Failed to deploy. Please check the log for more details.

[wmrenr]

Ask everyone for help: I applied large model of ollama deployed locally to start WrenAI. Now the UI interface is such an error, but all logs do not report any error, how to solve?

Here are my all logs, config.yaml, .env, docker-compose.yaml:
wrenai-wren-ai-service.log
wrenai-wren-engine.log
wrenai-wren-ui.log
wrenai-ibis-server.log

config.yaml
type: llm
provider: litellm_llm
models:

• api_base: http://host.docker.internal:11434/v1 # change this to your ollama host, api_base should be <ollama_url>/v1
  model: openai/qwen2.5:0.5b # openai/<ollama_model_name>
  api_key_name: LLM_OLLAMA_API_KEY
  timeout: 600
  kwargs:
  n: 1
  temperature: 0

---

type: embedder
provider: litellm_embedder
models:

• model: openai/nomic-embed-text:latest # put your ollama embedder model name here, openai/<ollama_model_name>
  api_key_name: EMBEDDER_OLLAMA_API_KEY
  api_base: http://host.docker.internal:11434/v1 # change this to your ollama host, api_base should be <ollama_url>/v1
  timeout: 600

---

type: engine
provider: wren_ui
endpoint: http://wren_ui:3000

---

type: document_store
provider: qdrant
location: http://qdrant:6333
embedding_model_dim: 768
timeout: 120
recreate_index: true

---

type: pipeline
pipes:

• name: db_schema_indexing
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: historical_question_indexing
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: table_description_indexing
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: db_schema_retrieval
  llm: litellm_llm.openai/qwen2.5:0.5b
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: historical_question_retrieval
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: sql_generation
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: sql_correction
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: followup_sql_generation
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: sql_summary
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_answer
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: sql_breakdown
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: sql_expansion
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: semantics_description
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: relationship_recommendation
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: question_recommendation
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: question_recommendation_db_schema_retrieval
  llm: litellm_llm.openai/qwen2.5:0.5b
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: question_recommendation_sql_generation
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: chart_generation
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: chart_adjustment
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: intent_classification
  llm: litellm_llm.openai/qwen2.5:0.5b
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  document_store: qdrant
• name: data_assistance
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_pairs_indexing
  document_store: qdrant
  embedder: litellm_embedder.openai/nomic-embed-text:latest
• name: sql_pairs_retrieval
  document_store: qdrant
  embedder: litellm_embedder.openai/nomic-embed-text:latest
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: preprocess_sql_data
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_executor
  engine: wren_ui
• name: sql_question_generation
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_generation_reasoning
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_regeneration
  llm: litellm_llm.openai/qwen2.5:0.5b
  engine: wren_ui
• name: sql_explanation
  llm: litellm_llm.openai/qwen2.5:0.5b
• name: sql_pairs_deletion
  document_store: qdrant
  embedder: litellm_embedder.openai/nomic-embed-text:latest

---

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: true

.env
COMPOSE_PROJECT_NAME=wrenai
PLATFORM=linux/amd64

PROJECT_DIR=/root/.wrenai

WREN_ENGINE_PORT=8080
WREN_ENGINE_SQL_PORT=7432
WREN_AI_SERVICE_PORT=5555
WREN_UI_PORT=3000
IBIS_SERVER_PORT=8000
WREN_UI_ENDPOINT=http://wren-ui:${WREN_UI_PORT}

QDRANT_HOST=qdrant
SHOULD_FORCE_DEPLOY=1

LLM_OPENAI_API_KEY=randomstring
EMBEDDER_OPENAI_API_KEY=randomstring
LLM_AZURE_OPENAI_API_KEY=randomstring
EMBEDDER_AZURE_OPENAI_API_KEY=randomstring
LLM_OLLAMA_API_KEY=randomstring
EMBEDDER_OLLAMA_API_KEY=randomstring
OPENAI_API_KEY=randomstring

WREN_PRODUCT_VERSION=0.15.3
WREN_ENGINE_VERSION=0.13.1
WREN_AI_SERVICE_VERSION=0.15.7
IBIS_SERVER_VERSION=latest
WREN_UI_VERSION=0.20.1
WREN_BOOTSTRAP_VERSION=0.1.5

user id (uuid v4)

USER_UUID=

TELEMETRY_ENABLED=true

this is for telemetry to know the model, i think ai-service might be able to provide a endpoint to get the information

GENERATION_MODEL=gpt-4o-mini
LANGFUSE_SECRET_KEY=
LANGFUSE_PUBLIC_KEY=

the port exposes to the host

OPTIONAL: change the port if you have a conflict

HOST_PORT=3000
AI_SERVICE_FORWARD_PORT=5555

Wren UI

EXPERIMENTAL_ENGINE_RUST_VERSION=false

docker-compose.yaml*********
version: "3"

volumes:
data:

networks:
wren:
driver: bridge

services:
bootstrap:
image: ghcr.io/canner/wren-bootstrap:${WREN_BOOTSTRAP_VERSION}
restart: on-failure
platform: ${PLATFORM}
environment:
DATA_PATH: /app/data
volumes:
- data:/app/data
command: /bin/sh /app/init.sh

wren-engine:
image: ghcr.io/canner/wren-engine:${WREN_ENGINE_VERSION}
restart: on-failure
platform: ${PLATFORM}
expose:
- ${WREN_ENGINE_PORT}
- ${WREN_ENGINE_SQL_PORT}
volumes:
- data:/usr/src/app/etc
- ${PROJECT_DIR}/data:/usr/src/app/data
networks:
- wren
extra_hosts:
- "host.docker.internal:host-gateway"
depends_on:
- bootstrap

ibis-server:
image: ghcr.io/canner/wren-engine-ibis:${IBIS_SERVER_VERSION}
restart: on-failure
platform: ${PLATFORM}
expose:
- ${IBIS_SERVER_PORT}
environment:
WREN_ENGINE_ENDPOINT: http://wren-engine:${WREN_ENGINE_PORT}
networks:
- wren
extra_hosts:
- "host.docker.internal:host-gateway"

wren-ai-service:
image: ghcr.io/canner/wren-ai-service:${WREN_AI_SERVICE_VERSION}
restart: on-failure
platform: ${PLATFORM}
expose:
- ${WREN_AI_SERVICE_PORT}
ports:
- ${AI_SERVICE_FORWARD_PORT}:${WREN_AI_SERVICE_PORT}
environment:
# sometimes the console won't show print messages,
# using PYTHONUNBUFFERED: 1 can fix this
PYTHONUNBUFFERED: 1
CONFIG_PATH: /app/data/config.yaml
env_file:
- ${PROJECT_DIR}/.env
volumes:
- ${PROJECT_DIR}/config.yaml:/app/data/config.yaml
networks:
- wren
extra_hosts:
- "host.docker.internal:host-gateway"
depends_on:
- qdrant

qdrant:
image: qdrant/qdrant:v1.11.0
restart: on-failure
expose:
- 6333
- 6334
volumes:
- data:/qdrant/storage
networks:
- wren
extra_hosts:
- "host.docker.internal:host-gateway"

wren-ui:
image: ghcr.io/canner/wren-ui:${WREN_UI_VERSION}
restart: on-failure
platform: ${PLATFORM}
environment:
DB_TYPE: sqlite
# /app is the working directory in the container
SQLITE_FILE: /app/data/db.sqlite3
WREN_ENGINE_ENDPOINT: http://wren-engine:${WREN_ENGINE_PORT}
WREN_AI_ENDPOINT: http://wren-ai-service:${WREN_AI_SERVICE_PORT}
IBIS_SERVER_ENDPOINT: http://ibis-server:${IBIS_SERVER_PORT}

  GENERATION_MODEL: ${GENERATION_MODEL}
  # telemetry
  WREN_ENGINE_PORT: ${WREN_ENGINE_PORT}
  WREN_AI_SERVICE_VERSION: ${WREN_AI_SERVICE_VERSION}
  WREN_UI_VERSION: ${WREN_UI_VERSION}
  WREN_ENGINE_VERSION: ${WREN_ENGINE_VERSION}
  USER_UUID: ${USER_UUID}
  POSTHOG_API_KEY: ${POSTHOG_API_KEY}
  POSTHOG_HOST: ${POSTHOG_HOST}
  TELEMETRY_ENABLED: ${TELEMETRY_ENABLED}
  # client side
  NEXT_PUBLIC_USER_UUID: ${USER_UUID}
  NEXT_PUBLIC_POSTHOG_API_KEY: ${POSTHOG_API_KEY}
  NEXT_PUBLIC_POSTHOG_HOST: ${POSTHOG_HOST}
  NEXT_PUBLIC_TELEMETRY_ENABLED: ${TELEMETRY_ENABLED}
  EXPERIMENTAL_ENGINE_RUST_VERSION: ${EXPERIMENTAL_ENGINE_RUST_VERSION}
  # configs
  WREN_PRODUCT_VERSION: ${WREN_PRODUCT_VERSION}
ports:
  # HOST_PORT is the port you want to expose to the host machine
  - ${HOST_PORT}:3000
volumes:
  - data:/app/data
networks:
  - wren
extra_hosts:
  - "host.docker.internal:host-gateway"
depends_on:
  - wren-ai-service
  - wren-engine

[wwwy3y3]

Hi @wmrenr thanks for reaching out. @paopa please check it when you're available.

[paopa]

Hi @wmrenr, I noticed there is an error log about litellm.exceptions.APIError: litellm.APIError: APIError: OpenAIException - Connection error. in your ai-service.log. and also noticed there are api_key_name: LLM_OLLAMA_API_KEY in llm and embedder section. Can you try to remove them and also the env in .env file, then give it a try again?

Also, provided my config for ollama, you might be able to refer to

models:
- api_base: http://host.docker.internal:11434/
  kwargs:
    n: 1
    temperature: 0
  model: ollama/phi4
provider: litellm_llm
timeout: 120
type: llm
---
models:
- api_base: http://host.docker.internal:11434/
  model: ollama/nomic-embed-text:latest
  timeout: 120
provider: litellm_embedder
type: embedder

[wmrenr]

Hi @wmrenr, I noticed there is an error log about litellm.exceptions.APIError: litellm.APIError: APIError: OpenAIException - Connection error. in your ai-service.log. and also noticed there are api_key_name: LLM_OLLAMA_API_KEY in llm and embedder section. Can you try to remove them and also the env in .env file, then give it a try again?

Also, provided my config for ollama, you might be able to refer to

models:

• api_base: http://host.docker.internal:11434/
  kwargs:
  n: 1
  temperature: 0
  model: ollama/phi4
  provider: litellm_llm
  timeout: 120
  type: llm

---

models:

• api_base: http://host.docker.internal:11434/
  model: ollama/nomic-embed-text:latest
  timeout: 120
  provider: litellm_embedder
  type: embedder

Sorry, the wrenai-ren-AI-service. log I uploaded is not corresponding before this, I now update all logs as fllows: (config.yaml, .env and docker-compose.yaml are the same as above )

wrenai-wren-ai-service.log
wrenai-wren-engine.log
wrenai-wren-ui.log
wrenai-ibis-server.log

All logs do not report any error, but the UI interface shows such errors.

[wmrenr]

Hi @wmrenr, I noticed there is an error log about litellm.exceptions.APIError: litellm.APIError: APIError: OpenAIException - Connection error. in your ai-service.log. and also noticed there are api_key_name: LLM_OLLAMA_API_KEY in llm and embedder section. Can you try to remove them and also the env in .env file, then give it a try again?
Also, provided my config for ollama, you might be able to refer to
models:

• api_base: http://host.docker.internal:11434/
  kwargs:
  n: 1
  temperature: 0
  model: ollama/phi4
  provider: litellm_llm
  timeout: 120
  type: llm

models:

• api_base: http://host.docker.internal:11434/
  model: ollama/nomic-embed-text:latest
  timeout: 120
  provider: litellm_embedder
  type: embedder

Sorry, the wrenai-ren-AI-service. log I uploaded is not corresponding before this, I now update all logs as fllows: (config.yaml, .env and docker-compose.yaml are the same as above )

wrenai-wren-ai-service.log wrenai-wren-engine.log wrenai-wren-ui.log wrenai-ibis-server.log

All logs do not report any error, but the UI interface shows such errors.

@paopa Could you please have time to look over my problems?

[paopa]

Hi @wmrenr, I’m having a bit of a hard time figuring out what’s causing this issue from your log. It seems to only pop up when Wren AI is deploying the model for your data source. Could you add some extra logging functionality? Also, could you let me know which version of Wren AI you’re using and how you’re deploying it (launcher, Docker Compose, or from scratch)? And does it happen every time you restart the system?

[wmrenr]

Hi @wmrenr, I’m having a bit of a hard time figuring out what’s causing this issue from your log. It seems to only pop up when Wren AI is deploying the model for your data source. Could you add some extra logging functionality? Also, could you let me know which version of Wren AI you’re using and how you’re deploying it (launcher, Docker Compose, or from scratch)? And does it happen every time you restart the system?

I can try to add some extra logging functionality; My version of Wren AI is 0.15.3; I deployed it by Docker Compose; It happen every time When I restart the system.