{"id":18594136,"url":"https://github.com/rubenszimbres/graph_rag","last_synced_at":"2025-05-05T15:23:10.685Z","repository":{"id":251763412,"uuid":"838369587","full_name":"RubensZimbres/Graph_RAG","owner":"RubensZimbres","description":"A Flask app running GraphRAG for healthcare, made with Vertex AI and Neo4j, to be deployed in a container (Cloud Run or ECS).","archived":false,"fork":false,"pushed_at":"2024-08-13T17:35:29.000Z","size":1741,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-30T22:03:18.235Z","etag":null,"topics":["agents","cloudrun","cloudrun-service","containers","docker","gpt-4","graphrag","langchain","langchain-python","python","python3","rag","retrieval-augmented-generation","vertexai"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RubensZimbres.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-05T13:55:29.000Z","updated_at":"2024-12-21T19:36:01.000Z","dependencies_parsed_at":"2024-12-26T20:25:26.866Z","dependency_job_id":"2194e8fa-c3db-4d59-850e-f71f5a462ae6","html_url":"https://github.com/RubensZimbres/Graph_RAG","commit_stats":null,"previous_names":["rubenszimbres/graph_rag"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FGraph_RAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FGraph_RAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FGraph_RAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RubensZimbres%2FGraph_RAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RubensZimbres","download_url":"https://codeload.github.com/RubensZimbres/Graph_RAG/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252522403,"owners_count":21761725,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","cloudrun","cloudrun-service","containers","docker","gpt-4","graphrag","langchain","langchain-python","python","python3","rag","retrieval-augmented-generation","vertexai"],"created_at":"2024-11-07T01:14:36.306Z","updated_at":"2025-05-05T15:23:10.670Z","avatar_url":"https://github.com/RubensZimbres.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Graph_RAG\n  \n\u003cb\u003eDescription\u003c/b\u003e  \nThis 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.  \n  \n\u003cb\u003eDeployment in Google Cloud Run\u003c/b\u003e  \n  \nRemove user \u003cb\u003einput\u003c/b\u003e from `app.py` and get JSON via Flask. \nAdd your secrets to Secret Manager\nAdapt configurations in` config.json`\n    \n```\nexport GCP_PROJECT='your-project'\nexport GCP_REGION='us-central1'\nexport AR_REPO='repo-graphrag'\nexport SERVICE_NAME='flask-app-graphrag'\n  \ngcloud artifacts repositories create \"$AR_REPO\" --location=\"$GCP_REGION\" --repository-format=Docker\ngcloud auth configure-docker \"$GCP_REGION-docker.pkg.dev\"\ngcloud builds submit --tag \"$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME\"\n\ngcloud run deploy \"$SERVICE_NAME\" \\\n     --port=8080 \\\n     --image=\"$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME\" \\\n     --allow-unauthenticated \\\n     --platform=managed  \\\n     --region=$GCP_REGION \\\n     --project=$GCP_PROJECT \\\n     --set-env-vars=GCP_PROJECT=$GCP_PROJECT,GCP_REGION=$GCP_REGION \\\n     --min-instances 1 --max-instances 5 --cpu 1 --memory 2048Mi --concurrency 10\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frubenszimbres%2Fgraph_rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frubenszimbres%2Fgraph_rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frubenszimbres%2Fgraph_rag/lists"}