RAG‑Agent with ChromaDB and Web Search

A lightweight AI agent that can answer user questions by searching a local knowledge base stored in ChromaDB and the web via Tavily.
The agent automatically decides which source to use, making it ideal for exam‑style assignments or quick prototyping.

Features
Prerequisites
Installation
Project Structure
Running the Agent
- vectorstore.py
- main.py
Example Usage
License

Features

Feature	Description
Local RAG	Stores documents in a persistent ChromaDB collection.
Web Search	Uses Tavily to fetch up‑to‑date information from the internet.
LLM & Embeddings	Powered by Ollama (`llama3` for generation, `nomic-embed-text` for embeddings).
Agent	LangChain agent that chooses between local and web sources automatically.
Easy Setup	One‑liner install script and minimal configuration.

Prerequisites

Requirement	Command / Note
Python	`>=3.10` (recommended 3.11+)
Ollama	Install from https://ollama.ai
Tavily API Key	Sign up at https://tavily.com and set `TAVILY_API_KEY` in `.env`.

Installation

# Pull required models into Ollama
ollama pull llama3
ollama pull nomic-embed-text

# Install Python dependencies
pip install langchain langchain-chroma langchain-tavily langchain-ollama tavily-python chromadb python-dotenv

Create a .env file in the project root:

TAVILY_API_KEY=your_tavily_api_key_here

Project Structure

.
├── vectorstore.py   # Helpers for creating/loading ChromaDB and adding docs
├── main.py          # Agent entry point
└── .env             # Tavily API key (not committed)

vectorstore.py
- create_vectorstore(persist_directory) – returns a ready‑to‑use Chroma collection.
- load_documents(directory, vectorstore) – reads .txt/.md, splits into chunks, and adds them to the store.
main.py
Sets up the LangChain agent with two tools:
- search_local_kb(query, top_k) – semantic search in Chroma.
- web_search(query) – Tavily web search.
  The agent decides which tool to invoke based on the query.

Running the Agent

1. Prepare the Knowledge Base

# Place your .txt or .md files into a folder, e.g., ./docs
mkdir docs
echo "Hello world!" > docs/hello.txt

# Load them into ChromaDB
python -c "
from vectorstore import create_vectorstore, load_documents
vs = create_vectorstore()
load_documents('docs', vs)
print('Documents loaded')
"

2. Start the Agent

python main.py

You will see a prompt:

> What would you like to know?

Type any question; the agent will answer using either the local KB or Tavily.

Example Usage

> Who is the current President of France?

Agent: The current President of France is Emmanuel Macron. (Source: web_search)

> Summarize the contents of hello.txt

Agent: The file contains a simple greeting: "Hello world!". (Source: search_local_kb)

The agent automatically selects the most relevant source.

3.3 KiB Raw Blame History Unescape Escape