feat: support Ernie-lite-pro-128k

[bigfish49]

Summary

support Ernie-lite-pro-128k

Resolves #12130

Screenshots

Before	After
...

Checklist

Important

Please review the checklist below before submitting your pull request.

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[HugoLian]

So how could I update this? I don't find this change at https://github.com/langgenius/dify/tree/main/api/core/model_runtime/model_providers/wenxin/llm
I am using a docker version.

[bigfish49]

So how could I update this? I don't find this change at https://github.com/langgenius/dify/tree/main/api/core/model_runtime/model_providers/wenxin/llm I am using a docker version.

just waiting for it to be merged~

[HugoLian]

So how could I update this? I don't find this change at https://github.com/langgenius/dify/tree/main/api/core/model_runtime/model_providers/wenxin/llm I am using a docker version.

just waiting for it to be merged~

Thanks, I found your branch.
Because I am using the docker version.
So do I need to change the version here?

Or when it is merged, the docker version will be update?

[HugoLian]

max: 2048

So how could I update this? I don't find this change at https://github.com/langgenius/dify/tree/main/api/core/model_runtime/model_providers/wenxin/llm I am using a docker version.

just waiting for it to be merged~

I think max_output_tokens should be 8192 not 2048.

[bigfish49]

max: 2048

So how could I update this? I don't find this change at https://github.com/langgenius/dify/tree/main/api/core/model_runtime/model_providers/wenxin/llm I am using a docker version.

just waiting for it to be merged~

I think max_output_tokens should be 8192 not 2048.

According to the official doc, max_output_tokens is 2048.

[HugoLian]

Thanks for your information.
But I confirmed with the model provider, they changed the webpage:
https://cloud.baidu.com/doc/WENXINWORKSHOP/s/9m0oofifc

max output tokens from 2048 to 4096