[Bug] web-retriever test failed

[yongfengdu]

Priority

P2-High

OS type

Ubuntu

Hardware type

Xeon-GNR

Installation method

• Pull docker images from hub.docker.com
• Build docker images from source
• Other

Deploy method

• Docker
• Docker Compose
• Kubernetes Helm Charts
• Other

Running nodes

Single Node

What's the version?

opea/web-retriever:latest

Description

Test failed with latest opea/web-retriever image, which is built 7 days ago.
Tried with both helm chart and docker compose (https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/src)

The huggingface_hub version in image is 0.28.1

The error message with latest image is:

• "POST /v1/web_retrieval HTTP/1.1" 500 Internal Server Error
  ERROR: Exception in ASGI application
  Traceback (most recent call last):
  File "/usr/local/lib/python3.11/site-packages/chromadb/api/models/CollectionCommon.py", line 90, in wrapper
  return func(self, *args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/chromadb/api/models/CollectionCommon.py", line 389, in _validate_and_prepare_upsert_request
  upsert_records = normalize_insert_record_set(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/chromadb/api/types.py", line 187, in normalize_insert_record_set
  base_record_set = normalize_base_record_set(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/chromadb/api/types.py", line 164, in normalize_base_record_set
  embeddings=normalize_embeddings(embeddings),
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/chromadb/api/types.py", line 88, in normalize_embeddings
  raise ValueError(
  ValueError: Expected embeddings to be a list of floats or ints, a list of lists, a numpy array, or a list of numpy arrays, got [[[[2.7395002841949463, 3.2552080154418945, 1.2531545162200928, 8.331116676330566, 1.4570555686950684, 2.380880117416382, -0.5619943141937256, -1.3199527263641357, -0.033070024102926254, 0.1076865866780281, 1.6511542797088623, 1.504760503768921, 0.8926490545272827, 1.0040695667266846, -0.3639872670173645, -1.6770744323730469, -0.31314

Reproduce steps

https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/src#2-start-microservice-with-docker-compose-option-2

Raw log

Attachments

No response

[ZePan110]

Local testing can be replicated

[Spycsh]

Hi @yongfengdu , please export GOOGLE_API_KEY and GOOGLE_CSE_ID before starting service.

[Spycsh]

There is also a bug caused by latest huggingface_hub, so I fixed the version to make it work. #1270

[ZePan110]

Fix test pass, so close this issue. https://github.com/opea-project/GenAIComps/actions/runs/13223893617/job/37000915604