Repository navigation
Conversation
![orca-security-eu[bot]](https://avatars.githubusercontent.com/in/276244?s=60&v=4){kind=small}
There was a problem hiding this comment.
Orca Security Scan Summary
| Status | Check | Issues by priority | |
|---|---|---|---|
 Passed |
Secrets |  0  0  0  0 |
View in Orca |
4 tasks
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## jose/rerank-decide-client #2204 +/- ##
============================================================
Coverage ? 88.73%
============================================================
Files ? 310
Lines ? 24817
Branches ? 0
============================================================
Hits ? 22022
Misses ? 2795
Partials ? 0 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
jfrancoa
force-pushed
the
jose/decisions-images-client
branch
2 times, most recently
from
October 14, 2026 11:22
443e434 to
d7d329f
Compare
jfrancoa
changed the title
jfrancoa
force-pushed
the
jose/decisions-images-client
branch
from
October 14, 2026 12:47
d7d329f to
c0aa4f3
Compare
Contributor
There was a problem hiding this comment.
🟢 Approval recommended
The documentation matches the server behavior, and the integration test covers the relevant client paths.
0 open findings
What changed in this PR
Updates client documentation and integration coverage for decisions over image blobs.
Changes:
- Documents blob-image support for decision questions and reranking.
- Adds integration coverage for blob decisions and refusal behavior.
| File | Description |
|---|---|
weaviate/collections/classes/grpc.py |
Clarifies image-capable property support. |
integration/test_collection_decisions.py |
Tests decisions and reranking on blobs. |
🧠 Review effort: Balanced
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
jfrancoa
force-pushed
the
jose/decisions-images-client
branch
from
October 14, 2026 13:14
c0aa4f3 to
d45473d
Compare
jfrancoa
force-pushed
the
jose/decisions-images-client
branch
from
October 14, 2026 13:46
d45473d to
7264a36
Compare
4 tasks
The decisions-typesafeai module judges blob properties as images when the collection opts in (weaviate/weaviate: the images class setting). Off by default: image input is an experimental feature of the TypeSafe AI API.
This branch has not been deployed
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
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.
What
decisions-openaijudges images on the server (weaviate/weaviate#13534): a question ofdecide=or arerank=Rerank.decide(...)about ablobproperty sends the image to the Decisions API. The client needs no code change:Decision.predicate/choice/score(prop=...)andRerank.decide(prop=...)take the blob property as they take a text one. This PR updates the docstrings, addsConfigure.Decisions.typesafeai(images=True), the opt-in fordecisions-typesafeaito judge blob properties as images (weaviate/weaviate#13543; image input is an experimental feature of the TypeSafe AI API, off by default), and adds an integration test ondecisions-dummy, which judges a blob as the text of its base64 (a probability of 0 for an object with a photo, a refusal for an object without one).Stacked on #2198.