{"id":23462534,"url":"https://github.com/harimkang/docsense","last_synced_at":"2025-07-06T21:11:13.448Z","repository":{"id":268533145,"uuid":"904649985","full_name":"harimkang/docsense","owner":"harimkang","description":"An intelligent document assistant powered by Open-Source Large Language Models","archived":false,"fork":false,"pushed_at":"2024-12-17T12:16:55.000Z","size":40,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-12T08:58:03.592Z","etag":null,"topics":["document-qa","llm","nlp","qwen","qwen2"],"latest_commit_sha":null,"homepage":"https://harimkang.github.io/docsense/","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/harimkang.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,"zenodo":null}},"created_at":"2024-12-17T09:49:25.000Z","updated_at":"2024-12-17T12:24:50.000Z","dependencies_parsed_at":"2025-04-14T11:32:06.141Z","dependency_job_id":null,"html_url":"https://github.com/harimkang/docsense","commit_stats":null,"previous_names":["harimkang/docsense"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/harimkang/docsense","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harimkang%2Fdocsense","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harimkang%2Fdocsense/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harimkang%2Fdocsense/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harimkang%2Fdocsense/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harimkang","download_url":"https://codeload.github.com/harimkang/docsense/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harimkang%2Fdocsense/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263973362,"owners_count":23537977,"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":["document-qa","llm","nlp","qwen","qwen2"],"created_at":"2024-12-24T08:17:36.291Z","updated_at":"2025-07-06T21:11:13.433Z","avatar_url":"https://github.com/harimkang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DocSense 📚\n\n[![PyPI version](https://badge.fury.io/py/docsense.svg)](https://badge.fury.io/py/docsense)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python Versions](https://img.shields.io/pypi/pyversions/docsense.svg)](https://pypi.org/project/docsense/)\n[![Tests](https://github.com/harimkang/docsense/actions/workflows/test.yml/badge.svg)](https://github.com/harimkang/docsense/actions/workflows/test.yml)\n[![codecov](https://codecov.io/gh/harimkang/docsense/branch/main/graph/badge.svg)](https://codecov.io/gh/harimkang/docsense)\n\nAn intelligent document assistant powered by Open-Source Large Language Models 🤖\n\nDocSense is a powerful tool that helps you interact with your documents using natural language. It leverages the open-source Qwen language model (with plans to support more open-source models) to understand and answer questions about your documents with high accuracy and context awareness, all completely free to use.\n\n## Features ✨\n\n- 🔍 Advanced semantic search using FAISS\n- 💡 Intelligent question answering with open-source LLMs (currently Qwen)\n- 📝 Support for multiple document formats (txt, md, rst, etc.)\n- ⚡ GPU acceleration for faster processing\n- 🔄 Batch processing for memory efficiency\n- 💾 Persistent vector storage\n\n## Installation 🛠️\n\n### CPU Version\n\n```bash\npip install docsense\n```\n\n### GPU Version (Recommended)\n\nFirst, install PyTorch with CUDA support:\n\n```bash\nconda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia\n```\n\nThen install FAISS with GPU support:\n\n```bash\nconda install -c conda-forge faiss-gpu\n```\n\nFinally, install DocSense:\n\n```bash\npip install docsense\n```\n\n## Usage 🚀\n\n### Creating Document Index\n\nIndex your documents directory:\n\n```bash\ndocsense index /path/to/your/documents\n```\n\n### Asking Questions\n\nAsk a question to your documents:\n\n```bash\ndocsense ask \"How to use this library?\"\n```\n\n### Interactive Mode\n\nStart an interactive session for multiple questions:\n\n```bash\ndocsense daemon\n```\n\n### Command Line Options\n\nAll commands support the following options:\n\n- `--model-name`: Specify the Qwen model to use (default: \"Qwen/Qwen2-7B\")\n- `--device`: Choose computing device (\"cuda\" or \"cpu\", default: \"cuda\")\n- `--index-path`: Set custom path for the vector index\n\nExample with options:\n\n```bash\ndocsense index /path/to/your/documents --model-name \"Qwen/Qwen2-7B\" --device \"cuda\" --index-path /path/to/your/index\n```\n\n## License 📄\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Star History 🌟\n\n[![Star History Chart](https://api.star-history.com/svg?repos=harimkang/docsense\u0026type=Date)](https://star-history.com/#harimkang/docsense\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharimkang%2Fdocsense","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharimkang%2Fdocsense","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharimkang%2Fdocsense/lists"}