[Question]:Embeddings and LLM compatibility in server

[DavidGOrtega]

Do you need to ask a question?

• I have searched the existing question and discussions and this question is not already answered.
• I believe this is a legitimate question, not just a bug or feature request.

Your Question

Despite that the project is states that its compatible with other Embeddings and LLMs I can not make it work in server.
I have tried LLMs and embeddings that I regularly use with the openAI library.

EMBEDDING_BINDING=openai
EMBEDDING_MODEL=voyage-3-large
EMBEDDING_DIM=1024
EMBEDDING_BINDING_HOST=https://api.voyageai.com/v1/embeddings
EMBEDDING_BINDING_API_KEY=XXXX

LLM_BINDING=openai
LLM_MODEL=gemini-2.5-flash
LLM_BINDING_HOST=https://generativelanguage.googleapis.com/v1beta/openai/
LLM_BINDING_API_KEY=XXXX

I cant not make them work. I will look into the code but embeddings give me a 404 (it works via Curl)

Additional Context

No response

[danielaskdd]

endpoint URL of Embedding service is incorrect. It should be:

EMBEDDING_BINDING_HOST=https://api.voyageai.com/v1