feat: 添加对Xinference模型的支持 #528
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
在.env.example中添加了XINFERENCE_OPENAI_ENDPOINT和XINFERENCE_MODEL环境变量，并在src/utils/utils.py中实现了对Xinference模型的支持。新增的模型名称列表包括qwen2.5和deepseek系列模型。
|
lao seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
![mrge-io[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
| @@ -30,6 +30,9 @@ UNBOUND_API_KEY= | |||
| SiliconFLOW_ENDPOINT=https://api.siliconflow.cn/v1/ | |||
| SiliconFLOW_API_KEY= | |||
|
|
|||
| XINFERENCE_OPENAI_ENDPOINT=https://api.xinference.com/v1 | |||
| XINFERENCE_MODEL= | |||
There was a problem hiding this comment.
Missing documentation for expected values for XINFERENCE_MODEL environment variable
| @@ -183,6 +183,18 @@ def get_llm_model(provider: str, **kwargs): | |||
| model_name=kwargs.get("model_name", "Qwen/QwQ-32B"), | |||
| temperature=kwargs.get("temperature", 0.0), | |||
| ) | |||
| elif provider == "xinference": | |||
There was a problem hiding this comment.
Missing entry for "xinference" in PROVIDER_DISPLAY_NAMES dictionary
src/utils/utils.py
Outdated
| base_url = kwargs.get("base_url") | ||
|
|
||
| return ChatOpenAI( | ||
| model=kwargs.get("model_name", "gpt-4o"), |
There was a problem hiding this comment.
Default model for Xinference provider is set to "gpt-4o" which is not in the xinference model list
| @@ -183,6 +183,18 @@ def get_llm_model(provider: str, **kwargs): | |||
| model_name=kwargs.get("model_name", "Qwen/QwQ-32B"), | |||
| temperature=kwargs.get("temperature", 0.0), | |||
| ) | |||
| elif provider == "xinference": | |||
| if not kwargs.get("base_url", ""): | |||
There was a problem hiding this comment.
API key retrieval uses a different environment variable pattern than what's defined in .env.example
在utils.py中添加对XInference的支持，并在.env.example中添加XINFERENCE_API_KEY环境变量。这些更改使得系统能够更好地集成XInference服务。
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary by mrge
Added support for Xinference models including Qwen2.5 and Deepseek series. This integration enables users to leverage these models through a standardized interface with configurable endpoints.
New Features
Refactors
在.env.example中添加了XINFERENCE_OPENAI_ENDPOINT和XINFERENCE_MODEL环境变量，并在src/utils/utils.py中实现了对Xinference模型的支持。新增的模型名称列表包括qwen2.5和deepseek系列模型。