https://github.com/rubenszimbres/graph_rag

A Flask app running GraphRAG for healthcare, made with Vertex AI and Neo4j, to be deployed in a container (Cloud Run or ECS).
https://github.com/rubenszimbres/graph_rag

agents cloudrun cloudrun-service containers docker gpt-4 graphrag langchain langchain-python python python3 rag retrieval-augmented-generation vertexai

Last synced: 2 days ago
JSON representation

A Flask app running GraphRAG for healthcare, made with Vertex AI and Neo4j, to be deployed in a container (Cloud Run or ECS).

• Host: GitHub
• URL: https://github.com/rubenszimbres/graph_rag
• Owner: RubensZimbres
• License: apache-2.0
• Created: 2024-08-05T13:55:29.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-08-10T20:39:26.000Z (3 months ago)
• Last Synced: 2024-08-11T15:40:31.080Z (3 months ago)
• Topics: agents, cloudrun, cloudrun-service, containers, docker, gpt-4, graphrag, langchain, langchain-python, python, python3, rag, retrieval-augmented-generation, vertexai
• Language: Python
• Homepage:
• Size: 1.66 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Graph_RAG

  

Description  

This project is a Flask app running GraphRAG for healthcare, made with Vertex AI and Neo4j, to be deployed in a container (Cloud Run or ECS). Initially, a PDF with diseases descriptions is used to enrich the LLM response via RAG. Then, another LLM automatically parses a CSV file with diseases data, generates the Knowledge Graph. After that, an LLM generates a cypher to query the Neo4j KG database and retrieve the possibles diseases, given the patient medical report.  

  

Deployment in Google Cloud Run  

  

Remove user input from `app.py` and get JSON via Flask. 

Add your secrets to Secret Manager

Adapt configurations in` config.json`

    

```

export GCP_PROJECT='your-project'

export GCP_REGION='us-central1'

export AR_REPO='repo-graphrag'

export SERVICE_NAME='flask-app-graphrag'

  

gcloud artifacts repositories create "$AR_REPO" --location="$GCP_REGION" --repository-format=Docker

gcloud auth configure-docker "$GCP_REGION-docker.pkg.dev"

gcloud builds submit --tag "$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME"

gcloud run deploy "$SERVICE_NAME" \

     --port=8080 \

     --image="$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME" \

     --allow-unauthenticated \

     --platform=managed  \

     --region=$GCP_REGION \

     --project=$GCP_PROJECT \

     --set-env-vars=GCP_PROJECT=$GCP_PROJECT,GCP_REGION=$GCP_REGION \

     --min-instances 1 --max-instances 5 --cpu 1 --memory 2048Mi --concurrency 10

```