Fix VideoQnA

[cwlacewe]

Description

This PR fixes the VideoQnA example.

Issues

Fixes #1476 #1478 #1477
Depends on GenAIComps PR#1317

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

cd VideoQnA/tests
export HF_TOKEN=<Huggingface token>
./test_compose_on_xeon.sh

[github-actions]

Dependency Review

✅ No vulnerabilities or license issues found.

Scanned Files

None

[lvliang-intel]

@cwlacewe,
please fix the CI issue.

[yinghu5]

@cwlacewe one CI for VideoQnA failed. could you please check?
[2025-04-10 02:56:33,543] [ ERROR] - opea_dataprep_multimodal_microservice - Error during dataprep ingest videos invocation: openai/clip-vit-base-patch32 does not appear to have a file named pytorch_model.bin but there is a file for TensorFlow weights. Use from_tf=True to load this model from those weights.
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
result = await app( # type: ignore[func-returns-value]

[xiguiw]

CI failure:
Could not cache non-existence of file. Will ignore error and continue. Error: [Errno 13] Permission denied: '/home/user/.cache/huggingface/hub/models--openai--clip-vit-base-patch32'
Permission denied

[2025-04-11 08:21:57,549] [    INFO] - opea_dataprep_vdms_multimodal - Connecting to vdms at 10.244.159.163:8001
Could not cache non-existence of file. Will ignore error and continue. Error: [Errno 13] Permission denied: '/home/user/.cache/huggingface/hub/models--openai--clip-vit-base-patch32'
Could not cache non-existence of file. Will ignore error and continue. Error: [Errno 13] Permission denied: '/home/user/.cache/huggingface/hub/models--openai--clip-vit-base-patch32'
Could not cache non-existence of file. Will ignore error and continue. Error: [Errno 13] Permission denied: '/home/user/.cache/huggingface/hub/models--openai--clip-vit-base-patch32'
[2025-04-11 08:21:58,100] [   ERROR] - opea_dataprep_multimodal_microservice - Error during dataprep ingest videos invocation: openai/clip-vit-base-patch32 does not appear to have a file named pytorch_model.bin but there is a file for TensorFlow weights. Use `from_tf=True` to load this model from those weights.
ERROR:    Exception in ASGI application