mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-12 20:12:33 +00:00
Merge origin/main into add-missing-provider-data-impls
Resolved conflicts in: - benchmarking/k8s-benchmark/stack_run_config.yaml (accepted new storage schema) - llama_stack/providers/remote/inference/cerebras/cerebras.py (kept provider data support) - llama_stack/providers/remote/inference/cerebras/config.py (kept provider data support) - llama_stack/providers/remote/inference/nvidia/config.py (kept provider data support) - llama_stack/providers/remote/inference/runpod/config.py (merged imports) - pyproject.toml (kept databricks-sdk dependency)
This commit is contained in:
Ashwin Bharambe
commit
9eb9a37ee4
1880 changed files with 804868 additions and 70533 deletions
|
|
@ -32,12 +32,9 @@ def available_providers() -> list[ProviderSpec]:
|
|||
Api.inference,
|
||||
Api.safety,
|
||||
Api.vector_io,
|
||||
Api.vector_dbs,
|
||||
Api.tool_runtime,
|
||||
Api.tool_groups,
|
||||
],
|
||||
optional_api_dependencies=[
|
||||
Api.telemetry,
|
||||
Api.conversations,
|
||||
],
|
||||
description="Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks.",
|
||||
),
|
||||
|
|
|
|||
|
|
@ -43,6 +43,12 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=[
|
||||
"torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
|
||||
"sentence-transformers --no-deps",
|
||||
# required by some SentenceTransformers architectures for tensor rearrange/merge ops
|
||||
"einops",
|
||||
# fast HF tokenization backend used by SentenceTransformers models
|
||||
"tokenizers",
|
||||
# safe and fast file format for storing and loading tensors
|
||||
"safetensors",
|
||||
],
|
||||
module="llama_stack.providers.inline.inference.sentence_transformers",
|
||||
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
|
||||
|
|
@ -275,7 +281,7 @@ Available Models:
|
|||
pip_packages=["litellm"],
|
||||
module="llama_stack.providers.remote.inference.watsonx",
|
||||
config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.watsonx.config.WatsonXProviderDataValidator",
|
||||
description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
|
||||
),
|
||||
RemoteProviderSpec(
|
||||
|
|
|
|||
|
|
@ -1,29 +0,0 @@
|
|||
# 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 (
|
||||
Api,
|
||||
InlineProviderSpec,
|
||||
ProviderSpec,
|
||||
)
|
||||
|
||||
|
||||
def available_providers() -> list[ProviderSpec]:
|
||||
return [
|
||||
InlineProviderSpec(
|
||||
api=Api.telemetry,
|
||||
provider_type="inline::meta-reference",
|
||||
pip_packages=[
|
||||
"opentelemetry-sdk",
|
||||
"opentelemetry-exporter-otlp-proto-http",
|
||||
],
|
||||
optional_api_dependencies=[Api.datasetio],
|
||||
module="llama_stack.providers.inline.telemetry.meta_reference",
|
||||
config_class="llama_stack.providers.inline.telemetry.meta_reference.config.TelemetryConfig",
|
||||
description="Meta's reference implementation of telemetry and observability using OpenTelemetry.",
|
||||
),
|
||||
]
|
||||
|
|
@ -26,7 +26,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="Meta's reference implementation of a vector database.",
|
||||
),
|
||||
InlineProviderSpec(
|
||||
|
|
@ -36,7 +36,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="""
|
||||
[Faiss](https://github.com/facebookresearch/faiss) is an inline vector database provider for Llama Stack. It
|
||||
allows you to store and query vectors directly in memory.
|
||||
|
|
@ -89,7 +89,7 @@ more details about Faiss in general.
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="""
|
||||
[SQLite-Vec](https://github.com/asg017/sqlite-vec) is an inline vector database provider for Llama Stack. It
|
||||
allows you to store and query vectors directly within an SQLite database.
|
||||
|
|
@ -297,7 +297,7 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="""
|
||||
Please refer to the sqlite-vec provider documentation.
|
||||
""",
|
||||
|
|
@ -310,7 +310,7 @@ Please refer to the sqlite-vec provider documentation.
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
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.
|
||||
|
|
@ -352,7 +352,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
|
|||
module="llama_stack.providers.inline.vector_io.chroma",
|
||||
config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
|
||||
api_dependencies=[Api.inference],
|
||||
optional_api_dependencies=[Api.files],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
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.
|
||||
|
|
@ -396,7 +396,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
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.
|
||||
|
|
@ -508,7 +508,7 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
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.
|
||||
|
|
@ -548,7 +548,7 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
|
|||
module="llama_stack.providers.inline.vector_io.qdrant",
|
||||
config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
|
||||
api_dependencies=[Api.inference],
|
||||
optional_api_dependencies=[Api.files],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description=r"""
|
||||
[Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
|
||||
allows you to store and query vectors directly in memory.
|
||||
|
|
@ -601,7 +601,7 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="""
|
||||
Please refer to the inline provider documentation.
|
||||
""",
|
||||
|
|
@ -614,7 +614,7 @@ Please refer to the inline provider documentation.
|
|||
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],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
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.
|
||||
|
|
@ -820,7 +820,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
|
|||
module="llama_stack.providers.inline.vector_io.milvus",
|
||||
config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
|
||||
api_dependencies=[Api.inference],
|
||||
optional_api_dependencies=[Api.files],
|
||||
optional_api_dependencies=[Api.files, Api.models],
|
||||
description="""
|
||||
Please refer to the remote provider documentation.
|
||||
""",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue