dup

[wrightju]

Hi,
I'm attempting to get the qdrant MCP server (version 0.7.1) working with claude desktop and Open WebUI. My Collection is using BAAI/bge-base-en-v1.5 embedding model, which I believe should be supported. However, when setting EMBEDDING_MODEL=BAAI/bge-base-en-v1.5 and performing query or insert I get this error:

Error executing tool qdrant-find: Unexpected Response: 400 (Bad Request)
Raw response content:
b'{"status":{"error":"Wrong input: Vector with name fast-bge-base-en-v1.5 is not configured in this collection, available names: BAAI/bge-base-en-v1.5"},"time":0.000075365}'

I noticed that in the fastembed.py the model name is being changed.

def get_vector_name(self) -> str:
    """
    Return the name of the vector for the Qdrant collection.
    Important: This is compatible with the FastEmbed logic used before 0.6.0.
    """
    **model_name = self.embedding_model.model_name.split("/")[-1].lower()
    return f"fast-{model_name}"**

Attached: claude_desktop_config.json

Attached:

Any help getting this working, would be greatly appreciated.
-Justin