{"id":13576089,"url":"https://github.com/asaniczka/SERP-RAG-Chatlorin","last_synced_at":"2025-04-05T05:30:42.072Z","repository":{"id":228251847,"uuid":"772933033","full_name":"asaniczka/SERP-RAG-Chatlorin","owner":"asaniczka","description":"Starter project for creating an API endpoint that performs web searches, scrapes results, and generates answers using LLM.","archived":false,"fork":false,"pushed_at":"2024-07-07T12:33:07.000Z","size":336,"stargazers_count":4,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T23:41:53.332Z","etag":null,"topics":["chromadb","gemini-pro","llm","rag","serp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/asaniczka.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-03-16T09:24:57.000Z","updated_at":"2025-02-06T03:47:25.000Z","dependencies_parsed_at":"2024-03-17T21:44:04.897Z","dependency_job_id":"ff7ba7d8-0431-4a57-83eb-c19042bd5ca4","html_url":"https://github.com/asaniczka/SERP-RAG-Chatlorin","commit_stats":null,"previous_names":["asaniczka/serp-rag-chatlorin"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asaniczka%2FSERP-RAG-Chatlorin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asaniczka%2FSERP-RAG-Chatlorin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asaniczka%2FSERP-RAG-Chatlorin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asaniczka%2FSERP-RAG-Chatlorin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/asaniczka","download_url":"https://codeload.github.com/asaniczka/SERP-RAG-Chatlorin/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247294068,"owners_count":20915330,"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":["chromadb","gemini-pro","llm","rag","serp"],"created_at":"2024-08-01T15:01:06.907Z","updated_at":"2025-04-05T05:30:39.443Z","avatar_url":"https://github.com/asaniczka.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# LLM Chat Endpoint with Internet Access\n\nThis Python project focuses on creating an API endpoint that:\n\n1. Searches Google for information\n2. Scrapes the results\n3. Processes the pages for RAG\n4. Uses an LLM to generate an answer\n5. and returns the response.\n\n## Notes:\n\n### Messages\n\n- Most of the core function have been written to be LLM independent.\n- The core uses `BaseMessageLog` and `BaseMessage` to pass around messages and roles.\n- Only the Gemini module uses Gemini-specific formats.\n- You can replace the Gemini-specific formats with OpenAI chat format and the core should still work.\n\n### Working Mode\n\n- By default, the Dockerfile sets the app to be in low-memory mode.\n- This mode will not use JavaScript rendering to load pages.\n- The performance is decent, but if you wish to increase the number of pages scraped, set the `WORKING_MODE` env to anything other than `low-mem`.\n\n## How to Use\n\n1. Clone the project repository to your local machine\n2. Run `docker build -t serp_rag:latest .`\n3. Launch a container with `docker run -p 8080:8000 --name serp_rag_con -e GOOGLE_GEMINI_KEY=\"YOUR GEMINI KEY\" serp_rag:latest`\n4. Load up `https://localhost:8080/docs` and try the API.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasaniczka%2FSERP-RAG-Chatlorin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fasaniczka%2FSERP-RAG-Chatlorin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasaniczka%2FSERP-RAG-Chatlorin/lists"}