WrenAI icon indicating copy to clipboard operation
WrenAI copied to clipboard
Published 1 week ago • verified publisher icon Canner

Azure open AI: 'Failed to create asking task'

Open louisssssssssss opened this issue 10 months ago • 4 comments

I used AZURE OPEN AI to deploy wernAI and i encountered 'Failed to create asking task' issue, please advise how to fix that, thx!

I use SHELL method to deploy service, the command of start service is './wren-launcher-linux'.

.env file as below.

env.txt

config.yaml as below

config.txt

logs as below

wren-ai-service.log

my containers as below

Image

louisssssssssss avatar Mar 13 '25 08:03 louisssssssssss

@louisssssssssss please carefully read the comment here: https://github.com/Canner/WrenAI/blob/1c4a5203ac657fa8332e18e102558c0cdc1516b9/wren-ai-service/docs/config_examples/config.azure.yaml#L49

cyyeh avatar Mar 13 '25 08:03 cyyeh

@cyyeh I updated pipeline as below. type: pipeline

pipes:

  • name: db_schema_indexing

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: historical_question_indexing

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: table_description_indexing

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: db_schema_retrieval

    llm: litellm_llm.azure/gpt-4o

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: historical_question_retrieval

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: sql_generation

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: sql_correction

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: followup_sql_generation

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: sql_summary

    llm: litellm_llm.azure/gpt-4o

  • name: sql_answer

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: sql_breakdown

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: sql_expansion

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: sql_explanation

    llm: litellm_llm.azure/gpt-4o

  • name: sql_regeneration

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: semantics_description

    llm: litellm_llm.azure/gpt-4o

  • name: relationship_recommendation

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: question_recommendation

    llm: litellm_llm.azure/gpt-4o

  • name: question_recommendation_db_schema_retrieval

    llm: litellm_llm.azure/gpt-4o

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: question_recommendation_sql_generation

    llm: litellm_llm.azure/gpt-4o

    engine: wren_ui

  • name: intent_classification

    llm: litellm_llm.azure/gpt-4o

    embedder: litellm_embedder.azure/text-embedding-3-large

    document_store: qdrant

  • name: data_assistance

    llm: litellm_llm.azure/gpt-4o

  • name: sql_pairs_indexing

    document_store: qdrant

    embedder: litellm_embedder.azure/text-embedding-3-large

  • name: sql_pairs_deletion

    document_store: qdrant

    embedder: litellm_embedder.azure/text-embedding-3-large

  • name: sql_pairs_retrieval

    document_store: qdrant

    embedder: litellm_embedder.azure/text-embedding-3-large

    llm: litellm_llm.azure/gpt-4o

  • name: preprocess_sql_data

    llm: litellm_llm.azure/gpt-4o

  • name: sql_executor

    engine: wren_ui

  • name: chart_generation

    llm: litellm_llm.azure/gpt-4o

  • name: chart_adjustment

    llm: litellm_llm.azure/gpt-4o

  • name: sql_question_generation

    llm: litellm_llm.azure/gpt-4o

  • name: sql_generation_reasoning

    llm: litellm_llm.azure/gpt-4o

a new issue emerged. wren-ai-service-1 | s: 0it [00:00, ?it/s] I0313 08:44:08.452 8 wren-ai-service:32] Project ID: None, Cleaning documents in view_questions

wren-ai-service-1 | W0313 08:44:08.461 8 wren-ai-service:261] Calling QdrantDocumentStore.write_documents() with empty list

wren-ai-service-1 | W0313 08:44:08.464 8 wren-ai-service:261] Calling QdrantDocumentStore.write_documents() with empty list

wren-ai-service-1 | INFO: 192.168.112.6:51786 - "GET /v1/semantics-preparations/ad0d51a67c9e7d9124b9fccebdf8853e6dda7830/status HTTP/1.1" 200 OK

wren-ai-service-1 | INFO: 192.168.112.6:51792 - "GET /v1/semantics-preparations/ad0d51a67c9e7d9124b9fccebdf8853e6dda7830/status HTTP/1.1" 200 OK

Calculating embeddings: 100%|██████████| 1/1 [00:03<00:00, 3.32s/it]

Calculating embeddings: 100%|██████████| 1/1 [00:03<00:00, 3.37s/it]

wren-ai-service-1 | I0313 08:44:11.820 8 wren-ai-service:32] Project ID: None, Cleaning documents in table_descriptions

wren-ai-service-1 | I0313 08:44:11.823 8 wren-ai-service:32] Project ID: None, Cleaning documents in Document

0%| | 0/12 [00:00<?, ?it/s]

wren-ai-service-1 | [00:00<?, ?it/s]

wren-ai-service-1 | ********************************************************************************

wren-ai-service-1 | > write [src.pipelines.indexing.db_schema.write()] encountered an error <

wren-ai-service-1 | > Node inputs:

wren-ai-service-1 | {'clean': "<Task finished name='Task-14' coro=<AsyncGraphAdap...",

wren-ai-service-1 | 'writer': '<src.pipelines.indexing.AsyncDocumentWriter object...'}

wren-ai-service-1 | ********************************************************************************

wren-ai-service-1 | Traceback (most recent call last):

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 122, in new_fn

wren-ai-service-1 | await fn(**fn_kwargs) if asyncio.iscoroutinefunction(fn) else fn(**fn_kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 219, in async_wrapper

wren-ai-service-1 | self._handle_exception(observation, e)

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 517, in _handle_exception

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 217, in async_wrapper

wren-ai-service-1 | result = await func(*args, **kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/db_schema.py", line 327, in write

wren-ai-service-1 | return await writer.run(documents=clean["documents"])

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/init.py", line 84, in run

wren-ai-service-1 | documents_written = await self.document_store.write_documents(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/providers/document_store/qdrant.py", line 283, in write_documents

wren-ai-service-1 | await self.async_client.upsert(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_client.py", line 1513, in upsert

wren-ai-service-1 | return await self._client.upsert(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_remote.py", line 1677, in upsert

wren-ai-service-1 | await self.openapi_client.points_api.upsert_points(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api/points_api.py", line 751, in upsert_points

wren-ai-service-1 | return await self._build_for_upsert_points(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 161, in request

wren-ai-service-1 | return await self.send(request, type_)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 184, in send

wren-ai-service-1 | raise UnexpectedResponse.for_response(response)

wren-ai-service-1 | qdrant_client.http.exceptions.UnexpectedResponse: Unexpected Response: 400 (Bad Request)

wren-ai-service-1 | Raw response content:

wren-ai-service-1 | b'{"status":{"error":"Wrong input: Vector dimension error: expected dim: 1536, got 3072"},"time":0.011539892}'

wren-ai-service-1 | -------------------------------------------------------------------

wren-ai-service-1 | Oh no an error! Need help with Hamilton?

wren-ai-service-1 | Join our slack and ask for help! https://join.slack.com/t/hamilton-opensource/shared_invite/zt-2niepkra8-DGKGf_tTYhXuJWBTXtIs4g

wren-ai-service-1 | -------------------------------------------------------------------

wren-ai-service-1 |

wren-ai-service-1 | E0313 08:44:11.907 8 wren-ai-service:98] Failed to prepare semantics: Unexpected Response: 400 (Bad Request)

wren-ai-service-1 | Raw response content:

wren-ai-service-1 | b'{"status":{"error":"Wrong input: Vector dimension error: expected dim: 1536, got 3072"},"time":0.011539892}'

wren-ai-service-1 | Traceback (most recent call last):

wren-ai-service-1 | File "/src/web/v1/services/semantics_preparation.py", line 90, in prepare_semantics

wren-ai-service-1 | await asyncio.gather(*tasks)

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 219, in async_wrapper

wren-ai-service-1 | self._handle_exception(observation, e)

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 517, in _handle_exception

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 217, in async_wrapper

wren-ai-service-1 | result = await func(*args, **kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/db_schema.py", line 370, in run

wren-ai-service-1 | return await self._pipe.execute(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 375, in execute

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 366, in execute

wren-ai-service-1 | outputs = await self.raw_execute(_final_vars, overrides, display_graph, inputs=inputs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 326, in raw_execute

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 321, in raw_execute

wren-ai-service-1 | results = await await_dict_of_tasks(task_dict)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 23, in await_dict_of_tasks

wren-ai-service-1 | coroutines_gathered = await asyncio.gather(*coroutines)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 36, in process_value

wren-ai-service-1 | return await val

wren-ai-service-1 | ^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 122, in new_fn

wren-ai-service-1 | await fn(**fn_kwargs) if asyncio.iscoroutinefunction(fn) else fn(**fn_kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 219, in async_wrapper

wren-ai-service-1 | self._handle_exception(observation, e)

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 517, in _handle_exception

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 217, in async_wrapper

wren-ai-service-1 | result = await func(*args, **kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/db_schema.py", line 327, in write

wren-ai-service-1 | return await writer.run(documents=clean["documents"])

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/init.py", line 84, in run

wren-ai-service-1 | documents_written = await self.document_store.write_documents(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/providers/document_store/qdrant.py", line 283, in write_documents

wren-ai-service-1 | await self.async_client.upsert(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_client.py", line 1513, in upsert

wren-ai-service-1 | return await self._client.upsert(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_remote.py", line 1677, in upsert

wren-ai-service-1 | await self.openapi_client.points_api.upsert_points(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api/points_api.py", line 751, in upsert_points

wren-ai-service-1 | return await self._build_for_upsert_points(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 161, in request

wren-ai-service-1 | return await self.send(request, type_)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 184, in send

wren-ai-service-1 | raise UnexpectedResponse.for_response(response)

wren-ai-service-1 | qdrant_client.http.exceptions.UnexpectedResponse: Unexpected Response: 400 (Bad Request)

wren-ai-service-1 | Raw response content:

wren-ai-service-1 | b'{"status":{"error":"Wrong input: Vector dimension error: expected dim: 1536, got 3072"},"time":0.011539892}'

0%| | 0/6 [00:00<?, ?it/s]

wren-ai-service-1 |

wren-ai-service-1 | ********************************************************************************

wren-ai-service-1 | > write [src.pipelines.indexing.table_description.write()] encountered an error<

wren-ai-service-1 | > Node inputs:

wren-ai-service-1 | {'clean': "<Task finished name='Task-28' coro=<AsyncGraphAdap...",

wren-ai-service-1 | 'writer': '<src.pipelines.indexing.AsyncDocumentWriter object...'}

wren-ai-service-1 | ********************************************************************************

wren-ai-service-1 | Traceback (most recent call last):

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/hamilton/async_driver.py", line 122, in new_fn

wren-ai-service-1 | await fn(**fn_kwargs) if asyncio.iscoroutinefunction(fn) else fn(**fn_kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 219, in async_wrapper

wren-ai-service-1 | self._handle_exception(observation, e)

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 517, in _handle_exception

wren-ai-service-1 | raise e

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/langfuse/decorators/langfuse_decorator.py", line 217, in async_wrapper

wren-ai-service-1 | result = await func(*args, **kwargs)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/table_description.py", line 110, in write

wren-ai-service-1 | return await writer.run(documents=clean["documents"])

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/pipelines/indexing/init.py", line 84, in run

wren-ai-service-1 | documents_written = await self.document_store.write_documents(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/src/providers/document_store/qdrant.py", line 283, in write_documents

wren-ai-service-1 | await self.async_client.upsert(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_client.py", line 1513, in upsert

wren-ai-service-1 | return await self._client.upsert(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/async_qdrant_remote.py", line 1677, in upsert

wren-ai-service-1 | await self.openapi_client.points_api.upsert_points(

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api/points_api.py", line 751, in upsert_points

wren-ai-service-1 | return await self._build_for_upsert_points(

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 161, in request

wren-ai-service-1 | return await self.send(request, type_)

wren-ai-service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

wren-ai-service-1 | File "/app/.venv/lib/python3.12/site-packages/qdrant_client/http/api_client.py", line 184, in send

wren-ai-service-1 | raise UnexpectedResponse.for_response(response)

wren-ai-service-1 | qdrant_client.http.exceptions.UnexpectedResponse: Unexpected Response: 400 (Bad Request)

wren-ai-service-1 | Raw response content:

wren-ai-service-1 | b'{"status":{"error":"Wrong input: Vector dimension error: expected dim: 1536, got 3072"},"time":0.00458162}'

wren-ai-service-1 | -------------------------------------------------------------------

wren-ai-service-1 | Oh no an error! Need help with Hamilton?

wren-ai-service-1 | Join our slack and ask for help! https://join.slack.com/t/hamilton-opensource/shared_invite/zt-2niepkra8-DGKGf_tTYhXuJWBTXtIs4g

wren-ai-service-1 | -------------------------------------------------------------------

wren-ai-service-1 |

wren-ai-service-1 | INFO: 192.168.112.6:51796 - "GET /v1/semantics-preparations/ad0d51a67c9e7d9124b9fccebdf8853e6dda7830/status HTTP/1.1" 200 OK

wren-ai-service-1 | Forcing deployment: {'data': {'deploy': {'status': 'FAILED', 'error': 'Wren AI Error: deployment hash:ad0d51a67c9e7d9124b9fccebdf8853e6dda7830, [object Object]'}}}

louisssssssssss avatar Mar 13 '25 08:03 louisssssssssss

Anybody can help this ? THX

louisssssssssss avatar Mar 14 '25 01:03 louisssssssssss

@louisssssssssss the error message said "Vector dimension error: expected dim: 1536, got 3072", please make sure you declare correct embedding model dimension in document store in config.yaml

type: document_store
provider: qdrant
location: http://qdrant:6333 # Donot set the QDRANT_API_KEY if you are using the qdrant from docker
embedding_model_dim: 1536 # Must match model dimension from embedder
timeout: 120
recreate_index: true

cyyeh avatar Mar 14 '25 01:03 cyyeh