{"id":13941978,"url":"https://github.com/leoneversberg/llm-chatbot-rag","last_synced_at":"2026-01-17T10:40:34.878Z","repository":{"id":228977118,"uuid":"775440012","full_name":"leoneversberg/llm-chatbot-rag","owner":"leoneversberg","description":" A local LLM chatbot with RAG for PDF input files","archived":false,"fork":false,"pushed_at":"2024-04-17T08:16:15.000Z","size":109,"stargazers_count":81,"open_issues_count":0,"forks_count":29,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-20T05:52:12.783Z","etag":null,"topics":["chatbot","llm","nlp","rag"],"latest_commit_sha":null,"homepage":"https://medium.com/towards-data-science/how-to-build-a-local-open-source-llm-chatbot-with-rag-f01f73e2a131","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/leoneversberg.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":"2024-03-21T11:51:30.000Z","updated_at":"2025-07-19T12:33:32.000Z","dependencies_parsed_at":"2024-11-27T11:42:13.419Z","dependency_job_id":null,"html_url":"https://github.com/leoneversberg/llm-chatbot-rag","commit_stats":null,"previous_names":["leoneversberg/llm-chatbot-rag"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/leoneversberg/llm-chatbot-rag","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoneversberg%2Fllm-chatbot-rag","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoneversberg%2Fllm-chatbot-rag/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoneversberg%2Fllm-chatbot-rag/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoneversberg%2Fllm-chatbot-rag/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/leoneversberg","download_url":"https://codeload.github.com/leoneversberg/llm-chatbot-rag/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoneversberg%2Fllm-chatbot-rag/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28506593,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T10:25:30.148Z","status":"ssl_error","status_checked_at":"2026-01-17T10:25:29.718Z","response_time":85,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["chatbot","llm","nlp","rag"],"created_at":"2024-08-08T02:01:38.420Z","updated_at":"2026-01-17T10:40:29.855Z","avatar_url":"https://github.com/leoneversberg.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# llm-chatbot-rag\n\n![Screenshot](/images/example.jpg)\n\nTo use certain LLM models (such as Gemma), you need to create a .env file containing the line `ACCESS_TOKEN=\u003cyour hugging face token\u003e`\n\nInstall dependencies with `pip install -r requirements.txt`\n\nRun with `streamlit run src/app.py`\n\n### Using quantization requires a GPU\nTo use bitsandbytes quantization, a Nvidia GPU is required.\nMake sure to install the NVIDIA Toolkit first and then PyTorch. \n\nYou can check if your GPU is available in Python with\n```\nimport torch\nprint(torch.cuda.is_available())\n```\n\nIf you do not have a compatible GPU, try setting `device=\"cpu\"` for the model and remove the quantization config.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleoneversberg%2Fllm-chatbot-rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fleoneversberg%2Fllm-chatbot-rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleoneversberg%2Fllm-chatbot-rag/lists"}