Error: src/pipelines/retrieval/retrieval.py table_contents

[lsky-walt]

Describe the bug
When ai-service is initialized, table_contents error is reported

To Reproduce
Steps to reproduce the behavior:

1. Use wren-launcher-linux to start and set custom
2. docker logs -f wrenai-wren-ai-service-1

Expected behavior
success?

Screenshots

Desktop (please complete the following information):

• OS: macos
• Browser chrome:133

Wren AI Information
WREN_PRODUCT_VERSION=0.15.3
WREN_ENGINE_VERSION=0.13.1
WREN_AI_SERVICE_VERSION=0.15.17
IBIS_SERVER_VERSION=0.13.1
WREN_UI_VERSION=0.20.1
WREN_BOOTSTRAP_VERSION=0.1.5

Additional context
Use Alibaba Cloud API, compatible with OpenAI

Relevant log output

# you should rename this file to config.yaml and put it in ~/.wrenai
# please pay attention to the comments starting with # and adjust the config accordingly

type: llm
provider: litellm_llm
models:
  # put OPENAI_API_KEY=<random_string> in ~/.wrenai/.env
  - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1 # change this to your ollama host, api_base should be <ollama_url>/v1
    api_key_name: LLM_OLLAMA_API_KEY
    model: openai/qwen-plus-2025-01-25 # openai/<ollama_model_name>
    timeout: 600
    kwargs:
      n: 1
      temperature: 0

---
type: embedder
provider: litellm_embedder
models:
  # put OPENAI_API_KEY=<random_string> in ~/.wrenai/.env
  - model: openai/text-embedding-v3 # put your ollama embedder model name here, openai/<ollama_model_name>
    api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
    api_key_name: EMBEDDER_OLLAMA_API_KEY
    timeout: 600

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

---
type: document_store
provider: qdrant
location: http://qdrant:6333
embedding_model_dim: 1024 # put your embedding model dimension here
timeout: 120
recreate_index: true

---
# please change the llm and embedder names to the ones you want to use
# the format of llm and embedder should be <provider>.<model_name> such as litellm_llm.gpt-4o-2024-08-06
# the pipes may be not the latest version, please refer to the latest version: https://raw.githubusercontent.com/canner/WrenAI/<WRENAI_VERSION_NUMBER>/docker/config.example.yaml
type: pipeline
pipes:
  - name: db_schema_indexing
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: historical_question_indexing
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: table_description_indexing
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: db_schema_retrieval
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: historical_question_retrieval
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: sql_generation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: sql_correction
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: followup_sql_generation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: sql_summary
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_answer
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: sql_breakdown
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: sql_expansion
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: sql_explanation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: semantics_description
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: relationship_recommendation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: question_recommendation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: question_recommendation_db_schema_retrieval
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: question_recommendation_sql_generation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui
  - name: chart_generation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: chart_adjustment
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: intent_classification
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    embedder: litellm_embedder.openai/text-embedding-v3
    document_store: qdrant
  - name: data_assistance
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_pairs_deletion
    document_store: qdrant
    embedder: litellm_embedder.openai/text-embedding-v3
  - name: sql_pairs_indexing
    document_store: qdrant
    embedder: litellm_embedder.openai/text-embedding-v3
  - name: sql_pairs_retrieval
    document_store: qdrant
    embedder: litellm_embedder.openai/text-embedding-v3
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_pairs_preparation
    document_store: qdrant
    embedder: litellm_embedder.openai/text-embedding-v3
  - name: preprocess_sql_data
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_executor
    engine: wren_ui
  - name: sql_question_generation
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_generation_reasoning
    llm: litellm_llm.openai/qwen-plus-2025-01-25
  - name: sql_regeneration
    llm: litellm_llm.openai/qwen-plus-2025-01-25
    engine: wren_ui

---
settings:
  column_indexing_batch_size: 50
  table_retrieval_size: 10
  table_column_retrieval_size: 100
  allow_using_db_schemas_without_pruning: false # if you want to use db schemas without pruning, set this to true. It will be faster
  query_cache_maxsize: 1000
  query_cache_ttl: 3600
  langfuse_host: https://cloud.langfuse.com
  langfuse_enable: true
  logging_level: DEBUG
  development: true