search

nlmatics / nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.
https://www.nlmatics.com
Apache License 2.0
972 stars 124 forks source link

Query: How would it integrate with other LLM apis. #1

Open sandeep2244 opened 6 months ago

sandeep2244 commented 6 months ago

Hello,

I am looking for PDF parser/extractor to read data for ready for LLM to give me values form it. Is it possible to do with this project ?

PDF -> nlm-ingestor -> PDF extracted o/p -> LLM

Thanks.

ansukla commented 6 months ago

You can integrate with LLM by using the llmsherpa library --> https://github.com/nlmatics/llmsherpa

Run nlm-service as the server and then connect to it using llmsherpa LayoutPDFReader interface and you will get convenient chunks to use for LLM. Here's another example: https://github.com/nlmatics/nlm-ingestor/blob/main/notebooks/test_llmsherpa_api.ipynb