llama-stack-mirror/tests/integration/suites.py
Matthew Farrellee ae804ed5a8 feat: (re-)enable Databricks inference adapter
Databricks inference adapter was broken, would not start, see #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 with: ./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
2025-09-20 05:05:05 -04:00

145 lines
4.3 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.
# Central definition of integration test suites. You can use these suites by passing --suite=name to pytest.
# For example:
#
# ```bash
# pytest tests/integration/ --suite=vision --setup=ollama
# ```
#
"""
Each suite defines what to run (roots). Suites can be run with different global setups defined in setups.py.
Setups provide environment variables and model defaults that can be reused across multiple suites.
CLI examples:
pytest tests/integration --suite=responses --setup=gpt
pytest tests/integration --suite=vision --setup=ollama
pytest tests/integration --suite=base --setup=vllm
"""
from pathlib import Path
from pydantic import BaseModel, Field
this_dir = Path(__file__).parent
class Suite(BaseModel):
name: str
roots: list[str]
default_setup: str | None = None
class Setup(BaseModel):
"""A reusable test configuration with environment and CLI defaults."""
name: str
description: str
defaults: dict[str, str] = Field(default_factory=dict)
env: dict[str, str] = Field(default_factory=dict)
# Global setups - can be used with any suite "technically" but in reality, some setups might work
# only for specific test suites.
SETUP_DEFINITIONS: dict[str, Setup] = {
"ollama": Setup(
name="ollama",
description="Local Ollama provider with text + safety models",
env={
"OLLAMA_URL": "http://0.0.0.0:11434",
"SAFETY_MODEL": "ollama/llama-guard3:1b",
},
defaults={
"text_model": "ollama/llama3.2:3b-instruct-fp16",
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
"safety_model": "ollama/llama-guard3:1b",
"safety_shield": "llama-guard",
},
),
"ollama-vision": Setup(
name="ollama",
description="Local Ollama provider with a vision model",
env={
"OLLAMA_URL": "http://0.0.0.0:11434",
},
defaults={
"vision_model": "ollama/llama3.2-vision:11b",
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
},
),
"vllm": Setup(
name="vllm",
description="vLLM provider with a text model",
env={
"VLLM_URL": "http://localhost:8000/v1",
},
defaults={
"text_model": "vllm/meta-llama/Llama-3.2-1B-Instruct",
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
},
),
"gpt": Setup(
name="gpt",
description="OpenAI GPT models for high-quality responses and tool calling",
defaults={
"text_model": "openai/gpt-4o",
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
},
),
"tgi": Setup(
name="tgi",
description="Text Generation Inference (TGI) provider with a text model",
env={
"TGI_URL": "http://localhost:8080",
},
defaults={
"text_model": "tgi/Qwen/Qwen3-0.6B",
},
),
"together": Setup(
name="together",
description="Together computer models",
defaults={
"text_model": "together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
"embedding_model": "together/togethercomputer/m2-bert-80M-32k-retrieval",
},
),
"databricks": Setup(
name="databricks",
description="Databricks models",
defaults={
"text_model": "databricks/databricks-meta-llama-3-3-70b-instruct",
"embedding_model": "databricks/databricks-bge-large-en",
},
),
}
base_roots = [
str(p)
for p in this_dir.glob("*")
if p.is_dir()
and p.name not in ("__pycache__", "fixtures", "test_cases", "recordings", "responses", "post_training")
]
SUITE_DEFINITIONS: dict[str, Suite] = {
"base": Suite(
name="base",
roots=base_roots,
default_setup="ollama",
),
"responses": Suite(
name="responses",
roots=["tests/integration/responses"],
default_setup="gpt",
),
"vision": Suite(
name="vision",
roots=["tests/integration/inference/test_vision_inference.py"],
default_setup="ollama-vision",
),
}