Open
Conversation
WalkthroughDocumentation adds optional PGVector-backed vector store support and detailed embedding model provisioning options (Hugging Face online/offline modes). Changes include env var examples for PGVector and HF, Kubernetes Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Client
participant Server
participant PGVectorDB as PostgreSQL (pgvector)
participant HF as Hugging Face
rect rgba(200,230,201,0.5)
User->>Client: Run quickstart / notebook (create/search)
Client->>Server: API request (create vector store / search)
end
rect rgba(187,222,251,0.5)
Server->>HF: Request embedding model / embeddings (HF_ENDPOINT or local cache)
HF-->>Server: Return embeddings
end
rect rgba(255,224,178,0.5)
Server->>PGVectorDB: Store vectors / Run hybrid search (pgvector)
PGVectorDB-->>Server: Return vector search results
end
Server-->>Client: Return search results
Client-->>User: Display results
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Warning There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure. 🔧 Ruff (0.15.11)docs/public/llama-stack/llama-stack_quickstart.ipynbUnexpected end of JSON input Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/public/llama-stack/llama-stack_quickstart.ipynb`:
- Around line 512-518: The code silently falls back to a hardcoded 768 when
determining embedding_dimension; instead, change the logic around
embedding_dimension (the block using
embedding_metadata.get("embedding_dimension") / get("dimensions") and
getattr(embedding_model, "embedding_dimension"/"dimensions")) to fail fast: if
none of those values exist, raise a clear error (e.g., ValueError) or log an
explicit warning and require the user to supply an explicit embedding_dimension
parameter; ensure the error message references the embedding_model and
embedding_metadata so users know to verify their model (e.g., mention common
dims like 384/1024/1536) and avoid creating the pgvector store with an incorrect
dimension.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 648bff00-c121-4c69-b176-58221b71c508
📒 Files selected for processing (4)
docs/en/llama_stack/install.mdxdocs/en/llama_stack/overview/features.mdxdocs/en/llama_stack/quickstart.mdxdocs/public/llama-stack/llama-stack_quickstart.ipynb
Deploying alauda-ai with
|
| Latest commit: |
c0d9a1b
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://f27b5259.alauda-ai.pages.dev |
| Branch Preview URL: | https://imp-llamastack-pgvector.alauda-ai.pages.dev |
There was a problem hiding this comment.
🧹 Nitpick comments (1)
docs/en/llama_stack/install.mdx (1)
148-182: Optional: consolidate HF configuration guidance.The Hugging Face setup is described in two places — the commented block inside the YAML (lines 90–104) and this standalone section — with partly overlapping content. Consider either (a) trimming the YAML comments to just cross-reference this section, or (b) removing the standalone section and keeping the YAML comments as the single source of truth. Not a blocker; purely a readability / maintenance nit.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/llama_stack/install.mdx` around lines 148 - 182, This file duplicates Hugging Face configuration guidance across the YAML comment block and the standalone "Hugging Face Access For Embedding Models" section; pick one canonical location and remove the duplicate: either trim the YAML comment block to a brief cross-reference that points to this standalone section, or delete this standalone section and expand the YAML comments to be the single source of truth. While editing, ensure the documented environment variables (HF_ENDPOINT, HF_HUB_CACHE, HF_HUB_OFFLINE, TRANSFORMERS_OFFLINE, HF_HUB_DISABLE_XET) and the recommended cache path (/home/lls/.lls/huggingface/hub) are preserved in the chosen location and update any internal links or comment markers so readers can find the full configuration in one place.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@docs/en/llama_stack/install.mdx`:
- Around line 148-182: This file duplicates Hugging Face configuration guidance
across the YAML comment block and the standalone "Hugging Face Access For
Embedding Models" section; pick one canonical location and remove the duplicate:
either trim the YAML comment block to a brief cross-reference that points to
this standalone section, or delete this standalone section and expand the YAML
comments to be the single source of truth. While editing, ensure the documented
environment variables (HF_ENDPOINT, HF_HUB_CACHE, HF_HUB_OFFLINE,
TRANSFORMERS_OFFLINE, HF_HUB_DISABLE_XET) and the recommended cache path
(/home/lls/.lls/huggingface/hub) are preserved in the chosen location and update
any internal links or comment markers so readers can find the full configuration
in one place.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: f29828f7-972d-4599-89ed-5a3ecdc0cfc2
📒 Files selected for processing (3)
docs/en/llama_stack/install.mdxdocs/en/llama_stack/quickstart.mdxdocs/public/llama-stack/llama-stack_quickstart.ipynb
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/en/llama_stack/quickstart.mdx
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
1 participant
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.
Summary by CodeRabbit