[Question]: How to add Volcengine embedding model?

[zsp0901]

Describe your problem

No matter I used Volcengine or other ways, e.g. OpenAI compatible, OpenRouter, it just got KeyError or other errors.

I tested both "Daobao-embedding" and "ep-xxxx" endpoint ID, it just failed.

base url: https://ark.cn-beijing.volces.com/api/v3

But I can add Volcengine chat model using OpenRouter.

Anyone help? Many thanks!!!

[Queensbarry]

I meet the same question. I use ep-xxx-xxx to add chat LLM is successful, but failed when adding embedding model.

[eriklee1895]

I have the same problem: when add Volcengine embedding model, pop error: KeyError('VolcEngine') but the chat model was added successful

[leoxu2024]

File "/ragflow/api/apps/llm_app.py", line 209, in add_llm mdl = EmbeddingModel[factory]( ~~~~~~~~~~~~~~^^^^^^^^^ KeyError: 'VolcEngine' 'VolcEngine' Traceback (most recent call last): File "/ragflow/.venv/lib/python3.12/site-packages/flask/app.py", line 880, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/ragflow/.venv/lib/python3.12/site-packages/flask/app.py", line 865, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/ragflow/.venv/lib/python3.12/site-packages/flask_login/utils.py", line 290, in decorated_view return current_app.ensure_sync(func)(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/ragflow/api/utils/api_utils.py", line 175, in decorated_function return func(_args, **_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^ File "/ragflow/api/apps/llm_app.py", line 209, in add_llm mdl = EmbeddingModel[factory](

添加豆包在线推理模型报错了

[which-W]

@zsp0901 Thanks so much for the suggestion — and sorry for the delay getting back to you! ⏱️

Good news! We've added support for Volcengine configuration 🎉 You can now complete the setup directly via the LLM configuration page 🛠️

If this resolves your issue, feel free to close the feather when it's convenient. Otherwise, we’ll help clean it up during routine maintenance.

Thanks again for being part of the community and helping improve the project! 🚀