openai[patch]: ignore file blocks when counting tokens (#30601)

OpenAI does not appear to document how it transforms PDF pages to
images, which determines how tokens are counted:
https://platform.openai.com/docs/guides/pdf-files?api-mode=chat#usage-considerations

Currently these block types raise ValueError inside
`get_num_tokens_from_messages`. Here we update to generate a warning and
continue.

libs/partners/openai/langchain_openai/chat_models/base.py

@@ -1298,6 +1298,12 @@ class BaseChatOpenAI(BaseChatModel):
                                 encoding.encode(val["function"]["arguments"])
                             )
                             num_tokens += len(encoding.encode(val["function"]["name"]))
+                        elif val["type"] == "file":
+                            warnings.warn(
+                                "Token counts for file inputs are not supported. "
+                                "Ignoring file inputs."
+                            )
+                            pass
                         else:
                             raise ValueError(
                                 f"Unrecognized content block type\n\n{val}"