phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 10:10:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(package): migrate to src/ layout (#3920)

Browse source 
Migrates package structure to src/ layout following Python packaging
best practices.

All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.

Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.

**Developer note**: Reinstall after pulling: `pip install -e .`
This commit is contained in:
Ashwin Bharambe 2025-10-27 12:02:21 -07:00 • committed by GitHub
parent 98a5047f9d
commit 471b1b248b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
791 changed files with 2983 additions and 456 deletions
Download patch file Download diff file Expand all files Collapse all files

44
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -1,44 +0,0 @@
# 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 databricks.sdk import WorkspaceClient
from llama_stack.apis.inference import OpenAICompletion, OpenAICompletionRequestWithExtraBody
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_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: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
raise NotImplementedError()