关于无法创建任务

[255121]

目前使用litellm进行连接deepseek官网api

config.yaml配置如下

models:

• api_base: https://api.deepseek.com/v1
  kwargs:
  n: 1
  response_format:
  type: text
  temperature: 0
  model: deepseek/deepseek-reasoner
  timeout: 120
• api_base: https://api.deepseek.com/v1
  kwargs:
  n: 1
  response_format:
  type: text
  temperature: 0
  model: deepseek/deepseek-chat
  timeout: 120
• api_base: https://api.deepseek.com/v1
  kwargs:
  n: 1
  response_format:
  type: json_object
  temperature: 0
  model: deepseek/deepseek-coder
  timeout: 120
  provider: litellm_llm
  type: llm

---

models:

• api_base: https://127.0.0.1:38097/v1
  model: gte-large
  timeout: 120
  provider: litellm_embedder
  type: embedder

---

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

connection_info: ''
endpoint: http://localhost:8000
manifest: ''
provider: wren_ibis
source: bigquery
type: engine

endpoint: http://localhost:8080
manifest: ''
provider: wren_engine
type: engine

embedding_model_dim: 3072
location: http://localhost:6333
provider: qdrant
recreate_index: false
timeout: 120
type: document_store

pipes:

• document_store: qdrant
  embedder: litellm_embedder.gte-large
  name: db_schema_indexing
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  name: historical_question_indexing
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  name: table_description_indexing
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  llm: litellm_llm.deepseek/deepseek-coder
  name: db_schema_retrieval
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  name: historical_question_retrieval
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_generation
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_correction
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: followup_sql_generation
• llm: litellm_llm.deepseek/deepseek-coder
  name: sql_summary
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-chat
  name: sql_answer
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_breakdown
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_expansion
• llm: litellm_llm.deepseek/deepseek-coder
  name: semantics_description
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: relationship_recommendation
• llm: litellm_llm.deepseek/deepseek-coder
  name: question_recommendation
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  llm: litellm_llm.deepseek/deepseek-coder
  name: question_recommendation_db_schema_retrieval
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: question_recommendation_sql_generation
• llm: litellm_llm.deepseek/deepseek-coder
  name: chart_generation
• llm: litellm_llm.deepseek/deepseek-coder
  name: chart_adjustment
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  llm: litellm_llm.deepseek/deepseek-coder
  name: intent_classification
• llm: litellm_llm.deepseek/deepseek-chat
  name: data_assistance
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  name: sql_pairs_indexing
• document_store: qdrant
  embedder: litellm_embedder.gte-large
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_pairs_retrieval
• llm: litellm_llm.deepseek/deepseek-coder
  name: preprocess_sql_data
• engine: wren_ui
  name: sql_executor
• llm: litellm_llm.deepseek/deepseek-coder
  name: sql_question_generation
• llm: litellm_llm.deepseek/deepseek-reasoner
  name: sql_generation_reasoning
• engine: wren_ui
  llm: litellm_llm.deepseek/deepseek-coder
  name: sql_regeneration
  type: pipeline

---

settings:
allow_using_db_schemas_without_pruning: false
column_indexing_batch_size: 50
development: false
engine_timeout: 30
host: 127.0.0.1
langfuse_enable: true
langfuse_host: https://cloud.langfuse.com
logging_level: INFO
port: 5556
query_cache_maxsize: 1000
query_cache_ttl: 3600
table_column_retrieval_size: 100
table_retrieval_size: 10

我们在env文件中加入了相应的deepseek api key，当请求what could i ask时出现如下问题
litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=litellm_llm/deepseek/deepseek-coder
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

Oh no an error! Need help with Hamilton?
Join our slack and ask for help! https://join.slack.com/t/hamilton-opensource/shared_invite/zt-2niepkra8-DGKGf_tTYhXuJWBTXtIs4g

E0307 16:40:17.972 31064 wren-ai-service:60] An error occurred during question recommendation generation: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=litellm_llm/deepseek/deepseek-coder
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers
E0307 16:40:17.972 31064 wren-ai-service:60] An error occurred during question recommendation generation: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=litellm_llm/deepseek/deepseek-coder
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

当输出任意问题时出现下列问题

http://localhost:3000/api/graphql请求响应为
{
"errors": [
{
"locations": [
{
"line": 2,
"column": 3
}
],
"path": [
"createAskingTask"
],
"message": "Cannot read properties of null (reading 'hash')",
"extensions": {
"code": "INTERNAL_SERVER_ERROR",
"message": "Cannot read properties of null (reading 'hash')",
"shortMessage": "Internal server error"
}
}
],
"data": null
}

[Trace2333]

same problem