Release v0.2.34#153
Merged
Merged
Conversation
…o Makefile - Add LLM_MODEL parameter to override the model ID via command line - Auto-derive Helm key from LLM_MODEL when LLM=remote-llm (reserved key in llama-stack chart that skips model registration) - Add INTERACTIVE flag (default: true) to skip interactive prompts for HF_TOKEN and TAVILY_API_KEY when set to false - Update README with remote LLM deployment example and parameter docs Co-authored-by: Cursor <cursoragent@cursor.com>
Remove the LLM_MODEL parameter and MODEL_KEY auto-derivation logic in favor of using the LLM key directly. Update help text to add Option 3 for remote LLM deployment with LLM_URL and LLM_API_TOKEN. Co-authored-by: Cursor <cursoragent@cursor.com>
- add framework to run conversations against RAG quickstart
UI and capture the user request, agent response along
with the RAG results shown in the UI
- add framework to evaluate captured conversation using
deep_eval to evaluate the response given "expected"
RAG results and to evaluate the actual RAG chunks against
the expected answer and the "expected" RAG results
- add initial set of conversations for the hr and legal
databases using the questions suggested in the UI
- see evaluations/README.md on how to setup and run
Signed-off-by: Michael Dawson <midawson@redhat.com>
…o Makefile - Add LLM_MODEL parameter to override the model ID via command line - Auto-derive Helm key from LLM_MODEL when LLM=remote-llm (reserved key in llama-stack chart that skips model registration) - Add INTERACTIVE flag (default: true) to skip interactive prompts for HF_TOKEN and TAVILY_API_KEY when set to false - Update README with remote LLM deployment example and parameter docs Co-authored-by: Cursor <cursoragent@cursor.com>
Remove the LLM_MODEL parameter and MODEL_KEY auto-derivation logic in favor of using the LLM key directly. Update help text to add Option 3 for remote LLM deployment with LLM_URL and LLM_API_TOKEN. Co-authored-by: Cursor <cursoragent@cursor.com>
Bump llama-stack chart and Python package versions, update local deploy VERSION, and tighten agent error logging for failed response creation. Made-with: Cursor
Add an Argo CD Application manifest for deploying deploy/helm/rag with parameterized namespace and remote LLM/API secret Helm values, and adjust agent request token handling. Made-with: Cursor
Replace the standalone application manifest with a bootstrap ApplicationSet template that centralizes Helm values, remote LLM parameters, and per-user namespace composition using rag prefix and guid. Made-with: Cursor
…e-mode feat: add remote LLM command-line support, and INTERACTIVE flag
Restructure bootstrap values to mirror the RAG chart schema and render them directly through ApplicationSet Helm values without per-field remapping. Made-with: Cursor
Set bootstrap remotellm.enabled to false so remote endpoint configuration is opt-in by default. Made-with: Cursor
refactor: align bootstrap values with RAG chart
Relocate the bootstrap chart files from deploy/bootstrap to deploy/helm/bootstrap while preserving the ApplicationSet and values structure used to configure the RAG Helm deployment. Made-with: Cursor
Configure ApplicationSet sync options to create destination namespaces automatically and explicitly disable llm-service in bootstrap values to avoid unsupported ServingRuntime resources. Made-with: Cursor
Add configurable GitOps namespace settings and provision ClusterRole/ClusterRoleBinding resources from the bootstrap chart so the Argo CD application controller can create target namespaces and reconcile RAG resources. Made-with: Cursor
…eploy-helm refactor: move bootstrap chart under deploy/helm
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Release v0.2.34
This PR merges changes from
devtomainfor release v0.2.34.Checklist
After merging, this will automatically: