{"id":21643499,"url":"https://github.com/aigptcode/askyourdocuments","last_synced_at":"2025-04-11T18:20:40.121Z","repository":{"id":228419642,"uuid":"773947437","full_name":"AiGptCode/AskyourDocuments","owner":"AiGptCode","description":"Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!","archived":false,"fork":false,"pushed_at":"2024-03-24T21:26:40.000Z","size":25,"stargazers_count":7,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-03-24T22:28:59.941Z","etag":null,"topics":["ai","api","assistant","chatbot","gpt-4","hugging-face","huggingface","huggingface-transformers","microsoft","openai","openai-api","pdf","pdf-generation","windows","word"],"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/AiGptCode.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}},"created_at":"2024-03-18T17:15:12.000Z","updated_at":"2024-04-14T19:30:26.725Z","dependencies_parsed_at":"2024-03-24T22:28:18.395Z","dependency_job_id":null,"html_url":"https://github.com/AiGptCode/AskyourDocuments","commit_stats":null,"previous_names":["aigptcode/askyourdocuments"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AiGptCode%2FAskyourDocuments","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AiGptCode%2FAskyourDocuments/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AiGptCode%2FAskyourDocuments/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AiGptCode%2FAskyourDocuments/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AiGptCode","download_url":"https://codeload.github.com/AiGptCode/AskyourDocuments/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248456384,"owners_count":21106606,"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":["ai","api","assistant","chatbot","gpt-4","hugging-face","huggingface","huggingface-transformers","microsoft","openai","openai-api","pdf","pdf-generation","windows","word"],"created_at":"2024-11-25T05:34:40.986Z","updated_at":"2025-04-11T18:20:40.088Z","avatar_url":"https://github.com/AiGptCode.png","language":"Python","readme":"# 💻 Ask your Documents  🤖\n \n👋 Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!\n\n\u003ca href=\"https://ibb.co/2WfRtKN\"\u003e\u003cimg src=\"https://i.ibb.co/0md1MJt/IMG-1413.jpg\" alt=\"IMG-1413\" border=\"0\"\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca target='_blank' href='https://it.imgbb.com/'\u003e\n \n## 🚀 Features\n \n* 💻 Supports a variety of document formats, including PDF, Word, Excel, PowerPoint, text files, and images\n* 🤖 Uses the Hugging Face Transformers library to create embeddings for document chunks\n* 🔍 Uses the FAISS library to create an index for those embeddings, allowing for efficient similarity search\n* 💬 Allows users to ask questions about their documents and get answers based on the contents of those documents\n* ⚡️ Uses multiprocessing to parallelize the creation of the index for improved performance\n\n## 📋 Requirements\n\n* Python 3.6 or higher\n* The following Python packages:\n\t+ transformers\n\t+ langchain\n\t+ fitz\n\t+ Pillow\n\t+ textract\n\t+ pandas\n\t+ python-pptx\n\t+ concurrent-futures\n\t+ opencv-python (for image support)\n\n## 🔧 Usage\n\n1. Clone this repository to your local machine:\n```bash\ngit clone https://github.com/AiGptCode/AskyourDocuments.git\n```\n2. Install the required Python packages:\n```bash\npip install transformers langchain fitz pillow textract pandas python-pptx opencv-python concurrent-futures\n```\n3. Set your Hugging Face API key as an environment variable:\n```bash\nexport HUGGINGFACE_API_TOKEN=your-api-key\n```\n4. Run the `main.py` script and enter the path to the directory containing your documents:\n```bash\npython AskyourDocuments.py\n```\n5. Ask a question about your documents and get an answer based on the contents of those documents.\n\nNote: If you want to include images in your search, make sure they are in a supported format (e.g., JPEG, PNG) and are located in the same directory as your other documents.\n\n## 🤝 Contributing\n\nIf you would like to contribute to this project, please follow these steps:\n\n1. Fork this repository to your own GitHub account.\n2. Create a new branch for your changes:\n```bash\ngit checkout -b my-feature-branch\n```\n3. Make your changes and commit them:\n```bash\ngit commit -am 'Add some feature'\n```\n4. Push your changes to your fork:\n```bash\ngit push origin my-feature-branch\n```\n5. Open a pull request against the original repository.\n\n## 📄 License\n\nThis project is licensed under the MIT License.\n\n## 🎉 Acknowledgments\n\n* The Hugging Face Transformers library for providing pre-trained models and tokenizers\n* The FAISS library for providing efficient similarity search and clustering of dense vectors\n* The `langchain` library for providing utilities for creating and working with language models\n* The `fitz` library for providing utilities for working with PDF files\n* The `Pillow` library for providing utilities for working with image files\n* The `textract` library for providing utilities for extracting text from various file formats\n* The `pandas` library for providing utilities for working with tabular data in Python\n* The `python-pptx` library for providing utilities for working with PowerPoint files\n* The `concurrent-futures` library for providing a high-level interface for asynchronously executing callables\n* The `opencv-python` library for providing utilities for working with image and video data (for image support)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faigptcode%2Faskyourdocuments","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faigptcode%2Faskyourdocuments","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faigptcode%2Faskyourdocuments/lists"}