Fix Azure Openai function calling in streaming mode (#13768)

- **Description**: This PR addresses an issue with the OpenAI API
streaming response, where initially the key (arguments) is provided but
the value is None. Subsequently, it updates with {"arguments": "{\n"},
leading to a type inconsistency that causes an exception. The specific
error encountered is ValueError: additional_kwargs["arguments"] already
exists in this message, but with a different type. This change aims to
resolve this inconsistency and ensure smooth API interactions.
- **Issue**: None.
- **Dependencies**: None.
- **Tag maintainer**: @eyurtsev

This is an updated version of #13229 based on the refactored code.
Credit goes to @superken01.

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
pull/14204/head
Hendrik Hogertz 10 months ago committed by GitHub
parent e204657b3c
commit e6862e6e7d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -71,7 +71,17 @@ class BaseMessageChunk(BaseMessage):
def _merge_kwargs_dict(
self, left: Dict[str, Any], right: Dict[str, Any]
) -> Dict[str, Any]:
"""Merge additional_kwargs from another BaseMessageChunk into this one."""
"""Merge additional_kwargs from another BaseMessageChunk into this one,
handling specific scenarios where a key exists in both dictionaries
but has a value of None in 'left'. In such cases, the method uses the
value from 'right' for that key in the merged dictionary.
Example:
If left = {"function_call": {"arguments": None}} and
right = {"function_call": {"arguments": "{\n"}}
then, after merging, for the key "function_call",
the value from 'right' is used,
resulting in merged = {"function_call": {"arguments": "{\n"}}.
"""
merged = left.copy()
for k, v in right.items():
if k not in merged:

@ -42,6 +42,9 @@ def test_message_chunks() -> None:
AIMessageChunk(
content="", additional_kwargs={"function_call": {"name": "web_search"}}
)
+ AIMessageChunk(
content="", additional_kwargs={"function_call": {"arguments": None}}
)
+ AIMessageChunk(
content="", additional_kwargs={"function_call": {"arguments": "{\n"}}
)

Loading…
Cancel
Save