-
Notifications
You must be signed in to change notification settings - Fork 200
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[k8s ChatQnA] retriever_deploy deployment failed due to "http://tei-embedding-svc.default.svc.cluster.local:6006/**" failed to access #313
Comments
Please add ".default.svc.cluster.local" to the no_proxy config too |
Thanks very much! It fixed this problem. I met with a new problem "Internal Server Error" when accessing the RAG service.: My GenAIExamples repo version is:
My GenAIComp version is
kubectl logs chaqna-xeon-backend-server-deploy-79cbbb7b-vb9lx You may be able to resolve this warning by setting |
please add those XXX_SERVICE_HOST_IP's values into no_proxy too, e.g. embedding-svc,retriever-svc, etc. |
Thanks! the solution works. |
…pea-project#313) Signed-off-by: Chendi.Xue <[email protected]>
…e for v0.9 (opea-project#538) * clip embedding support Signed-off-by: srinarayan-srikanthan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Signed-off-by: srinarayan-srikanthan <[email protected]> * test script for embedding Signed-off-by: srinarayan-srikanthan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Signed-off-by: srinarayan-srikanthan <[email protected]> * fix freeze workflow (opea-project#522) Signed-off-by: Sun, Xuehao <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * Fix Dataprep Potential Error in get_file (opea-project#540) * fix get file error & refine logs Signed-off-by: letonghan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: letonghan <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Signed-off-by: srinarayan-srikanthan <[email protected]> * Support SearchedDoc input type in LLM for No Rerank Pipeline (opea-project#541) Signed-off-by: letonghan <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * Add dependency for pdf2image and OCR processing (opea-project#421) Signed-off-by: srinarayan-srikanthan <[email protected]> * Add local_embedding return 768 length to align with chatqna example (opea-project#313) Signed-off-by: Chendi.Xue <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * add telemetry doc (opea-project#536) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Signed-off-by: srinarayan-srikanthan <[email protected]> * Add video-llama LVM microservice under lvms (opea-project#495) Signed-off-by: BaoHuiling <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Signed-off-by: srinarayan-srikanthan <[email protected]> * Fix the data load issue for structured files (opea-project#505) Signed-off-by: XuhuiRen <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * Add finetuning component (opea-project#502) Signed-off-by: Xinyu Ye <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: lkk <[email protected]> Co-authored-by: test <[email protected]> Co-authored-by: root <[email protected]> Co-authored-by: Letong Han <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * add torchvision into requirements (opea-project#546) Signed-off-by: chensuyue <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * Use Gaudi base images from Dockerhub (opea-project#526) * Use Gaudi base images from Dockerhub Signed-off-by: Abolfazl Shahbazi <[email protected]> * Fixing the malformed tag Signed-off-by: Abolfazl Shahbazi <[email protected]> * fix another malformed tag Signed-off-by: Abolfazl Shahbazi <[email protected]> --------- Signed-off-by: Abolfazl Shahbazi <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * Add toxicity detection microservice (opea-project#338) * Add toxicity detection microservice Signed-off-by: Qun Gao <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Modification to toxicity plugin PR (opea-project#432) * changed microservice to use Service.GUARDRAILS and input/output to TextDoc Signed-off-by: Tyler Wilbers <[email protected]> * simplify dockerfile to use langchain Signed-off-by: Tyler Wilbers <[email protected]> * sort requirements Signed-off-by: Tyler Wilbers <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Tyler Wilbers <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Minor SPDX header update (opea-project#434) Signed-off-by: Abolfazl Shahbazi <[email protected]> * Remove 'langsmith' per code review (opea-project#534) Signed-off-by: Abolfazl Shahbazi <[email protected]> * Add toxicity detection microservices with E2E testing Signed-off-by: Qun Gao <[email protected]> --------- Signed-off-by: Qun Gao <[email protected]> Signed-off-by: Tyler Wilbers <[email protected]> Signed-off-by: Abolfazl Shahbazi <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Abolfazl Shahbazi <[email protected]> Co-authored-by: Tyler W <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * rename script and use 5xxx Signed-off-by: BaoHuiling <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * add proxy for build Signed-off-by: BaoHuiling <[email protected]> Signed-off-by: srinarayan-srikanthan <[email protected]> * fixed commit issues Signed-off-by: srinarayan-srikanthan <[email protected]> * Fix docarray constraint Signed-off-by: srinarayan-srikanthan <[email protected]> * updated docarray Signed-off-by: srinarayan-srikanthan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Signed-off-by: srinarayan-srikanthan <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rm telemetry which cause error in mega Signed-off-by: BaoHuiling <[email protected]> * renamed dirs Signed-off-by: srinarayan-srikanthan <[email protected]> * renamed test Signed-off-by: srinarayan-srikanthan <[email protected]> --------- Signed-off-by: srinarayan-srikanthan <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Signed-off-by: letonghan <[email protected]> Signed-off-by: Chendi.Xue <[email protected]> Signed-off-by: BaoHuiling <[email protected]> Signed-off-by: XuhuiRen <[email protected]> Signed-off-by: Xinyu Ye <[email protected]> Signed-off-by: chensuyue <[email protected]> Signed-off-by: Abolfazl Shahbazi <[email protected]> Signed-off-by: Qun Gao <[email protected]> Signed-off-by: Tyler Wilbers <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sun, Xuehao <[email protected]> Co-authored-by: Letong Han <[email protected]> Co-authored-by: Zaili Wang <[email protected]> Co-authored-by: Chendi.Xue <[email protected]> Co-authored-by: Sihan Chen <[email protected]> Co-authored-by: Huiling Bao <[email protected]> Co-authored-by: XuhuiRen <[email protected]> Co-authored-by: XinyuYe-Intel <[email protected]> Co-authored-by: lkk <[email protected]> Co-authored-by: test <[email protected]> Co-authored-by: root <[email protected]> Co-authored-by: chen, suyue <[email protected]> Co-authored-by: Abolfazl Shahbazi <[email protected]> Co-authored-by: qgao007 <[email protected]> Co-authored-by: Tyler W <[email protected]>
Dear experts:
I followed these steps to run k8s chatQnA example.
https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker/xeon/README.md
https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/kubernetes/manifests/README.md
retriever-deploy deployment shows " requests.exceptions.HTTPError: 504 Server Error: Gateway Timeout for url: http://tei-embedding-svc.default.svc.cluster.local:6006/"
I have added proxy config below in "qna_configmap_xeon.yaml" and made sure tei-embedding, tei-reranking, tgi-service successfully downloaded 3 models.
http_proxy: http://proxy.xxx.xxxxx.com:xxx
https_proxy: http://proxy.xxx.xxxxx.com:xxx
no_proxy: 10.0.0.0/8,192.168.0.0/16,127.0.0.1,localhost,xxxxx.com
I suspect network or proxy config relevant issue. any suggestions are appreciated.
Below are logs.
NAMESPACE NAME READY STATUS RESTARTS AGE
default chaqna-xeon-backend-server-deploy-79cbbb7b-4q9t6 1/1 Running 0 58m
default embedding-deploy-7bb6df68f5-4k8kr 1/1 Running 0 58m
default llm-deploy-5c85678ddd-sjbsn 1/1 Running 0 58m
default redis-vector-db-6db798f98d-56vqz 1/1 Running 0 58m
default reranking-deploy-87c5bf6cd-r4cph 1/1 Running 0 58m
default retriever-deploy-6bb494f5bd-9ggnd 0/1 CrashLoopBackOff 14 ( ago) 58m
default tei-embedding-service-deploy-78fbbcbf67-xvx9v 1/1 Running 0 58m
default tei-reranking-service-deploy-6cdb544d49-fmfj8 1/1 Running 0 58m
default tgi-service-deploy-78f488ff9f-tlmg8 1/1 Running 0 58m
kubectl get svc -o wide
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE SELECTOR
chaqna-xeon-backend-server-svc NodePort 10.103.16.9 8888:32441/TCP 69m app=chaqna-xeon-backend-server-deploy
embedding-svc ClusterIP 10.104.135.74 6000/TCP 69m app=embedding-deploy
kubernetes ClusterIP 10.96.0.1 443/TCP 6d
llm-svc ClusterIP 10.104.216.23 9000/TCP 69m app=llm-deploy
redis-vector-db ClusterIP 10.103.250.80 6379/TCP,8001/TCP 69m app=redis-vector-db
reranking-svc ClusterIP 10.103.2.220 8000/TCP 69m app=reranking-deploy
retriever-svc ClusterIP 10.110.168.101 7000/TCP 69m app=retriever-deploy
tei-embedding-svc ClusterIP 10.103.168.217 6006/TCP 69m app=tei-embedding-service-deploy
tei-reranking-svc ClusterIP 10.107.35.174 8808/TCP 69m app=tei-reranking-service-deploy
tgi-svc ClusterIP 10.104.172.25 9009/TCP 69m app=tgi-service-deploy
kubectl logs retriever-deploy-6bb494f5bd-9ggnd
Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU.
Downloading detection model, please wait. This may take several minutes depending upon your network connection.
Parsing 10k filing doc for NIKE data/nke-10k-2023.pdf
Progress: |███████████████████████████████▒Downloading recognition model, please wait. This may take several minutes depending upon your network connection.
Progress: |██████████████████████████████████████████████████| 100.0% CompleteDone preprocessing. Created 270 chunks of the original pdf
Traceback (most recent call last):
File "/home/user/.local/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 304, in hf_raise_for_status
response.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 504 Server Error: Gateway Timeout for url: http://tei-embedding-svc.default.svc.cluster.local:6006/
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/user/comps/retrievers/langchain/redis/ingest.py", line 99, in
ingest_documents()
File "/home/user/comps/retrievers/langchain/redis/ingest.py", line 88, in ingest_documents
_ = Redis.from_texts(
^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/langchain_community/vectorstores/redis/base.py", line 485, in from_texts
instance, _ = cls.from_texts_return_keys(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/langchain_community/vectorstores/redis/base.py", line 418, in from_texts_return_keys
keys = instance.add_texts(texts, metadatas, keys=keys)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/langchain_community/vectorstores/redis/base.py", line 705, in add_texts
embeddings = embeddings or self._embeddings.embed_documents(list(texts))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/langchain_community/embeddings/huggingface_hub.py", line 95, in embed_documents
responses = self.client.post(
^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/huggingface_hub/inference/_client.py", line 273, in post
hf_raise_for_status(response)
File "/home/user/.local/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 371, in hf_raise_for_status
raise HfHubHTTPError(str(e), response=response) from e
huggingface_hub.utils._errors.HfHubHTTPError: 504 Server Error: Gateway Timeout for url: http://tei-embedding-svc.default.svc.cluster.local:6006/
/usr/local/lib/python3.11/site-packages/pydantic/_internal/fields.py:149: UserWarning: Field "model_name_or_path" has conflict with protected namespace "model".
You may be able to resolve this warning by setting
model_config['protected_namespaces'] = ()
.warnings.warn(
[2024-06-24 05:15:52,520] [ INFO] - CORS is enabled.
[2024-06-24 05:15:52,521] [ INFO] - Setting up HTTP server
[2024-06-24 05:15:52,521] [ INFO] - Uvicorn server setup on port 7000
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:7000 (Press CTRL+C to quit)
[2024-06-24 05:15:52,533] [ INFO] - HTTP server setup successful
Traceback (most recent call last):
File "/home/user/comps/retrievers/langchain/redis/retriever_redis.py", line 71, in
vector_db = Redis.from_existing_index(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/langchain_community/vectorstores/redis/base.py", line 562, in from_existing_index
raise ValueError(
ValueError: Redis failed to connect: Index rag-redis does not exist.
The text was updated successfully, but these errors were encountered: