docs: sync Haystack API reference on Docusaurus (#13147)

Co-authored-by: sjrl <[email protected]>

docs-website/reference/haystack-api/query_api.md

@@ -58,7 +58,8 @@ Initialize the QueryExpander component.
 **Parameters:**
 
 - **chat_generator** (<code>ChatGenerator | None</code>) – The chat generator component to use for query expansion.
-  If None, a default OpenAIChatGenerator with gpt-4.1-mini model is used.
+  If None, a default `OpenAIResponsesChatGenerator` with the gpt-4.1-mini model and `store` set to `False`
+  is used.
 - **prompt_template** (<code>str | None</code>) – Custom [PromptBuilder](https://docs.haystack.deepset.ai/docs/promptbuilder)
   template for query expansion. The template should instruct the LLM to return a JSON response with the
   structure: `{"queries": ["query1", "query2", "query3"]}`. The template should include 'query' and

docs-website/reference/haystack-api/rankers_api.md

@@ -82,8 +82,8 @@ Initialize the LLMRanker component.
 
 **Parameters:**
 
-- **chat_generator** (<code>ChatGenerator | None</code>) – The chat generator to use for reranking. If `None`, a default `OpenAIChatGenerator` configured for JSON
-  output is used.
+- **chat_generator** (<code>ChatGenerator | None</code>) – The chat generator to use for reranking. If `None`, a default `OpenAIResponsesChatGenerator` configured for
+  JSON output and with `store` set to `False` is used.
 - **prompt** (<code>str</code>) – Custom prompt template for reranking. The prompt must include exactly the variables `query` and
   `documents` and instruct the LLM to return ranked 1-based document indices as JSON.
 - **top_k** (<code>int</code>) – The maximum number of ranked documents to return. Not applied when the ranker falls back to the input