Skip to content

feat(ai): Integrate AI container deployment in Intel chart#93

Merged
danc094codetogether merged 3 commits intodevfrom
AI-Model-Container
Mar 11, 2025
Merged

feat(ai): Integrate AI container deployment in Intel chart#93
danc094codetogether merged 3 commits intodevfrom
AI-Model-Container

Conversation

@danc094codetogether
Copy link
Contributor

Added support for AI container deployment with bundled and external modes. Configured Helm values to allow users to specify AI providers (OpenAI or custom). Implemented environment variable injection for AI-related configurations. Ensured compatibility with existing Intel deployment. Fixed potential issues with missing secrets and resource allocation.
#3950

Added support for AI container deployment with bundled and external modes.
Configured Helm values to allow users to specify AI providers (OpenAI or custom).
Implemented environment variable injection for AI-related configurations.
Ensured compatibility with existing Intel deployment.
Fixed potential issues with missing secrets and resource allocation.
Copy link
Member

@nmorenor nmorenor left a comment

Choose a reason for hiding this comment

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

just need to define how ai keys will be consumed by spring backend.

- Included instructions for securely storing AI API keys using Kubernetes secrets.
- Provided a command to create the `ai-secrets` secret for OpenAI and external AI providers.
- Ensured secure key management by referencing secrets instead of storing keys in `values.yaml`.
@danc094codetogether danc094codetogether marked this pull request as ready for review March 5, 2025 01:21
Copy link
Contributor

@patrick-codetogether patrick-codetogether left a comment

Choose a reason for hiding this comment

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

lgtm, thanks for the secret changes

- Integrated a **NON-OpenAI** bundled model using **Ollama**.
- Added support for **Qwen2.5 Coder 3B** from LM Studio.
- Updated **Dockerfile.ai** to dynamically pull models via `MODELS` build argument.
- Modified **deployment.yaml** to pass `AI_BUNDLED_URL` dynamically from Helm.
- Updated **values.yaml** to configure `ai.bundled_url` automatically.
- Ensured **external AI mode** is handled via product portal (not Helm).
- Verified deployment stability and resource usage.

**Successfully tested bundled AI mode with Qwen2.5 Coder 3B.**
@danc094codetogether danc094codetogether merged commit 487acb1 into dev Mar 11, 2025
1 check failed
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.

3 participants