mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 13:44:38 +00:00
3130ca0a78
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
The purpose of this task is to implement
`openai/v1/vector_stores/{vector_store_id}/search` for PGVector
provider. It involves implementing vector similarity search, keyword
search and hybrid search for `PGVectorIndex`.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes #3006
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
Run unit tests:
` ./scripts/unit-tests.sh `
Run integration tests for openai vector stores:
1. Export env vars:
```
export ENABLE_PGVECTOR=true
export PGVECTOR_HOST=localhost
export PGVECTOR_PORT=5432
export PGVECTOR_DB=llamastack
export PGVECTOR_USER=llamastack
export PGVECTOR_PASSWORD=llamastack
```
2. Create DB:
```
psql -h localhost -U postgres -c "CREATE ROLE llamastack LOGIN PASSWORD 'llamastack';"
psql -h localhost -U postgres -c "CREATE DATABASE llamastack OWNER llamastack;"
psql -h localhost -U llamastack -d llamastack -c "CREATE EXTENSION IF NOT EXISTS vector;"
```
3. Install sentence-transformers:
` uv pip install sentence-transformers `
4. Run:
```
uv run --group test pytest -s -v --stack-config="inference=inline::sentence-transformers,vector_io=remote::pgvector" --embedding-model sentence-transformers/all-MiniLM-L6-v2 tests/integration/vector_io/test_openai_vector_stores.py
```
Inspect PGVector vector stores (optional):
```
psql llamastack
psql (14.18 (Homebrew))
Type "help" for help.
llamastack=# \z
Access privileges
Schema | Name | Type | Access privileges | Column privileges | Policies
--------+------------------------------------------------------+-------+-------------------+-------------------+----------
public | llamastack_kvstore | table | | |
public | metadata_store | table | | |
public | vector_store_pgvector_main | table | | |
public | vector_store_vs_1dfbc061_1f4d_4497_9165_ecba2622ba3a | table | | |
public | vector_store_vs_2085a9fb_1822_4e42_a277_c6a685843fa7 | table | | |
public | vector_store_vs_2b3dae46_38be_462a_afd6_37ee5fe661b1 | table | | |
public | vector_store_vs_2f438de6_f606_4561_9d50_ef9160eb9060 | table | | |
public | vector_store_vs_3eeca564_2580_4c68_bfea_83dc57e31214 | table | | |
public | vector_store_vs_53942163_05f3_40e0_83c0_0997c64613da | table | | |
public | vector_store_vs_545bac75_8950_4ff1_b084_e221192d4709 | table | | |
public | vector_store_vs_688a37d8_35b2_4298_a035_bfedf5b21f86 | table | | |
public | vector_store_vs_70624d9a_f6ac_4c42_b8ab_0649473c6600 | table | | |
public | vector_store_vs_73fc1dd2_e942_4972_afb1_1e177b591ac2 | table | | |
public | vector_store_vs_9d464949_d51f_49db_9f87_e033b8b84ac9 | table | | |
public | vector_store_vs_a1e4d724_5162_4d6d_a6c0_bdafaf6b76ec | table | | |
public | vector_store_vs_a328fb1b_1a21_480f_9624_ffaa60fb6672 | table | | |
public | vector_store_vs_a8981bf0_2e66_4445_a267_a8fff442db53 | table | | |
public | vector_store_vs_ccd4b6a4_1efd_4984_ad03_e7ff8eadb296 | table | | |
public | vector_store_vs_cd6420a4_a1fc_4cec_948c_1413a26281c9 | table | | |
public | vector_store_vs_cd709284_e5cf_4a88_aba5_dc76a35364bd | table | | |
public | vector_store_vs_d7a4548e_fbc1_44d7_b2ec_b664417f2a46 | table | | |
public | vector_store_vs_e7f73231_414c_4523_886c_d1174eee836e | table | | |
public | vector_store_vs_ffd53588_819f_47e8_bb9d_954af6f7833d | table | | |
(23 rows)
llamastack=#
```
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
363 lines
13 KiB
TOML
363 lines
13 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.uv]
|
|
required-version = ">=0.7.0"
|
|
|
|
[project]
|
|
name = "llama_stack"
|
|
version = "0.2.19"
|
|
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
|
|
description = "Llama Stack"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
license = { "text" = "MIT" }
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Operating System :: OS Independent",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Information Technology",
|
|
"Intended Audience :: Science/Research",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
]
|
|
dependencies = [
|
|
"aiohttp",
|
|
"fastapi>=0.115.0,<1.0", # server
|
|
"fire", # for MCP in LLS client
|
|
"httpx",
|
|
"huggingface-hub>=0.34.0,<1.0",
|
|
"jinja2>=3.1.6",
|
|
"jsonschema",
|
|
"llama-stack-client>=0.2.19",
|
|
"llama-api-client>=0.1.2",
|
|
"openai>=1.99.6,<1.100.0",
|
|
"prompt-toolkit",
|
|
"python-dotenv",
|
|
"python-jose[cryptography]",
|
|
"pydantic>=2",
|
|
"rich",
|
|
"starlette",
|
|
"termcolor",
|
|
"tiktoken",
|
|
"pillow",
|
|
"h11>=0.16.0",
|
|
"python-multipart>=0.0.20", # For fastapi Form
|
|
"uvicorn>=0.34.0", # server
|
|
"opentelemetry-sdk>=1.30.0", # server
|
|
"opentelemetry-exporter-otlp-proto-http>=1.30.0", # server
|
|
"aiosqlite>=0.21.0", # server - for metadata store
|
|
"asyncpg", # for metadata store
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
ui = [
|
|
"streamlit",
|
|
"pandas",
|
|
"llama-stack-client>=0.2.19",
|
|
"streamlit-option-menu",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"pytest>=8.4",
|
|
"pytest-timeout",
|
|
"pytest-asyncio>=1.0",
|
|
"pytest-cov",
|
|
"pytest-html",
|
|
"pytest-json-report",
|
|
"pytest-socket", # For blocking network access in unit tests
|
|
"nbval", # For notebook testing
|
|
"black",
|
|
"ruff",
|
|
"types-requests",
|
|
"types-setuptools",
|
|
"pre-commit",
|
|
"ruamel.yaml", # needed for openapi generator
|
|
]
|
|
# These are the dependencies required for running unit tests.
|
|
unit = [
|
|
"sqlite-vec",
|
|
"ollama",
|
|
"openai",
|
|
"aiosqlite",
|
|
"aiohttp",
|
|
"psycopg2-binary>=2.9.0",
|
|
"pypdf",
|
|
"mcp",
|
|
"chardet",
|
|
"qdrant-client",
|
|
"sqlalchemy",
|
|
"sqlalchemy[asyncio]>=2.0.41",
|
|
"blobfile",
|
|
"faiss-cpu",
|
|
"pymilvus>=2.5.12",
|
|
"milvus-lite>=2.5.0",
|
|
"litellm",
|
|
"together",
|
|
"coverage",
|
|
"chromadb>=1.0.15",
|
|
"moto[s3]>=5.1.10",
|
|
]
|
|
# These are the core dependencies required for running integration tests. They are shared across all
|
|
# providers. If a provider requires additional dependencies, please add them to your environment
|
|
# separately. If you are using "uv" to execute your tests, you can use the "--group" flag to specify extra
|
|
# dependencies.
|
|
test = [
|
|
"openai",
|
|
"aiosqlite",
|
|
"aiohttp",
|
|
"torch>=2.6.0",
|
|
"torchvision>=0.21.0",
|
|
"chardet",
|
|
"psycopg2-binary>=2.9.0",
|
|
"pypdf",
|
|
"mcp",
|
|
"datasets",
|
|
"autoevals",
|
|
"transformers",
|
|
"sqlalchemy",
|
|
"sqlalchemy[asyncio]>=2.0.41",
|
|
"requests",
|
|
"pymilvus>=2.5.12",
|
|
"milvus-lite>=2.5.0",
|
|
"weaviate-client>=4.16.4",
|
|
]
|
|
docs = [
|
|
"setuptools",
|
|
"sphinx-autobuild",
|
|
"myst-parser",
|
|
"sphinx",
|
|
"sphinx-rtd-theme",
|
|
"sphinx_rtd_dark_mode",
|
|
"sphinx-copybutton",
|
|
"sphinx-tabs",
|
|
"sphinx-design",
|
|
"sphinxcontrib.redoc",
|
|
"sphinxcontrib.video",
|
|
"sphinxcontrib.mermaid",
|
|
"sphinx-reredirects",
|
|
"tomli",
|
|
"linkify",
|
|
"sphinxcontrib.openapi",
|
|
"requests",
|
|
]
|
|
codegen = ["rich", "pydantic", "jinja2>=3.1.6"]
|
|
benchmark = [
|
|
"locust>=2.37.14",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/meta-llama/llama-stack"
|
|
|
|
[project.scripts]
|
|
llama = "llama_stack.cli.llama:main"
|
|
install-wheel-from-presigned = "llama_stack.cli.scripts.run:install_wheel_from_presigned"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
include = ["llama_stack", "llama_stack.*"]
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cpu"
|
|
url = "https://download.pytorch.org/whl/cpu"
|
|
explicit = true
|
|
|
|
[tool.uv.sources]
|
|
torch = [{ index = "pytorch-cpu" }]
|
|
torchvision = [{ index = "pytorch-cpu" }]
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
exclude = [
|
|
"./.git",
|
|
"./docs/*",
|
|
"./build",
|
|
"./venv",
|
|
"*.pyi",
|
|
".pre-commit-config.yaml",
|
|
"*.md",
|
|
".flake8",
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"UP", # pyupgrade
|
|
"B", # flake8-bugbear
|
|
"B9", # flake8-bugbear subset
|
|
"C", # comprehensions
|
|
"E", # pycodestyle
|
|
"F", # Pyflakes
|
|
"N", # Naming
|
|
"W", # Warnings
|
|
"DTZ", # datetime rules
|
|
"I", # isort (imports order)
|
|
"RUF001", # Checks for ambiguous Unicode characters in strings
|
|
"RUF002", # Checks for ambiguous Unicode characters in docstrings
|
|
"RUF003", # Checks for ambiguous Unicode characters in comments
|
|
"PLC2401", # Checks for the use of non-ASCII characters in variable names
|
|
"PLC2403", # Checks for the use of non-ASCII characters in import statements
|
|
"PLE2510", # Checks for strings that contain the control character BS.
|
|
"PLE2512", # Checks for strings that contain the raw control character SUB.
|
|
"PLE2513", # Checks for strings that contain the raw control character ESC.
|
|
"PLE2514", # Checks for strings that contain the raw control character NUL (0 byte).
|
|
"PLE2515", # Checks for strings that contain the zero width space character.
|
|
]
|
|
ignore = [
|
|
# The following ignores are desired by the project maintainers.
|
|
"E402", # Module level import not at top of file
|
|
"E501", # Line too long
|
|
"F405", # Maybe undefined or defined from star import
|
|
"C408", # Ignored because we like the dict keyword argument syntax
|
|
"N812", # Ignored because import torch.nn.functional as F is PyTorch convention
|
|
|
|
# These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later.
|
|
"C901", # Complexity of the function is too high
|
|
]
|
|
unfixable = [
|
|
"PLE2515",
|
|
] # Do not fix this automatically since ruff will replace the zero-width space with \u200b - let's do it manually
|
|
|
|
# Ignore the following errors for the following files
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"tests/**/*.py" = ["DTZ"] # Ignore datetime rules for tests
|
|
"llama_stack/providers/inline/scoring/basic/utils/ifeval_utils.py" = ["RUF001"]
|
|
"llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py" = [
|
|
"RUF001",
|
|
"PLE2515",
|
|
]
|
|
"llama_stack/apis/**/__init__.py" = [
|
|
"F403",
|
|
] # Using import * is acceptable (or at least tolerated) in an __init__.py of a package API
|
|
|
|
[tool.mypy]
|
|
mypy_path = ["llama_stack"]
|
|
packages = ["llama_stack"]
|
|
plugins = ['pydantic.mypy']
|
|
disable_error_code = []
|
|
warn_return_any = true
|
|
# # honor excludes by not following there through imports
|
|
follow_imports = "silent"
|
|
# Note: some entries are directories, not files. This is because mypy doesn't
|
|
# respect __init__.py excludes, so the only way to suppress these right now is
|
|
# to exclude the entire directory.
|
|
exclude = [
|
|
# As we fix more and more of these, we should remove them from the list
|
|
"^llama_stack/cli/download\\.py$",
|
|
"^llama_stack.core/build\\.py$",
|
|
"^llama_stack.core/client\\.py$",
|
|
"^llama_stack.core/request_headers\\.py$",
|
|
"^llama_stack.core/routers/",
|
|
"^llama_stack.core/routing_tables/",
|
|
"^llama_stack.core/server/endpoints\\.py$",
|
|
"^llama_stack.core/server/server\\.py$",
|
|
"^llama_stack.core/stack\\.py$",
|
|
"^llama_stack.core/store/registry\\.py$",
|
|
"^llama_stack.core/utils/exec\\.py$",
|
|
"^llama_stack.core/utils/prompt_for_config\\.py$",
|
|
"^llama_stack/models/llama/llama3/interface\\.py$",
|
|
"^llama_stack/models/llama/llama3/tokenizer\\.py$",
|
|
"^llama_stack/models/llama/llama3/tool_utils\\.py$",
|
|
"^llama_stack/providers/inline/agents/meta_reference/",
|
|
"^llama_stack/providers/inline/agents/meta_reference/agent_instance\\.py$",
|
|
"^llama_stack/providers/inline/agents/meta_reference/agents\\.py$",
|
|
"^llama_stack/providers/inline/datasetio/localfs/",
|
|
"^llama_stack/providers/inline/eval/meta_reference/eval\\.py$",
|
|
"^llama_stack/providers/inline/inference/meta_reference/inference\\.py$",
|
|
"^llama_stack/models/llama/llama3/generation\\.py$",
|
|
"^llama_stack/models/llama/llama3/multimodal/model\\.py$",
|
|
"^llama_stack/models/llama/llama4/",
|
|
"^llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls\\.py$",
|
|
"^llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers\\.py$",
|
|
"^llama_stack/providers/inline/post_training/common/validator\\.py$",
|
|
"^llama_stack/providers/inline/safety/code_scanner/",
|
|
"^llama_stack/providers/inline/safety/llama_guard/",
|
|
"^llama_stack/providers/inline/scoring/basic/",
|
|
"^llama_stack/providers/inline/scoring/braintrust/",
|
|
"^llama_stack/providers/inline/scoring/llm_as_judge/",
|
|
"^llama_stack/providers/remote/agents/sample/",
|
|
"^llama_stack/providers/remote/datasetio/huggingface/",
|
|
"^llama_stack/providers/remote/datasetio/nvidia/",
|
|
"^llama_stack/providers/remote/inference/anthropic/",
|
|
"^llama_stack/providers/remote/inference/bedrock/",
|
|
"^llama_stack/providers/remote/inference/cerebras/",
|
|
"^llama_stack/providers/remote/inference/databricks/",
|
|
"^llama_stack/providers/remote/inference/fireworks/",
|
|
"^llama_stack/providers/remote/inference/gemini/",
|
|
"^llama_stack/providers/remote/inference/groq/",
|
|
"^llama_stack/providers/remote/inference/nvidia/",
|
|
"^llama_stack/providers/remote/inference/openai/",
|
|
"^llama_stack/providers/remote/inference/passthrough/",
|
|
"^llama_stack/providers/remote/inference/runpod/",
|
|
"^llama_stack/providers/remote/inference/sambanova/",
|
|
"^llama_stack/providers/remote/inference/sample/",
|
|
"^llama_stack/providers/remote/inference/tgi/",
|
|
"^llama_stack/providers/remote/inference/together/",
|
|
"^llama_stack/providers/remote/inference/watsonx/",
|
|
"^llama_stack/providers/remote/safety/bedrock/",
|
|
"^llama_stack/providers/remote/safety/nvidia/",
|
|
"^llama_stack/providers/remote/safety/sambanova/",
|
|
"^llama_stack/providers/remote/safety/sample/",
|
|
"^llama_stack/providers/remote/tool_runtime/bing_search/",
|
|
"^llama_stack/providers/remote/tool_runtime/brave_search/",
|
|
"^llama_stack/providers/remote/tool_runtime/model_context_protocol/",
|
|
"^llama_stack/providers/remote/tool_runtime/tavily_search/",
|
|
"^llama_stack/providers/remote/tool_runtime/wolfram_alpha/",
|
|
"^llama_stack/providers/remote/post_training/nvidia/",
|
|
"^llama_stack/providers/remote/vector_io/chroma/",
|
|
"^llama_stack/providers/remote/vector_io/milvus/",
|
|
"^llama_stack/providers/remote/vector_io/pgvector/",
|
|
"^llama_stack/providers/remote/vector_io/qdrant/",
|
|
"^llama_stack/providers/remote/vector_io/sample/",
|
|
"^llama_stack/providers/remote/vector_io/weaviate/",
|
|
"^llama_stack/providers/tests/conftest\\.py$",
|
|
"^llama_stack/providers/utils/bedrock/client\\.py$",
|
|
"^llama_stack/providers/utils/bedrock/refreshable_boto_session\\.py$",
|
|
"^llama_stack/providers/utils/inference/embedding_mixin\\.py$",
|
|
"^llama_stack/providers/utils/inference/litellm_openai_mixin\\.py$",
|
|
"^llama_stack/providers/utils/inference/model_registry\\.py$",
|
|
"^llama_stack/providers/utils/inference/openai_compat\\.py$",
|
|
"^llama_stack/providers/utils/inference/prompt_adapter\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/config\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/kvstore\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/mongodb/mongodb\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/postgres/postgres\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/redis/redis\\.py$",
|
|
"^llama_stack/providers/utils/kvstore/sqlite/sqlite\\.py$",
|
|
"^llama_stack/providers/utils/memory/vector_store\\.py$",
|
|
"^llama_stack/providers/utils/scoring/aggregation_utils\\.py$",
|
|
"^llama_stack/providers/utils/scoring/base_scoring_fn\\.py$",
|
|
"^llama_stack/providers/utils/telemetry/dataset_mixin\\.py$",
|
|
"^llama_stack/providers/utils/telemetry/trace_protocol\\.py$",
|
|
"^llama_stack/providers/utils/telemetry/tracing\\.py$",
|
|
"^llama_stack/strong_typing/auxiliary\\.py$",
|
|
"^llama_stack/strong_typing/deserializer\\.py$",
|
|
"^llama_stack/strong_typing/inspection\\.py$",
|
|
"^llama_stack/strong_typing/schema\\.py$",
|
|
"^llama_stack/strong_typing/serializer\\.py$",
|
|
"^llama_stack/distributions/groq/groq\\.py$",
|
|
"^llama_stack/distributions/llama_api/llama_api\\.py$",
|
|
"^llama_stack/distributions/sambanova/sambanova\\.py$",
|
|
"^llama_stack/distributions/template\\.py$",
|
|
]
|
|
|
|
[[tool.mypy.overrides]]
|
|
# packages that lack typing annotations, do not have stubs, or are unavailable.
|
|
module = ["yaml", "fire"]
|
|
ignore_missing_imports = true
|
|
|
|
[tool.pydantic-mypy]
|
|
init_forbid_extra = true
|
|
init_typed = true
|
|
warn_required_dynamic_aliases = true
|
|
|
|
[tool.ruff.lint.pep8-naming]
|
|
classmethod-decorators = ["classmethod", "pydantic.field_validator"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
markers = [
|
|
"allow_network: Allow network access for specific unit tests",
|
|
]
|