phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 16:48:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tests pass with Ollama now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 17:31:21 -08:00
parent a9a041a1de
commit e51154964f
27 changed files with 83 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/distribution/routers/routers.py
View file

@ -59,7 +59,7 @@ class MemoryRouter(Memory):
async def query_documents(
self,
bank_id: str,
query: InterleavedTextMedia,
query: InterleavedContent,
params: Optional[Dict[str, Any]] = None,
) -> QueryDocumentsResponse:
return await self.routing_table.get_provider_impl(bank_id).query_documents(
@ -133,7 +133,7 @@ class InferenceRouter(Inference):
async def completion(
self,
model_id: str,
content: InterleavedTextMedia,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
@ -163,7 +163,7 @@ class InferenceRouter(Inference):
async def embeddings(
self,
model_id: str,
contents: List[InterleavedTextMedia],
contents: List[InterleavedContent],
) -> EmbeddingsResponse:
model = await self.routing_table.get_model(model_id)
if model is None: