Skip to content

chore(upgrade): upgrade configure pipelines to enable disable managed pipelines. and fix image used in llamastack#189

Merged
sauagarwa merged 3 commits into
devfrom
rj_fix_rag_llamastack_version
Jun 9, 2026
Merged

chore(upgrade): upgrade configure pipelines to enable disable managed pipelines. and fix image used in llamastack#189
sauagarwa merged 3 commits into
devfrom
rj_fix_rag_llamastack_version

Conversation

@johnson2500

Copy link
Copy Markdown
Collaborator
  • add volume mounts for new image paths
    volumeMounts:
    • mountPath: /app-config
      name: run-config-volume
    • mountPath: /opt/app-root/src/.llama
      name: dot-llama
    • mountPath: /opt/app-root/src/.cache
      name: cache
  • enable PGvector for vector store to prevent errors.
  • added managed pipelines fix for backaward compatability with 3.4 an non 3.4 versions.

@johnson2500 johnson2500 force-pushed the rj_fix_rag_llamastack_version branch from ef527b7 to 7183aa1 Compare June 9, 2026 19:39
@johnson2500 johnson2500 changed the base branch from main to dev June 9, 2026 19:40
secret:
hf_token: ""
enabled: true
models:

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

the model should be added under global.models, the enabled flag should be set to false. Change the model id as llama-3-2-1b-instruct-cpu so that it does not conflict with the gpu one

@sauagarwa sauagarwa merged commit 99fa3d3 into dev Jun 9, 2026
7 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.

2 participants