mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: (re-)enable Databricks inference adapter (#3500)
# What does this PR do? add/enable the Databricks inference adapter Databricks inference adapter was broken, closes #3486 - remove deprecated completion / chat_completion endpoints - enable dynamic model listing w/o refresh, listing is not async - use SecretStr instead of str for token - backward incompatible change: for consistency with databricks docs, env DATABRICKS_URL -> DATABRICKS_HOST and DATABRICKS_API_TOKEN -> DATABRICKS_TOKEN - databricks urls are custom per user/org, add special recorder handling for databricks urls - add integration test --setup databricks - enable chat completions tests - enable embeddings tests - disable n > 1 tests - disable embeddings base64 tests - disable embeddings dimensions tests note: reasoning models, e.g. gpt oss, fail because databricks has a custom, incompatible response format ## Test Plan ci and ``` ./scripts/integration-tests.sh --stack-config server:ci-tests --setup databricks --subdirs inference --pattern openai ``` note: databricks needs to be manually added to the ci-tests distro for replay testing
This commit is contained in:
parent
9406a998b9
commit
d07ebce4d9
24 changed files with 11649 additions and 101 deletions
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, Field, SecretStr
|
||||
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
||||
|
@ -17,16 +17,16 @@ class DatabricksImplConfig(BaseModel):
|
|||
default=None,
|
||||
description="The URL for the Databricks model serving endpoint",
|
||||
)
|
||||
api_token: str = Field(
|
||||
default=None,
|
||||
api_token: SecretStr = Field(
|
||||
default=SecretStr(None),
|
||||
description="The Databricks API token",
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(
|
||||
cls,
|
||||
url: str = "${env.DATABRICKS_URL:=}",
|
||||
api_token: str = "${env.DATABRICKS_API_TOKEN:=}",
|
||||
url: str = "${env.DATABRICKS_HOST:=}",
|
||||
api_token: str = "${env.DATABRICKS_TOKEN:=}",
|
||||
**kwargs: Any,
|
||||
) -> dict[str, Any]:
|
||||
return {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue