使用qwen3 llm和 qwen text-embedding-v3时，发生的运行时异常

**Describe the bug**
使用qwen3 llm和 qwen text-embedding-v3时，发生的运行时异常，在提问时候点击send后，客户端显示“Failed to create asking task.”

**config.yaml**
```
type: llm
provider: litellm_llm
models:
  # 通义千问Qwen-Max - 禁用思考模式
  - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    model: dashscope/qwen-plus
    alias: default
    timeout: 900
    kwargs:
      n: 1
      temperature: 0.1
      top_p: 0.8
      #allowed_openai_params: ["extra_headers"]
      #extra_headers:
        #X-DashScope-Async: "false"
  
  # 通义千问Qwen-Plus - 快速模式
  - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    model: dashscope/qwen-plus
    alias: qwen-fast
    timeout: 900
    kwargs:
      n: 1
      temperature: 0.1
      top_p: 0.8
      #allowed_openai_params: ["extra_headers"]
      #extra_headers:
        #X-DashScope-Async: "false"
  
  # 通义千问Qwen-Max - 启用思考模式处理复杂任务
  - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    model: dashscope/qwen-plus
    alias: qwen-thinking
    timeout: 1200  # 思考模式需要更长超时时间
    kwargs:
      n: 1
      temperature: 0.3
      top_p: 0.9
      #allowed_openai_params: ["extra_headers"]
      #extra_headers:
        #X-DashScope-Async: "false"
  
  # 通义千问Qwen-Max - JSON响应模式
  - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    model: dashscope/qwen-plus
    alias: qwen-json
    timeout: 900
    kwargs:
      n: 1
      temperature: 0.05
      top_p: 0.7
      response_format:
        type: json_object
      #allowed_openai_params: ["extra_headers"]
      #extra_headers:
        #X-DashScope-Async: "false"

---
type: embedder
provider: litellm_embedder
models:
  - model: dashscope/text-embedding-v3
    alias: default
    api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    timeout: 120
    kwargs:
      #allowed_openai_params: ["extra_headers"]
      #extra_headers:
        #X-DashScope-Async: "false"

---
type: engine
provider: wren_ui
endpoint: http://wren-ui:3000

---
type: engine
provider: wren_ibis
endpoint: http://ibis-server:8000

---
type: document_store
provider: qdrant
location: http://qdrant:6333
embedding_model_dim: 1024
timeout: 120
recreate_index: true

---
# 使用阿里云模型替换原有模型
# 格式为<provider>.<model_alias>
type: pipeline
pipes:
  - name: db_schema_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: historical_question_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: table_description_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: db_schema_retrieval
    llm: litellm_llm.default
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: historical_question_retrieval
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: sql_correction
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: followup_sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: sql_answer
    llm: litellm_llm.qwen-fast
  - name: semantics_description
    llm: litellm_llm.default
  - name: relationship_recommendation
    llm: litellm_llm.default
    engine: wren_ui
  - name: question_recommendation
    llm: litellm_llm.default
  - name: question_recommendation_db_schema_retrieval
    llm: litellm_llm.default
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: question_recommendation_sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: chart_generation
    llm: litellm_llm.default
  - name: chart_adjustment
    llm: litellm_llm.default
  - name: intent_classification
    llm: litellm_llm.default
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: misleading_assistance
    llm: litellm_llm.default
  - name: data_assistance
    llm: litellm_llm.qwen-fast
  - name: sql_pairs_indexing
    document_store: qdrant
    embedder: litellm_embedder.default
  - name: sql_pairs_retrieval
    document_store: qdrant
    embedder: litellm_embedder.default
    llm: litellm_llm.default
  - name: preprocess_sql_data
    llm: litellm_llm.default
  - name: sql_executor
    engine: wren_ui
  - name: user_guide_assistance
    llm: litellm_llm.default
  - name: sql_question_generation
    llm: litellm_llm.default
  - name: sql_generation_reasoning
    llm: litellm_llm.qwen-thinking
  - name: followup_sql_generation_reasoning
    llm: litellm_llm.qwen-thinking
  - name: sql_regeneration
    llm: litellm_llm.default
    engine: wren_ui
  - name: instructions_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: instructions_retrieval
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: sql_functions_retrieval
    engine: wren_ibis
    document_store: qdrant
  - name: project_meta_indexing
    document_store: qdrant
  - name: sql_tables_extraction
    llm: litellm_llm.default

---
settings:
  engine_timeout: 30
  column_indexing_batch_size: 50
  table_retrieval_size: 10
  table_column_retrieval_size: 100
  allow_intent_classification: true
  allow_sql_generation_reasoning: true
  allow_sql_functions_retrieval: true
  enable_column_pruning: false
  max_sql_correction_retries: 3
  query_cache_maxsize: 1000
  query_cache_ttl: 3600
  langfuse_host: https://cloud.langfuse.com
  langfuse_enable: true
  logging_level: DEBUG
  development: true
  historical_question_retrieval_similarity_threshold: 0.9
  sql_pairs_similarity_threshold: 0.7
  sql_pairs_retrieval_max_size: 10
  instructions_similarity_threshold: 0.7
  instructions_top_k: 10
```
**To Reproduce**
Steps to reproduce the behavior:
1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

**Expected behavior**
A clear and concise description of what you expected to happen.

**Screenshots**
If applicable, add screenshots to help explain your problem.

**Desktop (please complete the following information):**
- OS: [e.g. iOS]
- Browser [e.g. chrome, safari]

**Wren AI Information**
- Version: main latest

**Additional context**
Add any other context about the problem here.

**Relevant log output**
- [wren-ai-service:0.27.1]
    ```
bash
     > embedding [src.pipelines.retrieval.db_schema_retrieval.embedding()] encountered an error<

> Node inputs:

{'embedder': '<src.providers.embedder.litellm.AsyncTextEmbedder ...',

 'histories': [],

 'query': '不同采购订单类型的订单金额分布情况如何？'}

********************************************************************************

Traceback (most recent call last):

  File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 122, in new_fn

    await fn(**fn_kwargs) if asyncio.iscoroutinefunction(fn) else fn(**fn_kwargs)

    ^^^^^^^^^^^^^^^^^^^^^

  File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 219, in async_wrapper

    self._handle_exception(observation, e)

  File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 520, in _handle_exception

    raise e

  File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 217, in async_wrapper

    result = await func(*args, **kwargs)

             ^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/src/pipelines/retrieval/db_schema_retrieval.py", line 134, in embedding

    return await embedder.run(query)

           ^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/app/.venv/lib/python3.12/site-packages/backoff/_async.py", line 151, in retry

    ret = await target(*args, **kwargs)

          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/src/providers/embedder/litellm.py", line 62, in run

    response = await aembedding(

               ^^^^^^^^^^^^^^^^^

  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1586, in wrapper_async

    raise e

  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1437, in wrapper_async

    result = await original_function(*args, **kwargs)

             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^    


    ```


Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

使用qwen3 llm和 qwen text-embedding-v3时，发生的运行时异常 #1902

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

使用qwen3 llm和 qwen text-embedding-v3时，发生的运行时异常 #1902

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions