Skip to content

A platform to test multiple LLM models inside a RAG workflow to choose the best model for embedding and retrieval and the best prompt according to the use case

Notifications You must be signed in to change notification settings

riolaf05/langchain-fastapi-rag-platform

Repository files navigation

Setup on GCP Cloud RUN

  1. Create exports
export PROJECT_ID=progetti-poc
export APP=langchain-fastapi-rag-platform 
export PORT=3000
export REGION=europe-west8
export BRANCH=main
export TAG=${REGION}-docker.pkg.dev/${PROJECT_ID}/${APP}/${APP}:${BRANCH}
  1. Create Artifact Repo
gcloud artifacts repositories create langchain-fastapi-rag-platform --repository-format Docker --location europe-west8 --project progetti-poc
  1. Create Build
gcloud builds submit --tag  europe-west8-docker.pkg.dev/progetti-poc/langchain-fastapi-rag-platform/langchain-fastapi-rag-platform:main --project progetti-poc
  1. Deploy
gcloud run deploy $APP --image $TAG --platform managed --region $REGION --port $PORT --allow-unauthenticated --env-vars-file=.env
  1. Clean
gcloud run services delete $APP --region $REGION 
gcloud run services list

About

A platform to test multiple LLM models inside a RAG workflow to choose the best model for embedding and retrieval and the best prompt according to the use case

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published