Skip to content

Update example config with citation annotation #1314

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.

Sign up for GitHub

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

Merged
tisnik merged 1 commit into from
Mar 12, 2026
Merged

Update example config with citation annotation #1314

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions examples/run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,6 +163,12 @@ registered_resources:
- toolgroup_id: builtin::rag # Register the RAG tool
provider_id: rag-runtime
vector_stores:
annotation_prompt_params: # Override the default Llama Stack annotation that adds <| file-xyz |> to responses
enable_annotations: true
annotation_instruction_template: >
When appropriate, cite sources at the end of sentences using doc_url and doc_title format.
Citing sources is not always required because citations are handled externally.
Never include any citation that is in the form '<| file-id |>'.
Comment on lines +166 to +171

@coderabbitai coderabbitai Bot Mar 12, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🔴 Critical

This example config is invalid unless the schema grows with it.

src/configuration.py:95 loads YAML via Configuration(**config_dict), and src/models/config.py:38-41 sets extra="forbid". With that combination, this new vector_stores.annotation_prompt_params block will be rejected during config parsing unless the corresponding Pydantic model fields are added first. As written, the example can cause startup/config-load failure instead of documenting a supported option. Please either wire these fields into the config models in the same PR or remove them from the example until that support exists.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@examples/run.yaml` around lines 166 - 171, The example adds
vector_stores.annotation_prompt_params which will be rejected by
Configuration(**config_dict) because src/models/config.py sets extra="forbid";
either remove that block from examples/run.yaml or add corresponding fields to
the Pydantic model used for vector stores (e.g., extend the
VectorStore/VectorStoreConfig model in src/models/config.py with an optional
annotation_prompt_params field and its subfields like enable_annotations: bool
and annotation_instruction_template: str), update imports/typing, and run tests
to ensure Configuration(**config_dict) accepts the new keys.

default_provider_id: faiss
default_embedding_model: # Define the default embedding model for RAG
provider_id: sentence-transformers
Expand Down
Loading