Wrenai service container throws "Error: Application startup failed. Exiting"

[Erbaz]

Description

When using wrenai launcher on windows and selecting custom option for setup, I was able to up the docker network. However, the wrenai-wren-ai-service-1 container logs error and fails to start application and retries. The docker container remains up.

To Reproduce

Steps to reproduce the behavior:

1. Install wrenai launcher on Windows 11
2. Launch docker desktop
3. Launch Ollama and make sure you have nomic-embed-text:latest and llama3.1:latest pulled.
4. Update ~/.wrenai/config.yaml and ~/.wrenai/.env
5. Launch wrenai and select custom LLM provider
6. Open docker desktop and go to wrenai service container logs

Expected behavior

No error in logs should have appeared, and the application would not throw error.

Desktop Environment:

• OS: Windows 11
• Browser: Chrome

Wren AI Information

• Wrenai Launcher (Windows) Version: 0.29.1
• Wrenai service: 0.14.0

Additional context

I made changes to PROJECT_DIR in .env aswell trying to fix the issue but it did not really work:

COMPOSE_PROJECT_NAME=wrenai
PLATFORM=linux/amd64

PROJECT_DIR=C:/Users/pc/.wrenai 
...

Relevant log output

The config.yaml that is seen set on the wrenai-wren-ai-service-1 container:

# cat /app/config.yaml
type: llm
provider: litellm_llm
models:
- api_base: http://host.docker.internal:11434/v1
  model: ollama_chat/llama3.1:latest  # ollama_chat/<ollama_model_name>
  alias: default
  timeout: 600
  kwargs:
    n: 1
    temperature: 0
---
type: embedder
provider: litellm_embedder
models:
- model: openai/nomic-embed-text:latest
  alias: default
  api_base: http://host.docker.internal:11434/v1
  timeout: 600
---
type: document_store
provider: qdrant
location: http://qdrant:6333
embedding_model_dim: 768  # put your embedding model dimension here
timeout: 120
recreate_index: true

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

---

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.default
  - 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.default
  - 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.default
  - name: followup_sql_generation_reasoning
    llm: litellm_llm.default
  - 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
  - name: sql_diagnosis
    llm: litellm_llm.default
  - name: sql_knowledge_retrieval
    engine: wren_ibis
    document_store: qdrant
---
settings:
  column_indexing_batch_size: 50
  table_retrieval_size: 10
  table_column_retrieval_size: 100
  allow_using_db_schemas_without_pruning: false
  query_cache_maxsize: 1000
  query_cache_ttl: 3600
  langfuse_host: https://cloud.langfuse.com
  langfuse_enable: true
  logging_level: DEBUG
  development: false
# 

Error Logs:

I0110 14:42:44.540 8 wren-ai-service:42] Imported Provider: src.providers.llm.azure_openai

/app/.venv/lib/python3.12/site-packages/pydantic/_internal/_config.py:345: UserWarning: Valid config keys have changed in V2:

* 'fields' has been removed

  warnings.warn(message, UserWarning)

I0110 14:42:45.347 8 wren-ai-service:66] Registering provider: litellm_llm

I0110 14:42:45.347 8 wren-ai-service:42] Imported Provider: src.providers.llm.litellm

I0110 14:42:45.349 8 wren-ai-service:66] Registering provider: ollama_llm

I0110 14:42:45.349 8 wren-ai-service:42] Imported Provider: src.providers.llm.ollama

I0110 14:42:45.383 8 wren-ai-service:66] Registering provider: openai_llm

I0110 14:42:45.383 8 wren-ai-service:42] Imported Provider: src.providers.llm.openai

I0110 14:42:45.383 8 wren-ai-service:42] Imported Provider: src.providers.loader

ERROR:    Traceback (most recent call last):

  File "/app/.venv/lib/python3.12/site-packages/starlette/routing.py", line 693, in lifespan

    async with self.lifespan_context(app) as maybe_state:

  File "/usr/local/lib/python3.12/contextlib.py", line 204, in __aenter__

    return await anext(self.gen)

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

  File "/app/.venv/lib/python3.12/site-packages/fastapi/routing.py", line 133, in merged_lifespan

    async with original_context(app) as maybe_original_state:

  File "/usr/local/lib/python3.12/contextlib.py", line 204, in __aenter__

    return await anext(self.gen)

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

  File "/src/__main__.py", line 29, in lifespan

    pipe_components = generate_components(settings.components)

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

  File "/src/providers/__init__.py", line 391, in generate_components

    config = transform(configs)

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

  File "/src/providers/__init__.py", line 294, in transform

    converted = processor(entry)

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

  File "/src/providers/__init__.py", line 132, in embedder_processor

    "dimension": model["dimension"],

                 ~~~~~^^^^^^^^^^^^^

KeyError: 'dimension'


ERROR:    Application startup failed. Exiting.

[miguelmanlyx]

@Erbaz

Without a receipt it’s tough to tell if this is client, gateway, or provider. Tracing one request end to end (timing, retries, exit point) usually answers that. Happy to return a receipt via base_url swap or redacted payload (AI Badgr).

[Erbaz]

@miguelmanlyx I have updated the logs. Seems like I did not paste the relevant part of the error. But now you should be able to see the error cause.