mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-10 05:24:39 +00:00
a70fc60485
# What does this PR do? ## Test Plan # What does this PR do? ## Test Plan # What does this PR do? ## Test Plan Completes the refactoring started in previous commit by: 1. **Fix library client** (critical): Add logic to detect Pydantic model parameters and construct them properly from request bodies. The key fix is to NOT exclude any params when converting the body for Pydantic models - we need all fields to pass to the Pydantic constructor. Before: _convert_body excluded all params, leaving body empty for Pydantic construction After: Check for Pydantic params first, skip exclusion, construct model with full body 2. **Update remaining providers** to use new Pydantic-based signatures: - litellm_openai_mixin: Extract extra fields via __pydantic_extra__ - databricks: Use TYPE_CHECKING import for params type - llama_openai_compat: Use TYPE_CHECKING import for params type - sentence_transformers: Update method signatures to use params 3. **Update unit tests** to use new Pydantic signature: - test_openai_mixin.py: Use OpenAIChatCompletionRequestParams This fixes test failures where the library client was trying to construct Pydantic models with empty dictionaries. The previous fix had a bug: it called _convert_body() which only keeps fields that match function parameter names. For Pydantic methods with signature: openai_chat_completion(params: OpenAIChatCompletionRequestParams) The signature only has 'params', but the body has 'model', 'messages', etc. So _convert_body() returned an empty dict. Fix: Skip _convert_body() entirely for Pydantic params. Use the raw body directly to construct the Pydantic model (after stripping NOT_GIVENs). This properly fixes the ValidationError where required fields were missing. The streaming code path (_call_streaming) had the same issue as non-streaming: it called _convert_body() which returned empty dict for Pydantic params. Applied the same fix as commit 7476c0ae: - Detect Pydantic model parameters before body conversion - Skip _convert_body() for Pydantic params - Construct Pydantic model directly from raw body (after stripping NOT_GIVENs) This fixes streaming endpoints like openai_chat_completion with stream=True. The streaming code path (_call_streaming) had the same issue as non-streaming: it called _convert_body() which returned empty dict for Pydantic params. Applied the same fix as commit 7476c0ae: - Detect Pydantic model parameters before body conversion - Skip _convert_body() for Pydantic params - Construct Pydantic model directly from raw body (after stripping NOT_GIVENs) This fixes streaming endpoints like openai_chat_completion with stream=True.
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
# 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 collections.abc import Iterable
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from databricks.sdk import WorkspaceClient
|
|
|
|
from llama_stack.apis.inference import OpenAICompletion
|
|
|
|
if TYPE_CHECKING:
|
|
from llama_stack.apis.inference import OpenAICompletionRequestParams
|
|
from llama_stack.log import get_logger
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import DatabricksImplConfig
|
|
|
|
logger = get_logger(name=__name__, category="inference::databricks")
|
|
|
|
|
|
class DatabricksInferenceAdapter(OpenAIMixin):
|
|
config: DatabricksImplConfig
|
|
|
|
# source: https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models
|
|
embedding_model_metadata: dict[str, dict[str, int]] = {
|
|
"databricks-gte-large-en": {"embedding_dimension": 1024, "context_length": 8192},
|
|
"databricks-bge-large-en": {"embedding_dimension": 1024, "context_length": 512},
|
|
}
|
|
|
|
def get_api_key(self) -> str:
|
|
return self.config.api_token.get_secret_value()
|
|
|
|
def get_base_url(self) -> str:
|
|
return f"{self.config.url}/serving-endpoints"
|
|
|
|
async def list_provider_model_ids(self) -> Iterable[str]:
|
|
return [
|
|
endpoint.name
|
|
for endpoint in WorkspaceClient(
|
|
host=self.config.url, token=self.get_api_key()
|
|
).serving_endpoints.list() # TODO: this is not async
|
|
]
|
|
|
|
async def openai_completion(
|
|
self,
|
|
params: "OpenAICompletionRequestParams",
|
|
) -> OpenAICompletion:
|
|
raise NotImplementedError()
|