From 66d1ed6099d6b5615eddbb79676edfafb357ff0f Mon Sep 17 00:00:00 2001
From: Jacob Lee <jacoblee93@gmail.com>
Date: Wed, 7 May 2025 07:57:37 -0700
Subject: [PATCH] fix(core): Permit OpenAI style blocks to be passed into
 convert_to_openai_messages (#31140)

Should effectively be a noop, just shouldn't throw

CC @madams0013

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
---
 libs/core/langchain_core/messages/utils.py     | 18 ++++++++++++++++++
 .../tests/unit_tests/messages/test_utils.py    | 16 +++++++++++++++-
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/libs/core/langchain_core/messages/utils.py b/libs/core/langchain_core/messages/utils.py
index d3e27c502a4..5b51f63c09d 100644
--- a/libs/core/langchain_core/messages/utils.py
+++ b/libs/core/langchain_core/messages/utils.py
@@ -1139,6 +1139,24 @@ def convert_to_openai_messages(
                             f"content block:\n\n{block}"
                         )
                         raise ValueError(err)
+                # OpenAI file format
+                elif (
+                    block.get("type") == "file"
+                    and isinstance(block.get("file"), dict)
+                    and isinstance(block.get("file", {}).get("file_data"), str)
+                ):
+                    if block.get("file", {}).get("filename") is None:
+                        logger.info("Generating a fallback filename.")
+                        block["file"]["filename"] = "LC_AUTOGENERATED"
+                    content.append(block)
+                # OpenAI audio format
+                elif (
+                    block.get("type") == "input_audio"
+                    and isinstance(block.get("input_audio"), dict)
+                    and isinstance(block.get("input_audio", {}).get("data"), str)
+                    and isinstance(block.get("input_audio", {}).get("format"), str)
+                ):
+                    content.append(block)
                 elif block.get("type") == "tool_use":
                     if missing := [
                         k for k in ("id", "name", "input") if k not in block
diff --git a/libs/core/tests/unit_tests/messages/test_utils.py b/libs/core/tests/unit_tests/messages/test_utils.py
index db75921e1a3..218f94dc2e8 100644
--- a/libs/core/tests/unit_tests/messages/test_utils.py
+++ b/libs/core/tests/unit_tests/messages/test_utils.py
@@ -1209,6 +1209,13 @@ def test_convert_to_openai_messages_multimodal() -> None:
                     "mime_type": "application/pdf",
                     "filename": "test.pdf",
                 },
+                {
+                    "type": "file",
+                    "file": {
+                        "filename": "draconomicon.pdf",
+                        "file_data": "data:application/pdf;base64,<base64 string>",
+                    },
+                },
                 {
                     "type": "file",
                     "source_type": "id",
@@ -1220,13 +1227,20 @@ def test_convert_to_openai_messages_multimodal() -> None:
                     "data": "<base64 string>",
                     "mime_type": "audio/wav",
                 },
+                {
+                    "type": "input_audio",
+                    "input_audio": {
+                        "data": "<base64 string>",
+                        "format": "wav",
+                    },
+                },
             ]
         )
     ]
     result = convert_to_openai_messages(messages, text_format="block")
     assert len(result) == 1
     message = result[0]
-    assert len(message["content"]) == 6
+    assert len(message["content"]) == 8
 
     # Test adding filename
     messages = [