[Question]: When calling the Create Knowledge Base API and selecting the vllm-deployed bge-m3 embedding model, I received {'code': 102, 'message': "embedding_model bge-m3@Xinference doesn't exist"}

[Jonsun-N]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Describe your problem

When calling the Create Knowledge Base API and selecting the vllm-deployed bge-m3 embedding model, I received {'code': 102, 'message': "embedding_model bge-m3 doesn't exist"}
code:
create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_id": "bge-m3",
}
create_response = requests.post(
datasets_url,
headers={
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}",
},
json=create_data,
)
When replacing "bge-m3" with "BAAI/bge-large-zh-v1.5@BAAI", it can be successfully operational.
When creating a knowledge base by selecting "bge-m3" in the web version succeeds, how should I adjust the code?

[KevinHuSh]

Give it a try:

create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_id": "bge-m3@VLLM",
}

Or,

create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_id": "bge-m3___VLLM",
}

[Jonsun-N]

Give it a try:

create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_id": "bge-m3@VLLM",
}

Or,

create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_id": "bge-m3___VLLM",
}

create_data = {
"name": DATASET_NAME,
"chunk_method": "naive",
"embedding_model": "bge-m3___VLLM",
}
is ok. Thanks