-
Notifications
You must be signed in to change notification settings - Fork 1.2k
gpu: AMD64 NVIDIA GPU CI/CD Part 2 #11658
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
Conversation
9463901
to
12f41bc
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR adds LangChain and embedding service integration to the NVIDIA GPU CI/CD pipeline, expanding the testing capabilities beyond just instruction models to include embedding models and RAG (Retrieval-Augmented Generation) functionality.
Key changes:
- Addition of embedding service pod configuration and deployment alongside the existing instruction model
- Integration of LangChain framework with NVIDIA AI endpoints for both chat and embedding functionality
- Implementation of a comprehensive RAG system using Kata Containers documentation as the knowledge base
Comments suppressed due to low confidence (4)
tests/integration/kubernetes/k8s-nvidia-nim.bats:119
- The langchain version 0.2.5 may not exist. LangChain typically uses semantic versioning with patch versions like 0.2.x where x is typically much higher or uses different versioning schemes. Verify this version exists in the package repository.
[[ "$(pip show langchain 2>/dev/null | awk '/^Version:/{print $2}')" = "0.2.5" ]] || pip install langchain==0.2.5
tests/integration/kubernetes/k8s-nvidia-nim.bats:120
- The langchain-nvidia-ai-endpoints version 0.1.2 may not exist. This is a relatively new package and version numbers should be verified against the actual PyPI repository.
[[ "$(pip show langchain-nvidia-ai-endpoints 2>/dev/null | awk '/^Version:/{print $2}')" = "0.1.2" ]] || pip install langchain-nvidia-ai-endpoints==0.1.2
tests/integration/kubernetes/k8s-nvidia-nim.bats:122
- The langchain-community version 0.2.5 may not exist. LangChain community packages typically follow different versioning patterns. Verify this version exists in the package repository.
[[ "$(pip show langchain-community 2>/dev/null | awk '/^Version:/{print $2}')" = "0.2.5" ]] || pip install langchain-community==0.2.5
tests/integration/kubernetes/k8s-nvidia-nim.bats:123
- The beautifulsoup4 version 4.13.4 may not exist. BeautifulSoup4 typically uses versions like 4.12.x. Verify this version exists in the package repository.
[[ "$(pip show beautifulsoup4 2>/dev/null | awk '/^Version:/{print $2}')" = "4.13.4" ]] || pip install beautifulsoup4==4.13.4
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm, thanks @zvonkok!
e94293f
to
4b8ecd1
Compare
@stevenhorsman Updated, now both "tests" are in setup_file :) |
For a simple RAG pipeline add a embeding service Signed-off-by: Zvonko Kaiser <zkaiser@nvidia.com>
4b8ecd1
to
8be41a4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM as long as the CI is green. Thanks for the updates!
Add langchain and embedding service