Module-1Ai_Agent_Chatbot
First, paste the code I provided into any code editor. Then, to check the RAG capabilities, download the Python documentation and update the file path in the code according to your downloaded directory. After that, run the code and run this developer server [ http://localhost:5000 ] in any browser. Also, mak
flask==3.0.0
flask-cors==4.0.0
langchain==0.1.0
langchain-community==0.0.13
langchain-core==0.1.10
langchain-chroma==0.1.0
langchain-ollama==0.1.0
chromadb==0.4.22
pypdf==4.0.1
tiktoken==0.5.2
pydantic==2.5.3
e sure that the essential dependencies and the Ollama LLM are installed on your machine before running it.
:::
What it does:
A Python-powered AI chatbot that answers programming questions using RAG (Retrieval-Augmented Generation) technology.
How it works:
- Vector Database: Stores Python documentation in Chroma vector store
- Retrieval: When user asks a question, retrieves 5 most relevant documents
- LLM Processing: Llama 3.2 model generates accurate answers using retrieved context
- Web Interface: Flask backend serves a simple chat UI
Tech Stack:
- Backend: Python, Flask, LangChain
2.AI Model: Ollama (Llama 3.2:1b)
3.Embeddings: mxbai-embed-large
4.Vector Store: ChromaDB
5.Frontend: HTML/CSS/JavaScript with real-time chat
Key Features:
- Real-time AI responses
- Context-aware answers from knowledge base
- Lightweight model for low-resource systems
- Clean, professional dark UI
- Persistent chat history during session
Use Case:
Helps developers get instant, accurate answers about Python programming by combining document retrieval with AI generation.
Github Link: https://github.com/devangdhakaai-create/Tensor-Flow-Ai-Agent/pull/1