phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: unpublish /inference/chat-completion (#3609)

Browse source 
# What does this PR do?

BREAKING CHANGE: removes /inference/chat-completion route and updates
relevant documentation

## Test Plan

🤷
This commit is contained in:
Matthew Farrellee 2025-09-30 14:00:42 -04:00 • committed by GitHub
parent 62e302613f
commit cb33f45c11
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 1448 additions and 2137 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/integration/README.md
View file

@ -179,15 +179,15 @@ Note that when re-recording tests, you must use a Stack pointing to a server (i.
### Basic Test Pattern
```python
def test_basic_chat_completion(llama_stack_client, text_model_id):
response = llama_stack_client.inference.chat_completion(
model_id=text_model_id,
response = llama_stack_client.chat.completions.create(
model=text_model_id,
messages=[{"role": "user", "content": "Hello"}],
)
# Test structure, not AI output quality
assert response.completion_message is not None
assert isinstance(response.completion_message.content, str)
assert len(response.completion_message.content) > 0
assert response.choices[0].message is not None
assert isinstance(response.choices[0].message.content, str)
assert len(response.choices[0].message.content) > 0
```
### Provider-Specific Tests