spring-projects / spring-projects/spring-ai

Does the current version 1.1.0 of Springai not support Qwen3-VL-Embedding embedding models

Open
#5,402 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 7h
Merged PRs (30d)
6

Description

This is my configuration:
@Bean
public OpenAiEmbeddingModel embeddingModel() {
return new OpenAiEmbeddingModel(
OpenAiApi.builder()
.baseUrl("http://192.168.8.12:8000")
.apiKey("")
.build(),
MetadataMode.EMBED,
OpenAiEmbeddingOptions.builder()
.model("/home/ai/models/Qwen/Qwen3-VL-Embedding-2B")
.build()
);
}

@Bean
public MilvusServiceClient milvusServiceClient() {
    ConnectParam connectParam = ConnectParam.newBuilder()
            .withHost(host)
            .withPort(port)
            .withAuthorization("root","Milvus")
            .build();
    return new MilvusServiceClient(connectParam);
}

@Bean
@Primary
public MilvusVectorStore  milvusVectorStore(MilvusServiceClient milvusServiceClient,OpenAiEmbeddingModel embeddingModel) {
   return MilvusVectorStore.builder(milvusServiceClient,embeddingModel)
           .collectionName(collectionName)
           .build();
}

I started the Qwen3-VL-Embedding-2B model using VLLM

After using the vectorStore.add method, the error message is as follows:
{"error":{"message":"1 validation error:\n {'type': 'missing', 'loc': ('body',), 'msg': 'Field required', 'input': None}\n\n File "/home/venv_vllm_new/lib/python3.12/site-packages/vllm/entrypoints/utils.py", line 26, in create_embedding\n POST /v1/embeddings [{'type': 'missing', 'loc': ('body',), 'msg': 'Field required', 'input': None}]","type":"Bad Request","param":null,"code":400}}

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the vectorStore.add call with the shown OpenAiEmbeddingModel configuration and inspect the request sent to the VLLM /v1/embeddings endpoint. Compare the request with the endpoint's expected body for Qwen3-VL-Embedding-2B; done when the model works through the vector store or the incompatibility and required configuration are clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
java
Domain
databases, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.