phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: combine ProviderSpec datatypes (#3378)
Some checks failed
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Details
UI Tests / ui-tests (22) (push) Successful in 36s
Details
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Details
Test Llama Stack Build / build (push) Failing after 4s
Details
Pre-commit / pre-commit (push) Successful in 1m12s
Details
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Details
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Details
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Details
Python Package Build Test / build (3.13) (push) Failing after 1s
Details
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Details
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Details
Python Package Build Test / build (3.12) (push) Failing after 2s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 7s
Details
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Details
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Details
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Details
Test External API and Providers / test-external (venv) (push) Failing after 4s
Details
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Details

Browse source 
# What does this PR do?

currently `RemoteProviderSpec` has an `AdapterSpec` embedded in it.
Remove `AdapterSpec`, and put its leftover fields into
`RemoteProviderSpec`.

Additionally, many of the fields were duplicated between
`InlineProviderSpec` and `RemoteProviderSpec`. Move these to
`ProviderSpec` so they are shared.

Fixup the distro codegen to use `RemoteProviderSpec` directly rather
than `remote_provider_spec` which took an AdapterSpec and returned a
full provider spec

## Test Plan

existing distro tests should pass.

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-09-18 10:10:00 -04:00 • committed by GitHub
parent e66103c09d
commit 8422bd102a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 381 additions and 503 deletions
Download patch file Download diff file Expand all files Collapse all files

108
llama_stack/providers/registry/vector_io.py
View file

@ -6,11 +6,10 @@
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
RemoteProviderSpec,
)
@ -300,14 +299,16 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
Please refer to the sqlite-vec provider documentation.
""",
),
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",
description="""
RemoteProviderSpec(
api=Api.vector_io,
adapter_type="chromadb",
provider_type="remote::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],
optional_api_dependencies=[Api.files],
description="""
[Chroma](https://www.trychroma.com/) is an inline and remote vector
database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
That means you're not limited to storing vectors in memory or in a separate service.
@ -340,9 +341,6 @@ pip install chromadb
## Documentation
See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general.
""",
),
api_dependencies=[Api.inference],
optional_api_dependencies=[Api.files],
),
InlineProviderSpec(
api=Api.vector_io,
@ -387,14 +385,16 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
""",
),
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",
description="""
RemoteProviderSpec(
api=Api.vector_io,
adapter_type="pgvector",
provider_type="remote::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],
optional_api_dependencies=[Api.files],
description="""
[PGVector](https://github.com/pgvector/pgvector) is a remote vector database provider for Llama Stack. It
allows you to store and query vectors directly in memory.
That means you'll get fast and efficient vector retrieval.
@ -495,19 +495,18 @@ docker pull pgvector/pgvector:pg17
## Documentation
See [PGVector's documentation](https://github.com/pgvector/pgvector) for more details about PGVector in general.
""",
),
),
RemoteProviderSpec(
api=Api.vector_io,
adapter_type="weaviate",
provider_type="remote::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],
optional_api_dependencies=[Api.files],
),
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",
description="""
description="""
[Weaviate](https://weaviate.io/) is a vector database provider for Llama Stack.
It allows you to store and query vectors directly within a Weaviate database.
That means you're not limited to storing vectors in memory or in a separate service.
@ -538,9 +537,6 @@ To install Weaviate see the [Weaviate quickstart documentation](https://weaviate
## Documentation
See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more details about Weaviate in general.
""",
),
api_dependencies=[Api.inference],
optional_api_dependencies=[Api.files],
),
InlineProviderSpec(
api=Api.vector_io,
@ -594,28 +590,29 @@ docker pull qdrant/qdrant
See the [Qdrant documentation](https://qdrant.tech/documentation/) for more details about Qdrant in general.
""",
),
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",
description="""
Please refer to the inline provider documentation.
""",
),
RemoteProviderSpec(
api=Api.vector_io,
adapter_type="qdrant",
provider_type="remote::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],
optional_api_dependencies=[Api.files],
description="""
Please refer to the inline provider documentation.
""",
),
remote_provider_spec(
Api.vector_io,
AdapterSpec(
adapter_type="milvus",
pip_packages=["pymilvus>=2.4.10"],
module="llama_stack.providers.remote.vector_io.milvus",
config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
description="""
RemoteProviderSpec(
api=Api.vector_io,
adapter_type="milvus",
provider_type="remote::milvus",
pip_packages=["pymilvus>=2.4.10"],
module="llama_stack.providers.remote.vector_io.milvus",
config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
api_dependencies=[Api.inference],
optional_api_dependencies=[Api.files],
description="""
[Milvus](https://milvus.io/) is an inline and remote vector database provider for Llama Stack. It
allows you to store and query vectors directly within a Milvus database.
That means you're not limited to storing vectors in memory or in a separate service.
@ -806,9 +803,6 @@ See the [Milvus documentation](https://milvus.io/docs/install-overview.md) for m
For more details on TLS configuration, refer to the [TLS setup guide](https://milvus.io/docs/tls.md).
""",
),
api_dependencies=[Api.inference],
optional_api_dependencies=[Api.files],
),
InlineProviderSpec(
api=Api.vector_io,