phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-16 22:30:10 -08:00
parent 1bcc26ccd1
commit 7a1b60fccf
2 changed files with 4 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/distribution/library_client.py
View file

@ -25,7 +25,6 @@ from llama_stack_client import (
AsyncStream, AsyncStream,
LlamaStackClient, LlamaStackClient,
NOT_GIVEN, NOT_GIVEN,
Stream,
) )
from pydantic import BaseModel, TypeAdapter from pydantic import BaseModel, TypeAdapter
from rich.console import Console from rich.console import Console
@ -370,8 +369,10 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
json=options.json_data, json=options.json_data,
), ),
) )
origin = get_origin(stream_cls)
assert origin is Stream # we use asynchronous impl always internally and channel all requests to AsyncLlamaStackClient
# however, the top-level caller may be a SyncAPIClient -- so its stream_cls might be a Stream (SyncStream)
# so we need to convert it to AsyncStream
args = get_args(stream_cls) args = get_args(stream_cls)
stream_cls = AsyncStream[args[0]] stream_cls = AsyncStream[args[0]]
response = AsyncAPIResponse( response = AsyncAPIResponse(

13
tests/client-sdk/inference/test_inference.py
View file

@ -4,23 +4,10 @@
# This source code is licensed under the terms described in the LICENSE file in # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # the root directory of this source tree.
import sys
import traceback
import warnings
import pytest import pytest
from llama_stack_client.lib.inference.event_logger import EventLogger from llama_stack_client.lib.inference.event_logger import EventLogger
def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
log = file if hasattr(file, "write") else sys.stderr
traceback.print_stack(file=log)
log.write(warnings.formatwarning(message, category, filename, lineno, line))
warnings.showwarning = warn_with_traceback
def test_text_chat_completion(llama_stack_client): def test_text_chat_completion(llama_stack_client):
# non-streaming # non-streaming
available_models = [ available_models = [