{"id":46431021,"url":"https://github.com/wei/mlh-gemini-rag-workshop","last_synced_at":"2026-03-05T18:11:47.036Z","repository":{"id":338897946,"uuid":"1159465278","full_name":"wei/mlh-gemini-rag-workshop","owner":"wei","description":"Build a RAG-powered doc assistant with Gemini File Search","archived":false,"fork":false,"pushed_at":"2026-02-17T00:22:27.000Z","size":1250,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-02-17T06:47:43.468Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/wei.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-16T19:02:41.000Z","updated_at":"2026-02-17T00:22:30.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/wei/mlh-gemini-rag-workshop","commit_stats":null,"previous_names":["wei/mlh-gemini-rag-workshop"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/wei/mlh-gemini-rag-workshop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wei%2Fmlh-gemini-rag-workshop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wei%2Fmlh-gemini-rag-workshop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wei%2Fmlh-gemini-rag-workshop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wei%2Fmlh-gemini-rag-workshop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wei","download_url":"https://codeload.github.com/wei/mlh-gemini-rag-workshop/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wei%2Fmlh-gemini-rag-workshop/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30141716,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T16:58:46.102Z","status":"ssl_error","status_checked_at":"2026-03-05T16:58:45.706Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2026-03-05T18:11:46.376Z","updated_at":"2026-03-05T18:11:47.012Z","avatar_url":"https://github.com/wei.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MLH Gemini RAG Workshop\n\nBuild a RAG-powered doc assistant with [Gemini File Search](https://ai.google.dev/gemini-api/docs/file-search) for [MLH Global Hack Week](https://ghw.mlh.io/).\n\n## What You'll Build\n\nA chatbot that can answer questions about MLH's documentation using **Retrieval-Augmented Generation (RAG)**. Upload docs, ask questions, get accurate answers with citations — no hallucinations.\n\nThe same technique works with **any** documentation. Swap in your own docs after the workshop!\n\n## Workshop: Python + Streamlit\n\n| | Details |\n|---|---|\n| **Folder** | [`python/`](./python/) |\n| **Stack** | Python 3.10+, Streamlit, `google-genai` SDK |\n| **UI** | Streamlit chat components (chat interface in 10 lines!) |\n| **Best For** | Learning RAG concepts deeply, rapid prototyping |\n| **Deploy** | `streamlit run app.py` (or Streamlit Cloud for free hosting) |\n\n## Demo Corpus: MLH Resources\n\nThe workshop uses these MLH docs as the knowledge base:\n\n- [MLH Hackathon Organizer Guide](https://github.com/MLH/mlh-hackathon-organizer-guide) (organizer guide chapters, timeline, sponsorship, judging, community values)\n- [MLH Policies](https://github.com/MLH/mlh-policies/tree/main) (code of conduct, community values)\n- [MLH Hack Days Organizer Guide](https://github.com/MLH/mlh-hack-days-organizer-guide)\n\n## What is RAG?\n\n**Retrieval-Augmented Generation** solves a core LLM problem: models don't know about your private docs and can hallucinate when asked about them.\n\nRAG works in 3 steps:\n1. **Index** — Split your docs into chunks, convert to embeddings (numerical vectors), store in a vector database\n2. **Retrieve** — When a user asks a question, find the most relevant chunks via semantic search\n3. **Generate** — Feed the retrieved chunks to the LLM as context, generating an accurate, grounded answer\n\n**Gemini File Search** handles all of this automatically — no external vector database, no chunking logic, no embedding pipeline. Upload files, query, done.\n\n## Prerequisites\n\n- A [Google AI Studio](https://aistudio.google.com/) account and API key (free)\n- Python 3.10+, pip\n- No AI/ML experience required!\n\n## Getting Started\n\n```bash\n# Clone the repo\ngit clone https://github.com/wei/mlh-gemini-rag-workshop.git\ncd mlh-gemini-rag-workshop/python\n\n# Follow the STREAM_PLAN.md or docs/WORKSHOP.md\n```\n\n## Quick Demo\n\n```bash\ncd python/finished/\npip install -r requirements.txt\ncp .env.example .env\n# Add your GEMINI_API_KEY to .env\npython setup_store.py\nstreamlit run app.py\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwei%2Fmlh-gemini-rag-workshop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwei%2Fmlh-gemini-rag-workshop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwei%2Fmlh-gemini-rag-workshop/lists"}