About
No description or labels provided.
Meta
No variables defined in the prompt.
Tools
No tools added to the Pipe.
Readme
Build RAG Application for QnA with Documents — ⌘ Langbase
A RAG application example to help you create a powerful QnA system for your documents. This application is built by using a RAG Pipe on Langbase, it works with 30+ LLMs (OpenAI, Gemini, Mistral, Llama, Gemma, etc), any Data (10M+ context with Memory sets), and any Framework (standard web API you can use with any software).
Follow step-by-step instructions to build your own RAG application with Langbase. Check out the live demo here.
Features
- 🤔 Question & Answer: Ask questions from the content of your files.
- 🔗 Langbase Integration: Utilize Langbase's powerful Pipes and Memory services
- ⚡️ Streaming — Get real-time answers with streamed responses
- 🧩 Customizable: Easily extend and modify the application to fit your needs.
Learn more
- Check the Documents QnA Pipe on ⌘ Langbase
- Read the source code on GitHub for this example
- Go through Documentaion: Pipe Quick Start
- Learn more about Pipes & Memory features on ⌘ Langbase
Get started
Let's get started with the project:
To get started with Langbase, you'll need to create a free personal account on Langbase.com and verify your email address. Done? Cool, cool!
- Fork the Documents QnA Pipe on ⌘ Langbase.
- Go to the API tab to copy the Pipe's API key (to be used on server-side only).
- Download the example project folder from here or clone the repository.
cd
into the project directory and open it in your code editor.- Duplicate the
.env.example
file in this project and rename it to.env.local
. - Add the following environment variables:
sh1# Replace `LANGBASE_PIPE_API_KEY` with the copied API key. 2LANGBASE_PIPE_API_KEY="LANGBASE_PIPE_API_KEY" 3 4# Install the dependencies using the following command: 5npm install 6 7# Run the project using the following command: 8npm run dev
Your app template should now be running on localhost:3000.
NOTE: This is a Next.js project, so you can build and deploy it to any platform of your choice, like Vercel, Netlify, Cloudflare, etc.
Authors
This project is created by Langbase team members, with contributions from:
- Saqib Ameen (@saqibameen) - Founding Engineer, Langbase
Built by ⌘ Langbase.com — Ship hyper-personalized AI assistants with memory!