-
Notifications
You must be signed in to change notification settings - Fork 546
"make run_batch" in the streaming_pipeline gives error #85
Description
I get the following 2 errors in the streaming_pipeline while trying to run "make run_batch":
~/projects/hands-on-llms/modules/streaming_pipeline$ make run_batch
RUST_BACKTRACE=full poetry run python -m bytewax.run -p4 "tools.run_batch:build_flow(latest_n_days=1)"
2024-07-07 16:20:07,355 - INFO - Initializing env vars...
2024-07-07 16:20:07,355 - INFO - Loading environment variables from: .env
2024-07-07 16:20:07,356 - INFO - Extracting news from 2024-07-06 16:20:07.356816 to 2024-07-07 16:20:07.356816 [n_days=1]
2024-07-07 16:20:09,841 - INFO - HTTP Request: GET https://4007c426-1f83-4326-9500-ac1ae11ac9e6.us-east4-0.gcp.cloud.qdrant.io:6333/collections/alpaca_financial_news "HTTP/2 200 OK"
Traceback (most recent call last):
File "/home/patilmh/.cache/pypoetry/virtualenvs/streaming-pipeline-qRv2lzOY-py3.10/lib/python3.10/site-packages/qdrant_client/http/api_client.py", line 88, in send
return parse_as_type(response.json(), type_)
File "/home/patilmh/.cache/pypoetry/virtualenvs/streaming-pipeline-qRv2lzOY-py3.10/lib/python3.10/site-packages/qdrant_client/http/api_client.py", line 201, in parse_as_type
return model_type(obj=obj).obj
File "pydantic/main.py", line 341, in pydantic.main.BaseModel.init
pydantic.error_wrappers.ValidationError: 2 validation errors for ParsingModel[InlineResponse2005] (for parse_as_type)
obj -> result -> vectors_count
field required (type=value_error.missing)
obj -> result -> config -> optimizer_config -> max_optimization_threads
none is not an allowed value (type=type_error.none.not_allowed)
I tried using the solution posted in #76 where @dvquy13 suggested initializing max_optimization_threads, but that did not fix this problem. Also note that issue #72 was only for 1 error:
obj -> result -> config -> optimizer_config -> max_optimization_threads
none is not an allowed value (type=type_error.none.not_allowed)
That issue did not mention type=value_error.missing for obj -> result -> vectors_count. Please does anyone have any suggestions?