Release: v0.32.O.rc0

Author: hanouticelina

docs/source/en/guides/inference.md

@@ -452,6 +452,9 @@ The [`MCPClient`] connects to MCP servers (either local `stdio` scripts or remot
 In the following example, we use [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) model via [Nebius](https://nebius.com/) inference provider. We then add a remote MCP server, in this case, an SSE server which made the Flux image generation tool available to the LLM.
 
 ```python
+# install the latest `huggingface_hub` version with the `mcp` extra.
+# pip install -U huggingface_hub[mcp]
+
 import os
 
 from huggingface_hub import ChatCompletionInputMessage, ChatCompletionStreamOutput, MCPClient

src/huggingface_hub/__init__.py

@@ -46,7 +46,7 @@
 from typing import TYPE_CHECKING
 
 
-__version__ = "0.31.0.dev0"
+__version__ = "0.32.O.rc0"
 
 # Alphabetical order of definitions is ensured in tests
 # WARNING: any comment added in this dictionary definition will be lost when