phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 12:52:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into sambanova-inferene

Browse source
This commit is contained in:
snova-edwardm 2025-01-14 10:04:52 -08:00 • committed by GitHub
commit 89ab2be302
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
385 changed files with 39001 additions and 9280 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/registry/agents.py
View file

@ -6,7 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
from llama_stack.providers.utils.kvstore import kvstore_dependencies
@ -29,6 +35,8 @@ def available_providers() -> List[ProviderSpec]:
Api.safety,
Api.memory,
Api.memory_banks,
Api.tool_runtime,
Api.tool_groups,
],
),
remote_provider_spec(

8
llama_stack/providers/registry/datasetio.py
View file

@ -6,7 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
def available_providers() -> List[ProviderSpec]:

2
llama_stack/providers/registry/eval.py
View file

@ -6,7 +6,7 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec
def available_providers() -> List[ProviderSpec]:

27
llama_stack/providers/registry/inference.py
View file

@ -6,8 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
META_REFERENCE_DEPS = [
"accelerate",
@ -18,6 +23,7 @@ META_REFERENCE_DEPS = [
"transformers",
"zmq",
"lm-format-enforcer",
"sentence-transformers",
]
@ -52,6 +58,13 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.inline.inference.vllm",
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::sentence-transformers",
pip_packages=["sentence-transformers"],
module="llama_stack.providers.inline.inference.sentence_transformers",
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
@ -141,6 +154,16 @@ def available_providers() -> List[ProviderSpec]:
provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="groq",
pip_packages=["groq"],
module="llama_stack.providers.remote.inference.groq",
config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
provider_data_validator="llama_stack.providers.remote.inference.groq.GroqProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(

26
llama_stack/providers/registry/memory.py
View file

@ -6,8 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
EMBEDDING_DEPS = [
"blobfile",
@ -39,6 +44,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
deprecation_warning="Please use the `inline::faiss` provider instead.",
api_dependencies=[Api.inference],
),
InlineProviderSpec(
api=Api.memory,
@ -46,6 +52,7 @@ def available_providers() -> List[ProviderSpec]:
pip_packages=EMBEDDING_DEPS + ["faiss-cpu"],
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
api_dependencies=[Api.inference],
),
remote_provider_spec(
Api.memory,
@ -53,8 +60,17 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="chromadb",
pip_packages=EMBEDDING_DEPS + ["chromadb-client"],
module="llama_stack.providers.remote.memory.chroma",
config_class="llama_stack.distribution.datatypes.RemoteProviderConfig",
config_class="llama_stack.providers.remote.memory.chroma.ChromaRemoteImplConfig",
),
api_dependencies=[Api.inference],
),
InlineProviderSpec(
api=Api.memory,
provider_type="inline::chromadb",
pip_packages=EMBEDDING_DEPS + ["chromadb"],
module="llama_stack.providers.inline.memory.chroma",
config_class="llama_stack.providers.inline.memory.chroma.ChromaInlineImplConfig",
api_dependencies=[Api.inference],
),
remote_provider_spec(
Api.memory,
@ -64,6 +80,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.pgvector",
config_class="llama_stack.providers.remote.memory.pgvector.PGVectorConfig",
),
api_dependencies=[Api.inference],
),
remote_provider_spec(
Api.memory,
@ -74,6 +91,7 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.remote.memory.weaviate.WeaviateConfig",
provider_data_validator="llama_stack.providers.remote.memory.weaviate.WeaviateRequestProviderData",
),
api_dependencies=[Api.inference],
),
remote_provider_spec(
api=Api.memory,
@ -83,6 +101,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.sample",
config_class="llama_stack.providers.remote.memory.sample.SampleConfig",
),
api_dependencies=[],
),
remote_provider_spec(
Api.memory,
@ -92,5 +111,6 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.qdrant",
config_class="llama_stack.providers.remote.memory.qdrant.QdrantConfig",
),
api_dependencies=[Api.inference],
),
]

25
llama_stack/providers/registry/post_training.py Normal file
View file

@ -0,0 +1,25 @@
# 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 Api, InlineProviderSpec, ProviderSpec
def available_providers() -> List[ProviderSpec]:
return [
InlineProviderSpec(
api=Api.post_training,
provider_type="inline::torchtune",
pip_packages=["torch", "torchtune", "torchao", "numpy"],
module="llama_stack.providers.inline.post_training.torchtune",
config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
api_dependencies=[
Api.datasetio,
Api.datasets,
],
),
]

2
llama_stack/providers/registry/safety.py
View file

@ -6,7 +6,7 @@
from typing import List
from llama_stack.distribution.datatypes import (
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,

2
llama_stack/providers/registry/scoring.py
View file

@ -6,7 +6,7 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec
def available_providers() -> List[ProviderSpec]:

9
llama_stack/providers/registry/telemetry.py
View file

@ -6,7 +6,13 @@
from typing import List
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.providers.datatypes import (
AdapterSpec,
Api,
InlineProviderSpec,
ProviderSpec,
remote_provider_spec,
)
def available_providers() -> List[ProviderSpec]:
@ -18,6 +24,7 @@ def available_providers() -> List[ProviderSpec]:
"opentelemetry-sdk",
"opentelemetry-exporter-otlp-proto-http",
],
api_dependencies=[Api.datasetio],
module="llama_stack.providers.inline.telemetry.meta_reference",
config_class="llama_stack.providers.inline.telemetry.meta_reference.config.TelemetryConfig",
),

84
llama_stack/providers/registry/tool_runtime.py Normal file
View file

@ -0,0 +1,84 @@
# 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.tool_runtime,
provider_type="inline::memory-runtime",
pip_packages=[],
module="llama_stack.providers.inline.tool_runtime.memory",
config_class="llama_stack.providers.inline.tool_runtime.memory.config.MemoryToolRuntimeConfig",
api_dependencies=[Api.memory, Api.memory_banks, Api.inference],
),
InlineProviderSpec(
api=Api.tool_runtime,
provider_type="inline::code-interpreter",
pip_packages=[],
module="llama_stack.providers.inline.tool_runtime.code_interpreter",
config_class="llama_stack.providers.inline.tool_runtime.code_interpreter.config.CodeInterpreterToolConfig",
),
remote_provider_spec(
api=Api.tool_runtime,
adapter=AdapterSpec(
adapter_type="brave-search",
module="llama_stack.providers.remote.tool_runtime.brave_search",
config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator",
),
),
remote_provider_spec(
api=Api.tool_runtime,
adapter=AdapterSpec(
adapter_type="bing-search",
module="llama_stack.providers.remote.tool_runtime.bing_search",
config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator",
),
),
remote_provider_spec(
api=Api.tool_runtime,
adapter=AdapterSpec(
adapter_type="tavily-search",
module="llama_stack.providers.remote.tool_runtime.tavily_search",
config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator",
),
),
remote_provider_spec(
api=Api.tool_runtime,
adapter=AdapterSpec(
adapter_type="wolfram-alpha",
module="llama_stack.providers.remote.tool_runtime.wolfram_alpha",
config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig",
pip_packages=["requests"],
provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator",
),
),
remote_provider_spec(
api=Api.tool_runtime,
adapter=AdapterSpec(
adapter_type="model-context-protocol",
module="llama_stack.providers.remote.tool_runtime.model_context_protocol",
config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.ModelContextProtocolConfig",
pip_packages=["mcp"],
),
),
]