Skip to content

feat(openai): add openai unit test for streaming error in _generate #33134

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
Open

feat(openai): add openai unit test for streaming error in _generate #33134

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8ea8ae4
test(openai): add openai unit test for streaming error in _generate m…
Ali-Ismail-1 Sep 27, 2025
db1fa21
Merge branch 'master' into feat/openai-llm-generate-unit-tests
Ali-Ismail-1 Sep 30, 2025
d447108
test: pr-title-labler.yml not found in github ci tests. Add # to test…
Ali-Ismail-1 Sep 30, 2025
a4720ec
Merge branch 'master' into feat/openai-llm-generate-unit-tests
Ali-Ismail-1 Sep 30, 2025
c7f3d08
Merge branch 'feat/openai-llm-generate-unit-tests' of https://github.…
Ali-Ismail-1 Sep 30, 2025
3bab7cf
revert hashtag for testing
Ali-Ismail-1 Sep 30, 2025
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
10 changes: 10 additions & 0 deletions libs/partners/openai/tests/unit_tests/llms/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,3 +108,13 @@ def test_stream_response_to_generation_chunk() -> None:
assert chunk == GenerationChunk(
text="", generation_info={"finish_reason": None, "logprobs": None}
)


def test_generate_streaming_multiple_prompts_error() -> None:
"""Ensures ValueError when streaming=True and multiple prompts."""
llm = OpenAI(streaming=True)

with pytest.raises(
ValueError, match="Cannot stream results with multiple prompts\\."
):
llm._generate(["foo", "bar"])
Loading