A full-stack chatbot application that uses RAGS to interact intelligently with users based on custom-loaded knowledgebases. It supports dynamic dataset loading for seamless updates. The chatbot’s language model is evaluated on relevance, accuracy, coherence, completeness, creativity, tone, and alignment with intent, ensuring high-quality, user-focused interactions.

• React
• Tailwindcss
• FastAPI
• ChromaDB
• Langchain
• OpenAI
• Docker

This diagram illustrates the high level components involved and thier interaction Flowchart

Chatbot

Before running the project, make sure to adjust the following configuration files:

• Adjust the .env file located in the backend folder if any environment variables need modification.

To start the project, use Docker Compose to build and run the containers:

docker compose up --build

Once the containers are running, you can access the frontend application at:

http://localhost:5173/

Once the containers are running, you can access the backend application at:

http://localhost:8081/

• Add SQL/NoSQL DB to store the user queries and generated reponses

https://github.com/pixegami/langchain-rag-tutorial