Develop a self-hosted production-ready AI-powered chat app or service at a rapic pace with this powerful Firebase Genkit (opens in a new tab) and LangChain (opens in a new tab) based framework.

QvikChat is a framework that provides you with a solid foundation to build powerful AI-powered chat service endpoints quickly and efficiently. It includes support for multiple types of conversations (open-ended, close-ended), chat history, response caching, authentication, and information retrieval using Retrieval Augmented Generation (RAG).

QvikChat RAG endpoint demo

Note: This is not an official Firebase Genkit or LangChain framework. This is a community-driven project. Firebase Genkit is currently in beta, this means that the public API and framework design may change in backward-incompatible ways. We will do our best to keep this project up-to-date.

If you find value from this project, please consider contributing or sponsoring the project to help maintain and improve it. All contributions and support are greatly appreciated!

Features

Features

• Firebase Genkit: Built using the open-source Firebase Genkit framework (opens in a new tab) to help you build powerful production-ready AI-powered services with the possibility of easily extending the framework's functionalities through Genkit plugins.
• LangChain: Built using the open-source LangChain framework (opens in a new tab) to help you process data for RAG and information retrieval. Easily extend the framework by using any LangChain-supported embedding model, vector store, data loader, and more.
• Deploy to any NodeJS platform: Deploy your app or service to any NodeJS platform, including Firebase, Google Cloud, AWS, Heroku, etc., with ease.
• Firebase Firestore: In-built support for using Cloud Firestore (opens in a new tab) as the chat history store, cache store, and API key store.
• Endpoints with Chat History, Authentication, Caching, and RAG: Built-in architecture to help you build chat endpoints with support for conversation history, authenticated endpoints, response caching for faster response times, and RAG for answering queries that require additional context data.
• RAG: Built-in support for loading text, CSV, JSON, PDF, or code files easily, and generating and storing embeddings in a vector store to support information retrieval for context-aware chat endpoints. Add additional data loaders easily through LangChain, for example, to support ingesting data from cloud storage. For all available integrations for data loaders, check Document loaders | 🦜️🔗 Langchain. (opens in a new tab)
• Focus on Performance, Reliability, and Security: Every component in QvikChat is built to ensure low latency and scalable performance without compromising on security. From using prompts that help mitigate LLM hallucination and deter prompt injection attacks, to providing in-built support for enabling authentication for each endpoint, QvikChat is designed to help you build secure, performant, and reliable chat apps and services.