feat(decisions): Configure.Decisions.openai for the decisions-openai module

[jfrancoa]

What

Configure.Decisions.openai(...) and Reconfigure.Decisions.openai(...) for the decisions-openai module (server: weaviate/weaviate#13409, weaviate/weaviate#13485), with the question setting (relevance or statement for a plain rerank), min_probability and order as rerank defaults, model, base_url and max_documents.

from weaviate.classes.config import Configure, DecisionsQuestion, DecisionsOrder

client.collections.create(
    "Tickets",
    decisions_config=Configure.Decisions.openai(
        question=DecisionsQuestion.STATEMENT,
        min_probability=0.6,
        order=DecisionsOrder.SEARCH,
    ),
)

decide= works as with decisions-typesafeai (#2188).

Tests

Unit: serialisation, update within the decisions kind, read-back. Integration (integration/test_collection_decisions_openai.py): against the API; needs OPENAI_APIKEY and the module on the server, skips otherwise.

Stacked on #2188.

[orca-security-eu]

Orca Security Scan Summary

Status	Check	Issues by priority
Passed	Secrets	0   0   0   0	View in Orca

[codecov-commenter]

Codecov Report

❌ Patch coverage is 53.73134% with 31 lines in your changes missing coverage. Please review.
✅ Project coverage is 88.81%. Comparing base (f1a6600) to head (941bd58).

Files with missing lines	Patch %	Lines
integration/test_collection_decisions_openai.py	22.50%	31 Missing ⚠️

Additional details and impacted files

@@                      Coverage Diff                      @@
##           jose/decisions-typesafeai    #2189      +/-   ##
=============================================================
- Coverage                      88.95%   88.81%   -0.14%     
=============================================================
  Files                            310      310              
  Lines                          24692    24695       +3     
=============================================================
- Hits                           21965    21934      -31     
- Misses                          2727     2761      +34     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.