Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions langfuse/openai.py
Original file line number Diff line number Diff line change
Expand Up @@ -755,7 +755,7 @@ def _extract_streamed_openai_response(resource: Any, chunks: Any) -> Any:
if chunk_usage is not None:
usage = chunk_usage

choices = chunk.get("choices", [])
choices = chunk.get("choices") or []

for choice in choices:
if _is_openai_v1():
Expand Down Expand Up @@ -898,7 +898,7 @@ def _get_langfuse_data_from_default_response(
completion = None

if resource.type == "completion":
choices = response.get("choices", [])
choices = response.get("choices") or []
if len(choices) > 0:
choice = choices[-1]

Expand All @@ -908,7 +908,7 @@ def _get_langfuse_data_from_default_response(
completion = _extract_response_api_completion(response.get("output", {}))

elif resource.type == "chat":
choices = response.get("choices", [])
choices = response.get("choices") or []
if len(choices) > 0:
# If multiple choices were generated, we'll show all of them in the UI as a list.
if len(choices) > 1:
Expand All @@ -927,7 +927,7 @@ def _get_langfuse_data_from_default_response(
)

elif resource.type == "embedding":
data = response.get("data", [])
data = response.get("data") or []
if len(data) > 0:
first_embedding = data[0]
embedding_vector = (
Expand Down
63 changes: 63 additions & 0 deletions tests/unit/test_openai.py
Original file line number Diff line number Diff line change
Expand Up @@ -311,6 +311,69 @@ def test_chat_completion_exports_generation_span(
}


def test_chat_completion_with_none_choices_does_not_crash(
langfuse_memory_client, get_span, json_attr
):
openai_client = lf_openai.OpenAI(api_key="test")
response = SimpleNamespace(
model="gpt-4o-mini",
choices=None,
usage=SimpleNamespace(prompt_tokens=3, completion_tokens=1, total_tokens=4),
)

with patch.object(openai_client.chat.completions, "_post", return_value=response):
result = openai_client.chat.completions.create(
name="unit-openai-chat-none-choices",
model="gpt-4o-mini",
messages=[{"role": "user", "content": "1 + 1 = ?"}],
)

assert result is response

langfuse_memory_client.flush()
span = get_span("unit-openai-chat-none-choices")

assert LangfuseOtelSpanAttributes.OBSERVATION_LEVEL not in span.attributes
assert (
span.attributes[LangfuseOtelSpanAttributes.OBSERVATION_MODEL] == "gpt-4o-mini"
)
assert json_attr(span, LangfuseOtelSpanAttributes.OBSERVATION_USAGE_DETAILS) == {
"prompt_tokens": 3,
"completion_tokens": 1,
"total_tokens": 4,
}


def test_openai_stream_with_none_choices_chunk_does_not_crash(
langfuse_memory_client, get_span
):
openai_client = lf_openai.OpenAI(api_key="test")
chunks_with_none_choices = [
SimpleNamespace(model="gpt-4o-mini", choices=None, usage=None),
*_make_chat_stream_chunks(),
]
raw_stream = DummyOpenAIStream(chunks_with_none_choices, DummySyncResponse())

with patch.object(openai_client.chat.completions, "_post", return_value=raw_stream):
stream = openai_client.chat.completions.create(
name="unit-openai-stream-none-choices",
model="gpt-4o-mini",
messages=[{"role": "user", "content": "1 + 1 = ?"}],
stream=True,
)

chunks = list(stream)
stream.close()

assert len(chunks) == 3

langfuse_memory_client.flush()
span = get_span("unit-openai-stream-none-choices")

assert span.attributes[LangfuseOtelSpanAttributes.OBSERVATION_OUTPUT] == "2"
assert span.attributes["langfuse.observation.metadata.finish_reason"] == "stop"


def test_streaming_chat_completion_preserves_tool_calls_after_content():
model, completion, usage, metadata = (
lf_openai_module._extract_streamed_openai_response(
Expand Down