{"id":24401582,"url":"https://github.com/lh0x00/docsifer","last_synced_at":"2025-04-23T00:42:39.941Z","repository":{"id":272463013,"uuid":"916520956","full_name":"lh0x00/docsifer","owner":"lh0x00","description":"Docsifer is a powerful tool for converting various data formats into Markdown for applications such as indexing, text analysis, and more. It supports PDF, PowerPoint, Word, Excel, Images, Audio, HTML, and other text-based formats, and leverages LLMs to enhance performance.","archived":false,"fork":false,"pushed_at":"2025-03-03T03:02:09.000Z","size":154,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-23T00:42:31.218Z","etag":null,"topics":["analysis","autogen","chunking","docsier","documents","emeddings","indexing","langchain","llama-index","markdown","markitdown","rag","text-embeddings","text-processing","vector-database"],"latest_commit_sha":null,"homepage":"https://lamhieu-docsifer.hf.space","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/lh0x00.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":"2025-01-14T09:01:57.000Z","updated_at":"2025-03-03T03:02:13.000Z","dependencies_parsed_at":"2025-01-14T16:36:09.644Z","dependency_job_id":"e8855d2d-ebc6-44e1-a1f7-352b75cab1a9","html_url":"https://github.com/lh0x00/docsifer","commit_stats":null,"previous_names":["lh0x00/docsifer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lh0x00%2Fdocsifer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lh0x00%2Fdocsifer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lh0x00%2Fdocsifer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lh0x00%2Fdocsifer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lh0x00","download_url":"https://codeload.github.com/lh0x00/docsifer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250348891,"owners_count":21415907,"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":["analysis","autogen","chunking","docsier","documents","emeddings","indexing","langchain","llama-index","markdown","markitdown","rag","text-embeddings","text-processing","vector-database"],"created_at":"2025-01-20T00:32:15.974Z","updated_at":"2025-04-23T00:42:39.923Z","avatar_url":"https://github.com/lh0x00.png","language":"Python","readme":"---\ntitle: Docsifer\nemoji: 👻 / 📚\ncolorFrom: green\ncolorTo: indigo\nsdk: docker\napp_file: app.py\npinned: false\n---\n\n# 📄 Docsifer: Efficient Data Conversion to Markdown\n\n**Docsifer** is a powerful FastAPI + Gradio service for converting various data formats (PDF, PowerPoint, Word, Excel, Images, Audio, HTML, etc.) to Markdown. It leverages the [MarkItDown](https://github.com/microsoft/markitdown) library and can optionally use LLMs (via OpenAI) for richer extraction (OCR, speech-to-text, etc.).\n\n## ✨ Key Features\n\n- **Comprehensive Format Support**: \n  - **PDF**: Extracts text and structure effectively.\n  - **PowerPoint**: Converts slides into Markdown-friendly content.\n  - **Word**: Processes `.docx` files with precision.\n  - **Excel**: Extracts tabular data as Markdown tables.\n  - **Images**: Reads **EXIF metadata** and applies **OCR** for text extraction.\n  - **Audio**: Retrieves **EXIF metadata** and performs **speech transcription**.\n  - **HTML**: Transforms web pages into Markdown.\n  - **Text-Based Formats**: Handles CSV, JSON, XML with ease.\n  - **ZIP Files**: Iterates over contents for batch processing.\n- **LLM Integration**: Leverages OpenAI's GPT-4 for enhanced extraction quality and contextual understanding.\n- **Efficient and Fast**: Optimized for speed while maintaining high accuracy.\n- **Easy Deployment**: Dockerized for hassle-free setup and scalability.\n- **Interactive Playground**: Test conversion processes interactively using a **Gradio-powered interface**.\n- **Usage Analytics**: Tracks token usage and access statistics via Upstash Redis.\n\n## 🚀 Use Cases\n\n- **Knowledge Indexing**: Convert various document formats into Markdown for indexing and search.\n- **Text Analysis**: Prepare data for semantic analysis and NLP tasks.\n- **Content Transformation**: Simplify content preparation for blogs, documentation, or databases.\n- **Metadata Extraction**: Extract meaningful metadata from images and audio for categorization and tagging.\n\n## 🛠️ Getting Started\n\n### 1. Clone the Repository\n\n```bash\ngit clone https://github.com/lh0x00/docsifer.git\ncd docsifer\n```\n\n### 2. Build and Run with Docker\nMake sure Docker is installed and running on your machine.\n```bash\ndocker build -t lightweight-embeddings .\ndocker run -p 7860:7860 lightweight-embeddings\n```\n\nThe API will now be accessible at `http://localhost:7860`.\n\n## 📖 API Overview\n\n### Endpoints\n\n- **`/v1/convert`**: Convert a file to Markdown. Supports both file uploads and file path inputs. Accepts optional OpenAI parameters to enable LLM-based enhancements.\n- **`/v1/stats`**: Retrieve usage statistics, including access counts and token usage.\n\n### Interactive Docs\n\n- Visit the [Swagger UI](http://localhost:7860/docs) for detailed, interactive documentation.\n- Explore additional resources with [ReDoc](http://localhost:7860/redoc).\n\n## 🔬 Playground\n\n### Interactive Conversion\n\n- Test file conversion directly in the browser using the **Gradio interface**.\n- Simply visit `http://localhost:7860` after starting the server to access the playground.\n\n### Features\n\n- **File Upload**: Upload a file directly or provide a local file path.\n- **OpenAI Integration**: Optionally provide OpenAI API details to enhance conversion with LLM capabilities.\n- **Conversion Result**: View the resulting Markdown output instantly.\n- **Usage Statistics**: Monitor access and token usage through the Gradio interface.\n\n## 🌐 Resources\n\n- **Documentation**: [Explore full documentation](https://lamhieu-docsifer.hf.space/docs)\n- **Hugging Face Space**: [Try the live demo](https://huggingface.co/spaces/lh0x00/docsifer)\n- **GitHub Repository**: [View source code](https://github.com/lh0x00/docsifer)\n\n## 💡 Why Docsifer?\n\n1. **Versatile and Comprehensive**: Handles a wide range of formats, making it a one-stop solution for content conversion.\n2. **AI-Powered**: Uses OpenAI's GPT-4 to enhance extraction accuracy and adapt to complex data structures.\n3. **User-Friendly**: Offers intuitive APIs and a built-in interactive interface for experimentation.\n4. **Scalable and Efficient**: Optimized for performance with Docker support and asynchronous processing.\n5. **Transparent Analytics**: Tracks usage metrics to help monitor and manage service consumption.\n\n## 👥 Contributors\n\n- **lamhieu / lh0x00** – Creator and Maintainer ([GitHub](https://github.com/lh0x00), [HuggingFace](https://huggingface.co/lamhieu))\n\nContributions are welcome! Check out the [contribution guidelines](https://github.com/lh0x00/docsifer/blob/main/CONTRIBUTING.md).\n\n## 📜 License\n\nThis project is licensed under the **MIT License**. See the [LICENSE](https://github.com/lh0x00/docsifer/blob/main/LICENSE) file for details.\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flh0x00%2Fdocsifer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flh0x00%2Fdocsifer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flh0x00%2Fdocsifer/lists"}