phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert openai_compat changes and use OpenAIMixin for openai_chat_completion

Browse source
This commit is contained in:
Swapna Lekkala 2025-09-18 16:06:53 -07:00
parent 0f5bef893a
commit a6baa7b3d4
9 changed files with 23 additions and 303 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/integration/inference/test_openai_embeddings.py
View file

@ -6,6 +6,7 @@
import base64
import struct
import time
import pytest
from openai import OpenAI
@ -13,6 +14,13 @@ from openai import OpenAI
from llama_stack.core.library_client import LlamaStackAsLibraryClient
@pytest.fixture(autouse=True)
def rate_limit_delay():
"""Add delay between tests to avoid rate limiting from providers like Fireworks"""
yield
time.sleep(30) # 30 second delay after each test
def decode_base64_to_floats(base64_string: str) -> list[float]:
"""Helper function to decode base64 string to list of float32 values."""
embedding_bytes = base64.b64decode(base64_string)