://user:password@host:port/database
+   SUPABASE_URL=https://your-project.supabase.co
+   SUPABASE_SERVICE_KEY=your_service_role_key
+   
+   # MCP Server URLs
+   RAG_MCP_URL=http://localhost:8001
+   WEB_MCP_URL=http://localhost:8002
+   ADMIN_MCP_URL=http://localhost:8003
+   
+   # LLM Configuration
+   OLLAMA_URL=http://localhost:11434
+   OLLAMA_MODEL=llama3
+   # Or use Groq instead:
+   # GROQ_API_KEY=your_groq_api_key
+   ```
+
+4. **Start the RAG MCP Server**
    ```bash
-   cp .env.example .env
-   # Edit .env and fill in your Supabase + Groq keys
+   cd backend/mcp_servers
+   python main.py
    ```
+   The server will automatically initialize the database schema on startup.
+   - Server runs on `http://localhost:8001`
+   - API docs available at `http://localhost:8001/docs`
 
-4. **Run the development server**
+5. **Run the main API server**
    ```bash
+   cd backend
    uvicorn api.main:app --reload
    ```
 
+### RAG MCP Server API
+
+The RAG MCP Server provides two main endpoints:
+
+**Ingest Documents:**
+```bash
+curl -X POST http://localhost:8001/ingest \
+  -H "Content-Type: application/json" \
+  -d '{
+    "tenant_id": "tenant123",
+    "content": "Your document text here..."
+  }'
+```
+
+**Semantic Search:**
+```bash
+curl -X POST http://localhost:8001/search \
+  -H "Content-Type: application/json" \
+  -d '{
+    "tenant_id": "tenant123",
+    "query": "What are the HR policies?"
+  }'
+```
+
 ### Frontend Setup
 
 1. **Navigate to frontend directory**
@@ -438,7 +463,7 @@ Contributions are welcome! Please feel free to submit a Pull Request.
 ## 🙏 Acknowledgments
 
 - Built with [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)
-- Powered by [Groq](https://groq.com/) for LLM inference
+- Powered by [Ollama](https://ollama.ai/) or [Groq](https://groq.com/) for LLM inference
 - Database powered by [Supabase](https://supabase.com/)
 
 ---