Fix incorrect completion() signature for Databricks provider (#236)

This commit is contained in:
Yuan Tang 2024-10-11 11:47:57 -04:00 committed by GitHub
parent 9fbe8852aa
commit 2128e61da2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 19 additions and 6 deletions

View file

@ -73,7 +73,7 @@ docker run -it -p 5000:5000 -v ~/.llama:/root/.llama --gpus=all llamastack-local
```
> [!NOTE]
> `~/.llama` should be the path containing downloaded weights of Llama models.
> `~/.llama` should be the path containing downloaded weights of Llama models.
#### Via conda

View file

@ -7,10 +7,11 @@
from .config import DatabricksImplConfig
from .databricks import DatabricksInferenceAdapter
async def get_adapter_impl(config: DatabricksImplConfig, _deps):
assert isinstance(
config, DatabricksImplConfig
), f"Unexpected config type: {type(config)}"
impl = DatabricksInferenceAdapter(config)
await impl.initialize()
return impl
return impl

View file

@ -4,7 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel, Field
@ -19,4 +18,4 @@ class DatabricksImplConfig(BaseModel):
api_token: str = Field(
default=None,
description="The Databricks API token",
)
)

View file

@ -48,7 +48,14 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
async def shutdown(self) -> None:
pass
def completion(self, request: CompletionRequest) -> AsyncGenerator:
def completion(
self,
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(

View file

@ -170,7 +170,7 @@ class LlamaGuardShield(ShieldBase):
for i in range(1, len(messages)):
if messages[i].role == messages[i - 1].role:
raise ValueError(
f"Messages must alternate between user and assistant. Message {i} has the same role as message {i-1}"
f"Messages must alternate between user and assistant. Message {i} has the same role as message {i - 1}"
)
return messages

View file

@ -1,3 +1,9 @@
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any
from .config import VLLMConfig