# RAG Agent with Qdrant + Ollama

## Stack
- Python 3.10+
- Qdrant — vector database
- Ollama — local LLM and embeddings (`llama3`, `nomic-embed-text`)
- LangChain — agent and RAG framework

## Setup

### 1. Pull Ollama models
```bash
ollama pull llama3
ollama pull nomic-embed-text
```

### 2. Start Qdrant
```bash
docker run -p 6333:6333 qdrant/qdrant
```

### 3. Install Python dependencies
```bash
pip install -r requirements.txt
```

## Usage

### Initialize knowledge base from a directory
```bash
python init_knowledge_base.py ./docs
```
Loads all `.txt` and `.md` files from the given directory into the vector store.

### Run the interactive client
```bash
python client.py
```

### Client commands
| Command | Description |
|---------|-------------|
| `/add <title> \| <content>` | Add a document to the knowledge base |
| `/search <query>` | Semantic search in the knowledge base |
| `/quit` | Exit the client |
| `<any text>` | Send a question to the RAG agent |

## Project Structure

```
.
├── vector_store.py        # Qdrant + Ollama embeddings + chunking
├── tools.py               # @tool: search_knowledge_base, add_to_knowledge_base
├── agent.py               # create_react_agent with RAG tools
├── init_knowledge_base.py # Load documents from directory
├── client.py              # Interactive CLI client
└── requirements.txt
```