search

Filimoa / open-parse

Improved file parsing for LLM’s
https://filimoa.github.io/open-parse/
MIT License
2.44k stars 95 forks source link

support for Litellm module and Azure , aws OCR modules #10

Closed saitej123 closed 6 months ago

saitej123 commented 6 months ago

please provide supprot for

support for Litellm module and Azure , aws OCR modules

Filimoa commented 6 months ago

Thanks for taking the time to leave a comment, unfortunately integrating proprietary OCR modules is beyond the scope of this library. I don't think open-parse would add much values on top of those solutions anyways.

tan-yong-sheng commented 3 months ago

Hi @Filimoa,

I would like to suggest adding support for Litellm.

Litellm is an open source project, which unifies the API call of 100+ LLMs (including Anthropic, Cohere, and Ollama, etc) in an OpenAI compatible format: https://github.com/BerriAI/litellm

I believe integrating Litellm would be a fantastic enhancement because people could choose to switch or use their preferred embedding model api instead of OpenAI's ones only when dealing with semantic processing. Thanks.

For example, if they used litellm python client and without self hosting litellm proxy, then their code could be like this (which is very consistent with OpenAI python client format):

image

Reference: https://github.com/BerriAI/litellm

if someone self hosted litellm proxy, which they can call LLM API in an OpenAI compatible format via llmlite proxy, you could see the code could be as follows:

image

Reference: https://litellm.vercel.app/docs/providers/azure_ai#passing-additional-params---max_tokens-temperature