phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 15:49:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix docker failing to start container

Browse source
This commit is contained in:
Swapna Lekkala 2025-08-27 15:36:57 -07:00
parent 52106d95d3
commit 83ede71e76
4 changed files with 22 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/registry/inference.py
View file

@ -116,7 +116,7 @@ def available_providers() -> list[ProviderSpec]:
adapter=AdapterSpec(
adapter_type="fireworks",
pip_packages=[
"fireworks-ai",
"fireworks-ai==0.17.16",
],
module="llama_stack.providers.remote.inference.fireworks",
config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",

13
llama_stack/providers/remote/inference/vertexai/vertexai.py
View file

@ -6,7 +6,9 @@
from typing import Any
from llama_stack.apis.inference import ChatCompletionRequest
from openai.types.chat import ChatCompletionContentPartImageParam, ChatCompletionContentPartTextParam
from llama_stack.apis.inference import ChatCompletionRequest, RerankResponse
from llama_stack.providers.utils.inference.litellm_openai_mixin import (
LiteLLMOpenAIMixin,
)
@ -50,3 +52,12 @@ class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
params.pop("api_key", None)
return params
async def rerank(
self,
model: str,
query: str | ChatCompletionContentPartTextParam | ChatCompletionContentPartImageParam,
items: list[str | ChatCompletionContentPartTextParam | ChatCompletionContentPartImageParam],
max_num_results: int | None = None,
) -> RerankResponse:
raise NotImplementedError("Reranking is not supported for Vertex AI")