FAQ Bot (ChromaDB + MCP-style tool)

Overview

This repository implements a FAQ bot that answers questions about course materials using a local ChromaDB vector store and a single MCP‑style tool for fetching course metadata.

Technology stack

Python 3.10+
ChromaDB (langchain-chroma) with Ollama embeddings (langchain-ollama, model nomic-embed-text)
LangChain agent (langchain)
httpx for the mock MCP tool
python-dotenv for environment variables

How it works

Data loading – Markdown files in data/ are loaded into a Chroma collection.
Tools –
- search_course_docs – searches the local FAQ.
- fetch_course_meta – reads a local JSON file (course_meta.json) simulating an MCP call.
Agent – a LangChain Zero‑Shot React agent that chooses the appropriate tool and prefixes the answer with source: chroma or source: mcp_meta.
CLI – pre‑defined questions and an interactive mode.

Running

# Install dependencies
pip install -r requirements.txt

# Pull the Ollama embedding model
ollama pull nomic-embed-text

# Run the bot
python main.py

MCP‑style tool note

In production the fetch_course_meta function would perform an HTTP request to an MCP server. Here it simply reads a local JSON file for demonstration purposes.

1.3 KiB Raw Blame History Unescape Escape