Litellm open ai compatible protocol
—> feat: A new feature optimize: A new optimization fix: A bug fix perf: A code change that improves performance -->
Check the PR title.
- [ ] This PR title match the format: <type>(optional scope): <description>
- [ ] The description of this PR title is user-oriented and clear enough for others to understand.
- [ ] Attach the PR updating the user documentation if the current PR requires user awareness at the usage level. [User docs repo](https://github.com/
(Optional) More detailed description for this PR(en: English/zh: Chinese).
en: zh(optional):
(Optional) Which issue(s) this PR fixes:
Add LitellmModel for OpenAI-compatible API integration.
Define LitellmModel struct with a client field for OpenAI-compatible APIs. Implement NewLitellmModel function to create a new instance of LitellmModel. Add GenerateText method to generate text based on a given prompt using the OpenAI-compatible API. Include a comment explaining Litellm's compatibility with the OpenAI API protocol.
Hi, thanks for contribution.
- This repository is used to store component abstractions, orchestration capabilities, Agent paradigms, and other implementation-independent code. Component implementations can be submitted in the eino-ext.
- Components in eino-ext must implement interface defined in eino/component, for example, https://github.com/cloudwego/eino/blob/df93610a63a7d30d9cccddffe313d4ee967dccbf/components/model/interface.go#L29
- Why do you need this pr? I noticed that this protocol is exactly the same as OpenAI's, so maybe you can directly use the OpenAI package?
Do you have any code specific improvements should I be calling https://github.com/openai/openai-go from instead? Should this be implemented on eino-ext in this package eino-ext/libs/acl as a litellm folder with open ai protocol
It seems that this PR simply wraps the OpenAI protocol, which has already been done in https://github.com/cloudwego/eino-ext/tree/main/components/model/openai.