Show HN: LlamaExtract, a tool to automatically extract schema from documents

Show HN: LlamaExtract, a tool to automatically extract schema from documents(github.com)

8 points by pierre 1 year ago | 4 comments

We build LlamaExtract, a tool that allow you to automatically extract a data model from a collection of documents, and then reusing this datamodels (JSON Schema) to extract data from documents.

Available as a Python library and as an API.

Announcement blog: https://www.llamaindex.ai/blog/introducing-llamaextract-beta...

verdverm 1 year ago |

When you say "available as a python library", do you mean the LlamaCloud API wrapped in a Python package? This doesn't seem to be something that we can use without a LlamaCloud account. When I hear that, I think more that this is something I could run locally.

Is there any documentation or a paper on the methods?

Is this intended to be a proprietary service?

cheesyFishes 1 year ago |

Pretty neat initial launch. What's top of mind to add to it?

BinaryBrain 1 year ago |

Does it handles multiple input documents for extraction?

pierre 1 year ago | |

yes, you can pass an array of path to the extract function.