LLamaIndex Team is excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts than virtually every other parser, it is now steerable through natural language instructions – output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations
We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features:
- SOTA table/chart extraction,
- Seamless integration with,
- @llama_index advanced RAG/agents,
- Natural language Parsing Instructions,
- JSON mode and image extraction.
LlamaParse Image Extraction Feature
A standout feature in JSON mode is its capability to extract images from pages. This includes providing a list of images complete with metadata detailing their size and location on the page. This allows for the direct retrieval of images, enhancing the ability to glean more insights from documents rich in imagery.
Expanded Support for Document Types
Originally introduced with robust support for PDF documents, LlamaParse has progressively enhanced its capabilities. We now offer extensive support for a wide variety of document formats, including:
- Microsoft Word (.doc, .docx)
- Microsoft PowerPoint (.pptx)
- Rich Text Format (.rtf)
- Apple Pages (.pages)
- Apple Keynote (.key)
- ePub books (.epub)
- Plus many others!
These document types are seamlessly supported with no extra effort required from users. Our support for document formats is continually growing. For an illustration of our capabilities, consider our demo notebook, where we showcase the parsing of a PowerPoint file.
LlamaParse Pricing
Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud.
- LlamaParse client repo: https://github.com/run-llama/llama_parse
- Signup at: https://cloud.llamaindex.ai
- Come talk to us: https://llamaindex.ai/contact
Read other related articles: