phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 07:14:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Test fixes

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-08 16:57:52 -07:00 • committed by Ashwin Bharambe
parent 8eee5b9adc
commit f40cd62306
3 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/inference/client.py
View file

@ -84,7 +84,7 @@ class InferenceClient(Inference):
response.raise_for_status() response.raise_for_status()
j = response.json() j = response.json()
yield ChatCompletionResponse(**j) return ChatCompletionResponse(**j)
async def _stream_chat_completion( async def _stream_chat_completion(
self, request: ChatCompletionRequest self, request: ChatCompletionRequest

1
llama_stack/providers/tests/inference/test_inference.py
View file

@ -68,7 +68,6 @@ async def inference_settings(request):
ModelDef( ModelDef(
identifier=model, identifier=model,
llama_model=model, llama_model=model,
provider_id="",
) )
], ],
) )

1
llama_stack/providers/tests/memory/test_memory.py
View file

@ -67,7 +67,6 @@ def sample_documents():
async def register_memory_bank(memory_impl: Memory): async def register_memory_bank(memory_impl: Memory):
bank = VectorMemoryBankDef( bank = VectorMemoryBankDef(
identifier="test_bank", identifier="test_bank",
provider_id="",
embedding_model="all-MiniLM-L6-v2", embedding_model="all-MiniLM-L6-v2",
chunk_size_in_tokens=512, chunk_size_in_tokens=512,
overlap_size_in_tokens=64, overlap_size_in_tokens=64,