Different Embedding Models

[gvlx]

Your code example seems to imply that.

[Filimoa]

Currrently yes - we're shipping support for open source embeddings very soon!

[tan-yong-sheng]

Hi @Filimoa,

I have commented here: https://github.com/Filimoa/open-parse/issues/10#issuecomment-2214343987, but after that, I found here could be a better place to put this comment:

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):

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:

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

There are also quite a few projects that used litellm: https://litellm.vercel.app/docs/project to call models from different providers on LiteLLM.