forked from phoenix-oss/llama-stack-mirror
cca9bd6cc3
# What does this PR do? Removed local execution option from the remote Qdrant provider and introduced an explicit inline provider for the embedded execution. Updated the ollama template to include this option: this part can be reverted in case we don't want to have two default `vector_io` providers. (Closes #1082) ## Test Plan Build and run an ollama distro: ```bash llama stack build --template ollama --image-type conda llama stack run --image-type conda ollama ``` Run one of the sample ingestionapplicatinos like [rag_with_vector_db.py](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/rag_with_vector_db.py), but replace this line: ```py selected_vector_provider = vector_providers[0] ``` with the following, to use the `qdrant` provider: ```py selected_vector_provider = vector_providers[1] ``` After running the test code, verify the timestamp of the Qdrant store: ```bash % ls -ltr ~/.llama/distributions/ollama/qdrant.db/collection/test_vector_db_* total 784 -rw-r--r--@ 1 dmartino staff 401408 Feb 26 10:07 storage.sqlite ``` [//]: # (## Documentation) --------- Signed-off-by: Daniele Martinoli <dmartino@redhat.com> Co-authored-by: Francisco Arceo <farceo@redhat.com>
131 lines
5.5 KiB
Python
131 lines
5.5 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 typing import List
|
|
|
|
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],
|
|
),
|
|
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],
|
|
),
|
|
# 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],
|
|
),
|
|
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],
|
|
),
|
|
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],
|
|
),
|
|
]
|