apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-26 08:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Feature/streaming llm phase 1 (#566)

Browse source 
* Tidy up duplicate tech specs in doc directory

* Streaming LLM text-completion service tech spec.

* text-completion and prompt interfaces

* streaming change applied to all LLMs, so far tested with VertexAI

* Skip Pinecone unit tests, upstream module issue is affecting things, tests are passing again

* Added agent streaming, not working and has broken tests
This commit is contained in:
cybermaggedon 2025-11-26 09:59:10 +00:00 • committed by GitHub
parent 943a9d83b0
commit 310a2deb06
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
44 changed files with 2684 additions and 937 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tests/integration/test_text_completion_integration.py
View file

@ -282,10 +282,11 @@ class TestTextCompletionIntegration:
# Assert
# Verify OpenAI API call parameters
call_args = mock_openai_client.chat.completions.create.call_args
assert call_args.kwargs['response_format'] == {"type": "text"}
assert call_args.kwargs['top_p'] == 1
assert call_args.kwargs['frequency_penalty'] == 0
assert call_args.kwargs['presence_penalty'] == 0
# Note: response_format, top_p, frequency_penalty, and presence_penalty
# were removed in #561 as unnecessary parameters
assert 'model' in call_args.kwargs
assert 'temperature' in call_args.kwargs
assert 'max_tokens' in call_args.kwargs
# Verify result structure
assert hasattr(result, 'text')
@ -362,9 +363,8 @@ class TestTextCompletionIntegration:
assert call_args.kwargs['model'] == "gpt-4"
assert call_args.kwargs['temperature'] == 0.8
assert call_args.kwargs['max_tokens'] == 2048
assert call_args.kwargs['top_p'] == 1
assert call_args.kwargs['frequency_penalty'] == 0
assert call_args.kwargs['presence_penalty'] == 0
# Note: top_p, frequency_penalty, and presence_penalty
# were removed in #561 as unnecessary parameters
@pytest.mark.asyncio
@pytest.mark.slow