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
Version used
Python v3.12.9, Serverless v4, Langgraph v0.2.6
Environment details (OS name and version, etc.)
Linux
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
Version used
Python v3.12.9, Serverless v4, Langgraph v0.2.6
Environment details (OS name and version, etc.)
Linux