llama-stack/llama_stack/distribution/build.py
Xi Yan 3c72c034e6
[remove import *] clean up import *'s (#689)
# What does this PR do?

- as title, cleaning up `import *`'s
- upgrade tests to make them more robust to bad model outputs
- remove import *'s in llama_stack/apis/* (skip __init__ modules)
<img width="465" alt="image"
src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2"
/>

- run `sh run_openapi_generator.sh`, no types gets affected

## Test Plan

### Providers Tests

**agents**
```
pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8
```

**inference**
```bash
# meta-reference
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

# together
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py

pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py 
```

**safety**
```
pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B
```

**memory**
```
pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384
```

**scoring**
```
pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct
pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py
```


**datasetio**
```
pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py
pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py
```


**eval**
```
pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py
pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py
```

### Client-SDK Tests
```
LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk
```

### llama-stack-apps
```
PORT=5000
LOCALHOST=localhost

python -m examples.agents.hello $LOCALHOST $PORT
python -m examples.agents.inflation $LOCALHOST $PORT
python -m examples.agents.podcast_transcript $LOCALHOST $PORT
python -m examples.agents.rag_as_attachments $LOCALHOST $PORT
python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT
python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT
python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT

# Vision model
python -m examples.interior_design_assistant.app
python -m examples.agent_store.app $LOCALHOST $PORT
```

### CLI
```
which llama
llama model prompt-format -m Llama3.2-11B-Vision-Instruct
llama model list
llama stack list-apis
llama stack list-providers inference

llama stack build --template ollama --image-type conda
```

### Distributions Tests
**ollama**
```
llama stack build --template ollama --image-type conda
ollama run llama3.2:1b-instruct-fp16
llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct
```

**fireworks**
```
llama stack build --template fireworks --image-type conda
llama stack run ./llama_stack/templates/fireworks/run.yaml
```

**together**
```
llama stack build --template together --image-type conda
llama stack run ./llama_stack/templates/together/run.yaml
```

**tgi**
```
llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
```

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
2024-12-27 15:45:44 -08:00

155 lines
4.5 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 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.
import logging
from enum import Enum
from pathlib import Path
from typing import Dict, List
import pkg_resources
from pydantic import BaseModel
from termcolor import cprint
from llama_stack.distribution.datatypes import BuildConfig, Provider
from llama_stack.distribution.distribution import get_provider_registry
from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
from llama_stack.distribution.utils.exec import run_with_pty
from llama_stack.providers.datatypes import Api
log = logging.getLogger(__name__)
# These are the dependencies needed by the distribution server.
# `llama-stack` is automatically installed by the installation script.
SERVER_DEPENDENCIES = [
"aiosqlite",
"fastapi",
"fire",
"httpx",
"uvicorn",
]
class ImageType(Enum):
docker = "docker"
conda = "conda"
venv = "venv"
class ApiInput(BaseModel):
api: Api
provider: str
def get_provider_dependencies(
config_providers: Dict[str, List[Provider]],
) -> tuple[list[str], list[str]]:
"""Get normal and special dependencies from provider configuration."""
all_providers = get_provider_registry()
deps = []
for api_str, provider_or_providers in config_providers.items():
providers_for_api = all_providers[Api(api_str)]
providers = (
provider_or_providers
if isinstance(provider_or_providers, list)
else [provider_or_providers]
)
for provider in providers:
# Providers from BuildConfig and RunConfig are subtly different  not great
provider_type = (
provider if isinstance(provider, str) else provider.provider_type
)
if provider_type not in providers_for_api:
raise ValueError(
f"Provider `{provider}` is not available for API `{api_str}`"
)
provider_spec = providers_for_api[provider_type]
deps.extend(provider_spec.pip_packages)
if provider_spec.docker_image:
raise ValueError("A stack's dependencies cannot have a docker image")
normal_deps = []
special_deps = []
for package in deps:
if "--no-deps" in package or "--index-url" in package:
special_deps.append(package)
else:
normal_deps.append(package)
return list(set(normal_deps)), list(set(special_deps))
def print_pip_install_help(providers: Dict[str, List[Provider]]):
normal_deps, special_deps = get_provider_dependencies(providers)
cprint(
f"Please install needed dependencies using the following commands:\n\npip install {' '.join(normal_deps)}",
"yellow",
)
for special_dep in special_deps:
cprint(f"pip install {special_dep}", "yellow")
print()
def build_image(build_config: BuildConfig, build_file_path: Path):
docker_image = build_config.distribution_spec.docker_image or "python:3.10-slim"
normal_deps, special_deps = get_provider_dependencies(
build_config.distribution_spec.providers
)
normal_deps += SERVER_DEPENDENCIES
if build_config.image_type == ImageType.docker.value:
script = pkg_resources.resource_filename(
"llama_stack", "distribution/build_container.sh"
)
args = [
script,
build_config.name,
docker_image,
str(build_file_path),
str(BUILDS_BASE_DIR / ImageType.docker.value),
" ".join(normal_deps),
]
elif build_config.image_type == ImageType.conda.value:
script = pkg_resources.resource_filename(
"llama_stack", "distribution/build_conda_env.sh"
)
args = [
script,
build_config.name,
str(build_file_path),
" ".join(normal_deps),
]
elif build_config.image_type == ImageType.venv.value:
script = pkg_resources.resource_filename(
"llama_stack", "distribution/build_venv.sh"
)
args = [
script,
build_config.name,
str(build_file_path),
" ".join(normal_deps),
]
if special_deps:
args.append("#".join(special_deps))
return_code = run_with_pty(args)
if return_code != 0:
log.error(
f"Failed to build target {build_config.name} with return code {return_code}",
)
return return_code