fix(python): replace the retired gpt-4-turbo-preview default in OpenaiReranker (#4613)

OpenAI shuts down `gpt-4-turbo` and its snapshots on 2026-10-23
(https://developers.openai.com/api/docs/deprecations), so
`OpenaiReranker` fails for every user who relies on the default
`gpt-4-turbo-preview` after that date.

This changes the default to `gpt-5.6-sol`, the replacement OpenAI names
for `gpt-4-turbo` on that page, in the class, its docstring and the
integration docs page. `_rerank` also stops sending `temperature=0`: the
GPT-5 models only accept the default temperature, so keeping it would
fail the new default on its first call. The reranker still asks for
`json_object` output and the rest of the request is unchanged.

The new test calls `_rerank` with a mocked client and checks that no
`temperature` is sent. It fails on main and passes with the change. No
request was made to OpenAI.

This change was made with Claude Code.

Co-authored-by: Xuanwo <github@xuanwo.io>

docs/web/integrations/reranking/openai.mdx

@@ -26,7 +26,7 @@ credentials from environment variables or a secrets manager.
 ## Accepted Arguments {#accepted-arguments}
 | Argument | Type | Default | Description |
 | --- | --- | --- | --- |
-| `model_name` | `str` | `"gpt-4-turbo-preview"` | The name of the reranker model to use.|
+| `model_name` | `str` | `"gpt-5.6-sol"` | The name of the reranker model to use.|
 | `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
 | `return_score` | `str` | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type. |
 | `api_key` | `str` | `None` | The API key to use. If None, will use the OPENAI_API_KEY environment variable.

python/python/lancedb/rerankers/openai.py

@@ -21,7 +21,7 @@ class OpenaiReranker(Reranker):
 
     Parameters
     ----------
-    model_name : str, default "gpt-4-turbo-preview"
+    model_name : str, default "gpt-5.6-sol"
         The name of the cross encoder model to use.
     column : str, default "text"
         The name of the column to use as input to the cross encoder model.
@@ -33,7 +33,7 @@ class OpenaiReranker(Reranker):
 
     def __init__(
         self,
-        model_name: str = "gpt-4-turbo-preview",
+        model_name: str = "gpt-5.6-sol",
         column: str = "text",
         return_score="relevance",
         api_key: Optional[str] = None,
@@ -54,7 +54,6 @@ class OpenaiReranker(Reranker):
         response = self._client.chat.completions.create(
             model=self.model_name,
             response_format={"type": "json_object"},
-            temperature=0,
             messages=[
                 {
                     "role": "system",

python/python/tests/test_rerankers.py

@@ -2,6 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import os
+from unittest.mock import MagicMock
 import random
 
 import lancedb
@@ -547,6 +548,24 @@ def test_openai_reranker(tmp_path):
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
+def test_openai_reranker_does_not_send_temperature():
+    reranker = OpenaiReranker(api_key="test-key")
+    create = MagicMock()
+    create.return_value.choices = [
+        MagicMock(
+            message=MagicMock(
+                content='{"documents": [{"content": "a", "relevance_score": 0.5}]}'
+            )
+        )
+    ]
+    reranker.__dict__["_client"] = MagicMock()
+    reranker.__dict__["_client"].chat.completions.create = create
+
+    reranker._rerank(pa.table({"text": ["a"]}), "query")
+
+    assert "temperature" not in create.call_args.kwargs
+
+
 @pytest.mark.skipif(
     os.environ.get("JINA_API_KEY") is None, reason="JINA_API_KEY not set"
 )