phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 07:21:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use provider resource id to validate for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 08:21:37 -08:00
parent e4f14eafe2
commit 95b7f57d92
7 changed files with 75 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -74,7 +74,7 @@ class FireworksInferenceAdapter(
async def completion(
self,
model: str,
model_id: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
@ -82,7 +82,7 @@ class FireworksInferenceAdapter(
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = CompletionRequest(
model=model,
model=model_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
@ -138,7 +138,7 @@ class FireworksInferenceAdapter(
async def chat_completion(
self,
model: str,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = None,
@ -149,7 +149,7 @@ class FireworksInferenceAdapter(
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
model=model_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
@ -229,7 +229,7 @@ class FireworksInferenceAdapter(
async def embeddings(
self,
model: str,
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
raise NotImplementedError()

10
llama_stack/providers/remote/inference/together/together.py
View file

@ -63,7 +63,7 @@ class TogetherInferenceAdapter(
async def completion(
self,
model: str,
model_id: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
@ -71,7 +71,7 @@ class TogetherInferenceAdapter(
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = CompletionRequest(
model=model,
model=model_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
@ -135,7 +135,7 @@ class TogetherInferenceAdapter(
async def chat_completion(
self,
model: str,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = None,
@ -146,7 +146,7 @@ class TogetherInferenceAdapter(
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
model=model_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
@ -221,7 +221,7 @@ class TogetherInferenceAdapter(
async def embeddings(
self,
model: str,
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
raise NotImplementedError()