fix(vector_io): align Protocol signatures with request models #4747
+1,004
−672
Conversation
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
skamenan7
requested review from
ashwinb,
bbrowning,
cdoern,
ehhuang,
franciscojavierarceo,
leseb,
mattf and
raghotham
as code owners
meta-cla
bot
added
the
CLA Signed
skamenan7
force-pushed
the
fix/4717-Protocol-VectorIO
branch
2 times, most recently
from
dd2d6a4 to
6c23e0d
Compare
franciscojavierarceo
requested changes
Jan 27, 2026
Collaborator
franciscojavierarceo
left a comment
franciscojavierarceo
left a comment
There was a problem hiding this comment.
nice! this looks like the right direction, we should hold though until @alinaryan finishes this PR:
skamenan7
force-pushed
the
fix/4717-Protocol-VectorIO
branch
from
6c23e0d to
c3226e0
Compare
skamenan7
force-pushed
the
fix/4717-Protocol-VectorIO
branch
2 times, most recently
from
88c958c to
c896df3
Compare
This change aligns the VectorIO Protocol methods with the DatasetIO pattern by introducing dedicated Request models for complex operations. - Moves request models to `llama_stack_api/vector_io/models.py`. - Updates `api.py` protocol signatures to use these models. - Updates `fastapi_routes.py` to use models for request bodies. - Updates `VectorIORouter` and routing tables to handle request objects. - Updates `OpenAIVectorStoreMixin` and all vector store providers to accept request objects. - Implements missing file batch methods in `OpenAIVectorStoreMixin`. - Updates unit tests to reflect the new signatures. This improves type safety and allows for easier future extension of method arguments.
Update the tool_executor.py to use the new request model pattern for openai_search_vector_store() calls. This aligns with the VectorIO Protocol refactoring in issue llamastack#4717. The method was previously called with flat parameters but the Protocol now expects an OpenAISearchVectorStoreRequest object.
…tion limits - Fix batch file_counts.failed not being incremented during file batch processing. Failed files are now properly counted alongside completed. - Add pagination limit constraints (ge=1, le=100) to list endpoints for OpenAI API compatibility: openai_list_vector_stores, openai_list_files_in_vector_store, openai_list_files_in_vector_store_file_batch.
skamenan7
force-pushed
the
fix/4717-Protocol-VectorIO
branch
from
c896df3 to
916422a
Compare
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.
Summary
llama_stack_api/vector_io/models.pyOpenAIVectorStoreMixinto use request models throughoutTest plan
uv run pre-commit run --all-files -v)./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup ollama)Closes #4717
cc @leseb