mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
941f505eb0
# What does this PR do? This is an initial working prototype of wiring up the `file_search` builtin tool for the Responses API to our existing rag knowledge search tool. This is me seeing what I could pull together on top of the bits we already have merged. This may not be the ideal way to implement this, and things like how I shuffle the vector store ids from the original response API tool request to the actual tool execution feel a bit hacky (grep for `tool_kwargs["vector_db_ids"]` in `_execute_tool_call` to see what I mean). ## Test Plan I stubbed in some new tests to exercise this using text and pdf documents. Note that this is currently under tests/verification only because it sometimes flakes with tool calling of the small Llama-3.2-3B model we run in CI (and that I use as an example below). We'd want to make the test a bit more robust in some way if we moved this over to tests/integration and ran it in CI. ### OpenAI SaaS (to verify test correctness) ``` pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search' \ --base-url=https://api.openai.com/v1 \ --model=gpt-4o ``` ### Fireworks with faiss vector store ``` llama stack run llama_stack/templates/fireworks/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=meta-llama/Llama-3.3-70B-Instruct ``` ### Ollama with faiss vector store This sometimes flakes on Ollama because the quantized small model doesn't always choose to call the tool to answer the user's question. But, it often works. ``` ollama run llama3.2:3b INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run ./llama_stack/templates/ollama/run.yaml \ --image-type venv \ --env OLLAMA_URL="http://0.0.0.0:11434" pytest -sv tests/verifications/openai_api/test_responses.py \ -k'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=meta-llama/Llama-3.2-3B-Instruct ``` ### OpenAI provider with sqlite-vec vector store ``` llama stack run ./llama_stack/templates/starter/run.yaml --image-type venv pytest -sv tests/verifications/openai_api/test_responses.py \ -k 'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=openai/gpt-4o-mini ``` ### Ensure existing vector store integration tests still pass ``` ollama run llama3.2:3b INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run ./llama_stack/templates/ollama/run.yaml \ --image-type venv \ --env OLLAMA_URL="http://0.0.0.0:11434" LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io \ --text-model "meta-llama/Llama-3.2-3B-Instruct" \ --embedding-model=all-MiniLM-L6-v2 ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>
134 lines
5.6 KiB
Python
134 lines
5.6 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.
|
|
|
|
|
|
from llama_stack.providers.datatypes import (
|
|
AdapterSpec,
|
|
Api,
|
|
InlineProviderSpec,
|
|
ProviderSpec,
|
|
remote_provider_spec,
|
|
)
|
|
|
|
|
|
def available_providers() -> list[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::meta-reference",
|
|
pip_packages=["faiss-cpu"],
|
|
module="llama_stack.providers.inline.vector_io.faiss",
|
|
config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
|
|
deprecation_warning="Please use the `inline::faiss` provider instead.",
|
|
api_dependencies=[Api.inference],
|
|
optional_api_dependencies=[Api.files],
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::faiss",
|
|
pip_packages=["faiss-cpu"],
|
|
module="llama_stack.providers.inline.vector_io.faiss",
|
|
config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
|
|
api_dependencies=[Api.inference],
|
|
optional_api_dependencies=[Api.files],
|
|
),
|
|
# NOTE: sqlite-vec cannot be bundled into the container image because it does not have a
|
|
# source distribution and the wheels are not available for all platforms.
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::sqlite-vec",
|
|
pip_packages=["sqlite-vec"],
|
|
module="llama_stack.providers.inline.vector_io.sqlite_vec",
|
|
config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
|
|
api_dependencies=[Api.inference],
|
|
optional_api_dependencies=[Api.files],
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::sqlite_vec",
|
|
pip_packages=["sqlite-vec"],
|
|
module="llama_stack.providers.inline.vector_io.sqlite_vec",
|
|
config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
|
|
deprecation_warning="Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.",
|
|
api_dependencies=[Api.inference],
|
|
optional_api_dependencies=[Api.files],
|
|
),
|
|
remote_provider_spec(
|
|
Api.vector_io,
|
|
AdapterSpec(
|
|
adapter_type="chromadb",
|
|
pip_packages=["chromadb-client"],
|
|
module="llama_stack.providers.remote.vector_io.chroma",
|
|
config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig",
|
|
),
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::chromadb",
|
|
pip_packages=["chromadb"],
|
|
module="llama_stack.providers.inline.vector_io.chroma",
|
|
config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
remote_provider_spec(
|
|
Api.vector_io,
|
|
AdapterSpec(
|
|
adapter_type="pgvector",
|
|
pip_packages=["psycopg2-binary"],
|
|
module="llama_stack.providers.remote.vector_io.pgvector",
|
|
config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig",
|
|
),
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
remote_provider_spec(
|
|
Api.vector_io,
|
|
AdapterSpec(
|
|
adapter_type="weaviate",
|
|
pip_packages=["weaviate-client"],
|
|
module="llama_stack.providers.remote.vector_io.weaviate",
|
|
config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig",
|
|
provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData",
|
|
),
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::qdrant",
|
|
pip_packages=["qdrant-client"],
|
|
module="llama_stack.providers.inline.vector_io.qdrant",
|
|
config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
remote_provider_spec(
|
|
Api.vector_io,
|
|
AdapterSpec(
|
|
adapter_type="qdrant",
|
|
pip_packages=["qdrant-client"],
|
|
module="llama_stack.providers.remote.vector_io.qdrant",
|
|
config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig",
|
|
),
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
remote_provider_spec(
|
|
Api.vector_io,
|
|
AdapterSpec(
|
|
adapter_type="milvus",
|
|
pip_packages=["pymilvus"],
|
|
module="llama_stack.providers.remote.vector_io.milvus",
|
|
config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
|
|
),
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.vector_io,
|
|
provider_type="inline::milvus",
|
|
pip_packages=["pymilvus"],
|
|
module="llama_stack.providers.inline.vector_io.milvus",
|
|
config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
|
|
api_dependencies=[Api.inference],
|
|
),
|
|
]
|