base on File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs. # MegaParse - Your Parser for every type of documents <div align="center"> <img src="https://raw.githubusercontent.com/QuivrHQ/MegaParse/main/logo.png" alt="Quivr-logo" width="30%" style="border-radius: 50%; padding-bottom: 20px"/> </div> MegaParse is a powerful and versatile parser that can handle various types of documents with ease. Whether you're dealing with text, PDFs, Powerpoint presentations, Word documents MegaParse has got you covered. Focus on having no information loss during parsing. ## Key Features 🎯 - **Versatile Parser**: MegaParse is a powerful and versatile parser that can handle various types of documents with ease. - **No Information Loss**: Focus on having no information loss during parsing. - **Fast and Efficient**: Designed with speed and efficiency at its core. - **Wide File Compatibility**: Supports Text, PDF, Powerpoint presentations, Excel, CSV, Word documents. - **Open Source**: Freedom is beautiful, and so is MegaParse. Open source and free to use. ## Support - Files: ✅ PDF ✅ Powerpoint ✅ Word - Content: ✅ Tables ✅ TOC ✅ Headers ✅ Footers ✅ Images ### Example https://github.com/QuivrHQ/MegaParse/assets/19614572/1b4cdb73-8dc2-44ef-b8b4-a7509bc8d4f3 ## Installation required python version >= 3.11 ```bash pip install megaparse ``` ## Usage 1. Add your OpenAI or Anthropic API key to the .env file 2. Install poppler on your computer (images and PDFs) 3. Install tesseract on your computer (images and PDFs) 4. If you have a mac, you also need to install libmagic ```brew install libmagic``` ```python from megaparse import MegaParse from langchain_openai import ChatOpenAI from megaparse.parser.unstructured_parser import UnstructuredParser parser = UnstructuredParser() megaparse = MegaParse(parser) response = megaparse.load("./test.pdf") print(response) megaparse.save("./test.md") ``` ### Use MegaParse Vision * Change the parser to MegaParseVision ```python from megaparse import MegaParse from langchain_openai import ChatOpenAI from megaparse.parser.megaparse_vision import MegaParseVision model = ChatOpenAI(model="gpt-4o", api_key=os.getenv("OPENAI_API_KEY")) # type: ignore parser = MegaParseVision(model=model) megaparse = MegaParse(parser) response = megaparse.load("./test.pdf") print(response) megaparse.save("./test.md") ``` **Note**: The model supported by MegaParse Vision are the multimodal ones such as claude 3.5, claude 4, gpt-4o and gpt-4. ## Use as an API There is a MakeFile for you, simply use : ```make dev``` at the root of the project and you are good to go. See localhost:8000/docs for more info on the different endpoints ! ## BenchMark <!---BENCHMARK--> | Parser | similarity_ratio | | ----------------------------- | ---------------- | | megaparse_vision | 0.87 | | unstructured_with_check_table | 0.77 | | unstructured | 0.59 | | llama_parser | 0.33 | <!---END_BENCHMARK--> _Higher the better_ Note: Want to evaluate and compare your Megaparse module with ours ? Please add your config in ```evaluations/script.py``` and then run ```python evaluations/script.py```. If it is better, do a PR, I mean, let's go higher together . ## In Construction 🚧 - Improve table checker - Create Checkers to add **modular postprocessing** ⚙️ - Add Structured output, **let's get computer talking** 🤖 ## Star History [](https://star-history.com/#QuivrHQ/MegaParse&Date) ", Assign "at most 3 tags" to the expected json: {"id":"12392","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"