examples: Create a Langgraph RAG with Fastapi and Serverless Framework backend project

[edamico]

Describe the feature

Description We need to create a reference implementation of a Retrieval-Augmented Generation (RAG) pipeline using LangGraph, exposed via FastAPI, and deployed in a serverless environment.

Requirements Implement a LangGraph-based RAG workflow. Expose the API using FastAPI. Use serverless framework Deploy the solution in a serverless environment (AWS Lambda, Google Cloud Run, etc.). Ensure efficient retrieval and response generation. Provide clear documentation and deployment instructions.

Use Case

As developers working on AI-driven applications, we need a scalable and cost-efficient way to deploy RAG workflows without managing complex infrastructure.

Proposed Solution

No response

Other Information

No response

Acknowledgements

• [x] I may be able to implement this feature request
• [ ] This feature might incur a breaking change

Version used

Python v3.12.9, Serverless v4, Langgraph v0.2.6

Environment details (OS name and version, etc.)

Linux