Skip to content

Conversation

@lianhao
Copy link
Collaborator

@lianhao lianhao commented Jul 7, 2025

Description

Upgrade ghcr.io/huggingface/tei-gaudi:1.5.0 into
ghcr.io/huggingface/text-embeddings-inference:hpu-1.7.

Issues

Fixes #1157

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

Describe the tests that you ran to verify your changes.

Upgrade ghcr.io/huggingface/tei-gaudi:1.5.0 into
ghcr.io/huggingface/text-embeddings-inference:hpu-1.7

Signed-off-by: Lianhao Lu <[email protected]>
@lianhao lianhao requested a review from yongfengdu as a code owner July 7, 2025 08:48
Copy link
Collaborator

@eero-t eero-t left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

microservice-connector has also 3 references to this, but I guess we don't care about it any more => approved.

@eero-t
Copy link
Collaborator

eero-t commented Jul 7, 2025

Both ChatQnA faqgen-gaudi-values & cpu-ollaman-values CI tests had similar problem in test PDF uploading / model downloading:

 POD LOGS: chatqna07084824-data-prep-testpod
Get ingest file of type docx ...
Test ingest file of type docx ...
{"status":200,"message":"Data preparation succeeded"}
Get ingest file of type pdf ...
Test ingest file of type pdf ...
curl: (22) The requested URL returned error: 500
Internal Server Errorcurl failed with code 22

Error: unable to get pod logs for chatqna07084824-llm-uservice-testpod: pods "chatqna07084824-llm-uservice-testpod" not found
...
[pod/chatqna07084824-data-prep-5b98bdf675-9jgth/data-prep] [2025-07-07 08:50:16,000] [    INFO] - redis_dataprep - [ redis ingest] File ingest_dataprep.pdf does not exist.
[pod/chatqna07084824-data-prep-5b98bdf675-9jgth/data-prep] [2025-07-07 08:52:57,173] [   ERROR] - opea_dataprep_microservice - Error during dataprep ingest invocation: HTTPConnectionPool(host='chatqna07084824-tei', port=80): Max retries exceeded with url: / (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fa60226db90>: Failed to establish a new connection: [Errno 111] Connection refused'))
...
  Normal   Started    4m15s                kubelet            Started container tei
  Warning  Unhealthy  4m7s                 kubelet            Startup probe failed: Get "http://10.244.248.74:2081/health": dial tcp 10.244.248.74:2081: connect: connection refused
  Warning  Unhealthy  4s (x19 over 2m30s)  kubelet            Readiness probe failed: Get "http://10.244.248.74:2081/health": context deadline exceeded (Client.Timeout exceeded while awaiting headers)
...
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.328915Z  INFO text_embeddings_backend: backends/src/lib.rs:534: Downloading `model.onnx`
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.416779Z  WARN text_embeddings_backend: backends/src/lib.rs:538: Could not download `model.onnx`: request error: HTTP status client error (404 Not Found) for url (https://huggingface.co/BAAI/bge-base-en-v1.5/resolve/main/model.onnx)
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.416803Z  INFO text_embeddings_backend: backends/src/lib.rs:539: Downloading `onnx/model.onnx`
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.416862Z  INFO text_embeddings_backend: backends/src/lib.rs:548: Downloading `model.onnx_data`
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.508758Z  WARN text_embeddings_backend: backends/src/lib.rs:552: Could not download `model.onnx_data`: request error: HTTP status client error (404 Not Found) for url (https://huggingface.co/BAAI/bge-base-en-v1.5/resolve/main/model.onnx_data)
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.508785Z  INFO text_embeddings_backend: backends/src/lib.rs:553: Downloading `onnx/model.onnx_data`
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.592848Z  WARN text_embeddings_backend: backends/src/lib.rs:557: Could not download `onnx/model.onnx_data`: request error: HTTP status client error (404 Not Found) for url (https://huggingface.co/BAAI/bge-base-en-v1.5/resolve/main/onnx/model.onnx_data)
[pod/chatqna07084824-tei-fc5d44545-n9z9x/tei] 2025-07-07T08:48:45.592873Z  INFO text_embeddings_backend: backends/src/lib.rs:349: Model ONNX weights downloaded in 263.959007ms

@poussa poussa self-requested a review July 29, 2025 10:43
@poussa poussa merged commit d7b593e into opea-project:main Jul 29, 2025
45 of 55 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[ci-auto] GenAIExample ChatQnA,DocIndexRetriever,SearchQnA compose.yaml got changed.

3 participants