{"id":38756559,"url":"https://github.com/muktadiur/clark","last_synced_at":"2026-01-17T11:53:58.881Z","repository":{"id":179537567,"uuid":"660349258","full_name":"muktadiur/clark","owner":"muktadiur","description":"Chat with private documents(CSV, pdf, docx, doc, txt) using LangChain, OpenAI, HuggingFace, and FastAPI.","archived":false,"fork":false,"pushed_at":"2024-01-05T23:10:58.000Z","size":343,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-01-06T00:49:13.030Z","etag":null,"topics":["fastapi","huggingface","javascript","langchain","openai","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/muktadiur.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}},"created_at":"2023-06-29T20:08:00.000Z","updated_at":"2024-01-06T00:49:15.860Z","dependencies_parsed_at":"2023-12-21T06:27:55.833Z","dependency_job_id":"8a84e03b-f341-4429-b985-d499e32f08e5","html_url":"https://github.com/muktadiur/clark","commit_stats":null,"previous_names":["muktadiur/clark"],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/muktadiur/clark","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muktadiur%2Fclark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muktadiur%2Fclark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muktadiur%2Fclark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muktadiur%2Fclark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/muktadiur","download_url":"https://codeload.github.com/muktadiur/clark/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muktadiur%2Fclark/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28508462,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T11:50:55.898Z","status":"ssl_error","status_checked_at":"2026-01-17T11:50:55.569Z","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":["fastapi","huggingface","javascript","langchain","openai","python"],"created_at":"2026-01-17T11:53:58.759Z","updated_at":"2026-01-17T11:53:58.861Z","avatar_url":"https://github.com/muktadiur.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Clark\nChat with private documents(CSV, pdf, docx, doc, txt) using LangChain, OpenAI, HuggingFace, GPT4ALL, and FastAPI.\n\n![Clark](static/images/clark.png)\n\n## Installation\n\nInstall required packages.\n```\npython -m venv .venv\nsource .venv/bin/activate\n\npip install -r requirements.txt\n```\n\nRename `.env.example` to `.env` and update the OPENAI_API_KEY [OpenAI API key](https://platform.openai.com/account/api-keys), HUGGINGFACEHUB_API_TOKEN [HuggingFace Access Tokens] (https://huggingface.co/settings/tokens).\n\n\nPlace your own data (CSV, pdf, docx, doc, txt) into `data/` folder.\n\n## Run\n\n### Console\n```\npython console.py # default: openai\n\n```\n\n```\nWelcome to the Clark!\n(type 'exit' to quit)\nYou: what is the capital of Uzbekistan?\nClark: The capital of Uzbekistan is Tashkent.\nYou: exit\n```\n\n### Web\n```\npython app.py  # default: openai\n\nURL:\nhttp://127.0.0.1:8000/\nhttp://127.0.0.1:8000/docs\nhttp://127.0.0.1:8000/redoc\n```\n\n### Run in docker\n```\ndocker build -t clark .\ndocker run -p 8000:8000 -it clark\n```\n\n### To use HuggingFace\n```\nChange the CONVERSATION_ENGINE: from `openai`: to `hf` in the `.env` file.\n```\n\n### To use GPT4ALL (Slow)\n```\nmkdir models\ncd models\nwget https://huggingface.co/nomic-ai/gpt4all-falcon-ggml/resolve/main/ggml-model-gpt4all-falcon-q4_0.bin\n\nChange the CONVERSATION_ENGINE: from `openai`: to `gpt4all` in the `.env` file.\nNow read your documents locally using an LLM.\n\nNote: gpt4all performance is slow for now. The average response time is 50 seconds.\n\n```\n\n\n## Project structure\n```\n.\n├── Dockerfile\n├── LICENSE\n├── README.md\n├── app.py\n├── clark\n│   ├── __init__.py\n│   ├── base.py\n│   ├── document.py\n│   ├── gpt4all.py\n│   ├── helpers.py\n│   ├── hf.py\n│   └── openai.py\n├── console.py\n├── data\n│   └── sample_capitals.csv\n├── requirements.txt\n├── static\n│   ├── auth\n│   │   ├── login.html\n│   │   └── signup.html\n│   ├── base.html\n│   ├── css\n│   │   ├── font-awesome.min.css\n│   │   └── main.css\n│   ├── home.html\n│   ├── images\n│   │   ├── clark.png\n│   │   └── favicon.ico\n│   ├── index.html\n│   ├── index.js\n│   ├── js\n│   └── spinner.gif\n└── test_api.py\n\n8 directories, 26 files\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuktadiur%2Fclark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmuktadiur%2Fclark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuktadiur%2Fclark/lists"}