Update README.md

README.md

@@ -1,66 +1,62 @@
-# RAG Agent with ChromaDB and Tavily
+# RAG Agent with ChromaDB and Web Search
 
-## Overview
+This repository implements a simple RAG (Retrieval‑Augmented Generation) agent that can answer questions using a local knowledge base stored in **ChromaDB** and also perform real‑time web search via **Tavily**. The agent automatically decides which source to use and reports the chosen source in the answer.
-
-This repository implements a **RAG (Retrieval‑Augmented Generation) agent** that can answer questions by searching a local knowledge base stored in **ChromaDB** or by fetching up‑to‑date information from the web using **Tavily**. The agent automatically chooses the most appropriate source based on the query and returns the answer together with the source identifier.
 
 ## Features
 
-- **Local Knowledge Base** – Vector store backed by ChromaDB with embeddings from Ollama (`nomic-embed-text`).
+- **Local knowledge base** – Text files (.txt, .md) are loaded, chunked, and stored in a persistent ChromaDB collection.
-- **Web Search** – Uses Tavily API for real‑time web queries.
+- **Semantic search** – Uses Ollama embeddings (`nomic-embed-text`).
-- **Automatic Routing** – The agent decides whether to use the local KB or the web search.
+- **Web search** – Powered by Tavily.
-- **CLI** – Simple command‑line interface for interactive queries.
+- **Automatic source selection** – The agent chooses between local and web search based on the query.
-- **Persistence** – The ChromaDB store is persisted between runs.
+- **CLI** – Simple chat loop with `exit` to quit.
 
 ## Setup
 
-1. **Install Ollama** and pull the required models:
+```bash
-   ```bash
+# 1. Create a virtual environment (optional but recommended)
-   ollama pull llama3
+python -m venv venv
-   ollama pull nomic-embed-text
+source venv/bin/activate   # Windows: venv\Scripts\activate
-   ```
 
-2. **Install Python dependencies**:
+# 2. Install dependencies
-   ```bash
+pip install -r requirements.txt
-   pip install -r requirements.txt
-   ```
 
-3. **Set up the Tavily API key**. Create a `.env` file in the project root with:
+# 3. Pull required Ollama models
-   ```env
+ollama pull llama3
-   TAVILY_API_KEY=your_api_key_here
+ollama pull nomic-embed-text
-   ```
 
-4. **Add documents** you want to index into the `documents/` folder. The script will automatically load `.txt` and `.md` files.
+# 4. Set your Tavily API key
+export TAVILY_API_KEY=YOUR_KEY   # Windows: set TAVILY_API_KEY=YOUR_KEY
+```
 
 ## Usage
 
-```bash
+1. **Load documents** – Place your `.txt` or `.md` files in the `documents/` folder.
-python main.py
+2. **Run the agent**
-```
+   ```bash
+   python agent.py
+   ```
+3. **Chat** – Type your question. Type `exit` to quit.
 
-You will be prompted for a query. Type `exit` to quit.
+## Example
 
-Example:
 ```
 Query: Какие последние новости про AI-агентов?
-Answer:
+[Web Search] ...
-[Web Search]
+Источник: tavily
-1. AI Agents are ...
+
-   https://example.com
+Query: Что в наших конспектах про LangGraph?
-   ...
+[Local KB] ...
-Source: tavily
+Источник: chromadb
 ```
 
 ## Project Structure
 
-- `vectorstore.py` – Helper functions for creating and populating the ChromaDB vector store.
+- `vectorstore.py` – Functions to create and load the ChromaDB vector store.
-- `agent.py` – Defines the tools and initializes the LangChain agent.
+- `rag_tools.py` – Two LangChain tools: `search_local_kb` and `web_search`.
-- `main.py` – CLI entry point.
+- `agent.py` – Main script that sets up the agent and runs the chat loop.
 - `requirements.txt` – Python dependencies.
-- `README.md` – Documentation.
+- `README.md` – This file.
 
-## Notes
+## License
 
-- The agent uses the **Zero‑Shot React** strategy. It may call both tools if the query is ambiguous. You can tweak the prompt or the routing logic if needed.
+MIT License.
-- The ChromaDB store is persisted in `./chroma_db`. Delete this folder to re‑index.
-- Ensure the Ollama server is running locally when executing the agent.