From 994732e2e0a624ce83dc15b70f7f95d1b73c57bd Mon Sep 17 00:00:00 2001 From: Ashwin Bharambe Date: Wed, 6 Nov 2024 14:54:05 -0800 Subject: [PATCH] `impls` -> `inline`, `adapters` -> `remote` (#381) --- .gitmodules | 2 +- docs/source/api_providers/new_api_provider.md | 4 +- .../distributions/ondevice_distro/ios_sdk.md | 2 +- .../self_hosted_distro/ollama.md | 2 +- docs/source/getting_started/index.md | 2 +- .../{adapters => inline}/__init__.py | 0 .../braintrust/scoring/__init__.py | 0 .../braintrust/scoring/braintrust.py | 2 +- .../braintrust/scoring/config.py | 0 .../scoring/scoring_fn}/__init__.py | 0 .../scoring/scoring_fn/fn_defs}/__init__.py | 0 .../scoring_fn/fn_defs/answer_correctness.py | 0 .../scoring/scoring_fn/fn_defs/factuality.py | 0 .../project.pbxproj | 0 .../contents.xcworkspacedata | 0 .../xcshareddata/IDEWorkspaceChecks.plist | 0 .../LocalInferenceImpl/LocalInference.h | 0 .../LocalInferenceImpl/LocalInference.swift | 0 .../LocalInferenceImpl/Parsing.swift | 0 .../LocalInferenceImpl/PromptTemplate.swift | 0 .../LocalInferenceImpl/SystemPrompts.swift | 0 .../ios/inference/executorch | 0 .../meta_reference}/__init__.py | 0 .../meta_reference/agents/__init__.py | 0 .../meta_reference/agents/agent_instance.py | 0 .../meta_reference/agents/agents.py | 0 .../meta_reference/agents/config.py | 0 .../meta_reference/agents/persistence.py | 0 .../meta_reference/agents/rag}/__init__.py | 0 .../agents/rag/context_retriever.py | 0 .../meta_reference/agents/safety.py | 0 .../meta_reference/agents/tests}/__init__.py | 0 .../agents/tests/code_execution.py | 0 .../agents/tests/test_chat_agent.py | 0 .../meta_reference/agents/tools}/__init__.py | 0 .../meta_reference/agents/tools/base.py | 0 .../meta_reference/agents/tools/builtin.py | 0 .../agents/tools/ipython_tool}/__init__.py | 0 .../tools/ipython_tool/code_env_prefix.py | 0 .../tools/ipython_tool/code_execution.py | 0 .../ipython_tool/matplotlib_custom_backend.py | 0 .../agents/tools/ipython_tool/utils.py | 0 .../meta_reference/agents/tools/safety.py | 2 +- .../meta_reference/codeshield/__init__.py | 0 .../meta_reference/codeshield/code_scanner.py | 0 .../meta_reference/codeshield/config.py | 0 .../meta_reference/datasetio/__init__.py | 0 .../meta_reference/datasetio/config.py | 0 .../meta_reference/datasetio/datasetio.py | 0 .../meta_reference/eval/__init__.py | 0 .../meta_reference/eval/config.py | 0 .../meta_reference/eval/eval.py | 0 .../meta_reference/inference/__init__.py | 0 .../meta_reference/inference/config.py | 0 .../meta_reference/inference/generation.py | 0 .../meta_reference/inference/inference.py | 0 .../inference/model_parallel.py | 0 .../inference/parallel_utils.py | 0 .../inference/quantization}/__init__.py | 0 .../inference/quantization/fp8_impls.py | 0 .../quantization/fp8_txest_disabled.py | 0 .../inference/quantization/hadamard_utils.py | 0 .../inference/quantization/loader.py | 2 +- .../quantization/scripts}/__init__.py | 0 .../quantization/scripts/build_conda.sh | 0 .../scripts/quantize_checkpoint.py | 0 .../scripts/run_quantize_checkpoint.sh | 0 .../meta_reference/memory/__init__.py | 0 .../meta_reference/memory/config.py | 0 .../meta_reference/memory/faiss.py | 0 .../meta_reference/memory/tests/test_faiss.py | 4 +- .../meta_reference/safety/__init__.py | 0 .../meta_reference/safety/base.py | 0 .../meta_reference/safety/config.py | 0 .../meta_reference/safety/llama_guard.py | 0 .../meta_reference/safety/prompt_guard.py | 0 .../meta_reference/safety/safety.py | 0 .../meta_reference/scoring/__init__.py | 0 .../meta_reference/scoring/config.py | 0 .../meta_reference/scoring/scoring.py | 6 +-- .../scoring/scoring_fn}/__init__.py | 0 .../scoring/scoring_fn/base_scoring_fn.py | 0 .../scoring/scoring_fn/common.py | 0 .../scoring/scoring_fn/equality_scoring_fn.py | 6 +-- .../scoring/scoring_fn/fn_defs}/__init__.py | 0 .../scoring/scoring_fn/fn_defs/equality.py | 0 .../fn_defs/llm_as_judge_8b_correctness.py | 0 .../scoring/scoring_fn/fn_defs/subset_of.py | 0 .../scoring_fn/llm_as_judge_scoring_fn.py | 6 +-- .../scoring_fn/subset_of_scoring_fn.py | 6 +-- .../meta_reference/telemetry/__init__.py | 0 .../meta_reference/telemetry/config.py | 0 .../meta_reference/telemetry/console.py | 0 .../{impls => inline}/vllm/__init__.py | 0 .../{impls => inline}/vllm/config.py | 0 .../providers/{impls => inline}/vllm/vllm.py | 0 llama_stack/providers/registry/agents.py | 8 +-- llama_stack/providers/registry/datasetio.py | 4 +- llama_stack/providers/registry/eval.py | 4 +- llama_stack/providers/registry/inference.py | 54 +++++++++---------- llama_stack/providers/registry/memory.py | 24 ++++----- llama_stack/providers/registry/safety.py | 22 ++++---- llama_stack/providers/registry/scoring.py | 8 +-- llama_stack/providers/registry/telemetry.py | 12 ++--- .../agents/tools => remote}/__init__.py | 0 .../agents}/__init__.py | 0 .../agents/sample/__init__.py | 0 .../agents/sample/config.py | 0 .../agents/sample/sample.py | 0 .../inference}/__init__.py | 0 .../inference/bedrock/__init__.py | 0 .../inference/bedrock/bedrock.py | 2 +- .../inference/bedrock/config.py | 0 .../inference/databricks/__init__.py | 0 .../inference/databricks/config.py | 0 .../inference/databricks/databricks.py | 0 .../inference/fireworks/__init__.py | 0 .../inference/fireworks/config.py | 0 .../inference/fireworks/fireworks.py | 0 .../inference/ollama/__init__.py | 0 .../inference/ollama/ollama.py | 0 .../inference/sample/__init__.py | 0 .../inference/sample/config.py | 0 .../inference/sample/sample.py | 0 .../inference/tgi/__init__.py | 0 .../inference/tgi/config.py | 0 .../{adapters => remote}/inference/tgi/tgi.py | 0 .../inference/together/__init__.py | 0 .../inference/together/config.py | 0 .../inference/together/together.py | 0 .../inference/vllm/__init__.py | 0 .../inference/vllm/config.py | 0 .../inference/vllm/vllm.py | 0 .../scripts => remote/memory}/__init__.py | 0 .../memory/chroma/__init__.py | 0 .../memory/chroma/chroma.py | 0 .../memory/pgvector/__init__.py | 0 .../memory/pgvector/config.py | 0 .../memory/pgvector/pgvector.py | 0 .../memory/qdrant/__init__.py | 0 .../memory/qdrant/config.py | 0 .../memory/qdrant/qdrant.py | 2 +- .../memory/sample/__init__.py | 0 .../memory/sample/config.py | 0 .../memory/sample/sample.py | 0 .../memory/weaviate/__init__.py | 0 .../memory/weaviate/config.py | 0 .../memory/weaviate/weaviate.py | 0 .../scoring_fn => remote/safety}/__init__.py | 0 .../safety/bedrock/__init__.py | 0 .../safety/bedrock/bedrock.py | 0 .../safety/bedrock/config.py | 0 .../safety/sample/__init__.py | 0 .../safety/sample/config.py | 0 .../safety/sample/sample.py | 0 .../safety/together/__init__.py | 0 .../safety/together/config.py | 0 .../safety/together/together.py | 0 .../fn_defs => remote/telemetry}/__init__.py | 0 .../telemetry/opentelemetry/__init__.py | 0 .../telemetry/opentelemetry/config.py | 0 .../telemetry/opentelemetry/opentelemetry.py | 0 .../telemetry/sample/__init__.py | 0 .../telemetry/sample/config.py | 0 .../telemetry/sample/sample.py | 0 .../providers/tests/agents/fixtures.py | 2 +- .../providers/tests/inference/fixtures.py | 13 ++--- .../providers/tests/memory/fixtures.py | 6 +-- .../providers/tests/safety/fixtures.py | 4 +- 169 files changed, 106 insertions(+), 105 deletions(-) rename llama_stack/providers/{adapters => inline}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/braintrust/scoring/__init__.py (100%) rename llama_stack/providers/{impls => inline}/braintrust/scoring/braintrust.py (98%) rename llama_stack/providers/{impls => inline}/braintrust/scoring/config.py (100%) rename llama_stack/providers/{adapters/agents => inline/braintrust/scoring/scoring_fn}/__init__.py (100%) rename llama_stack/providers/{adapters/inference => inline/braintrust/scoring/scoring_fn/fn_defs}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/braintrust/scoring/scoring_fn/fn_defs/answer_correctness.py (100%) rename llama_stack/providers/{impls => inline}/braintrust/scoring/scoring_fn/fn_defs/factuality.py (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl/LocalInference.h (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl/LocalInference.swift (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl/Parsing.swift (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl/PromptTemplate.swift (100%) rename llama_stack/providers/{impls => inline}/ios/inference/LocalInferenceImpl/SystemPrompts.swift (100%) rename llama_stack/providers/{impls => inline}/ios/inference/executorch (100%) rename llama_stack/providers/{adapters/memory => inline/meta_reference}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/agent_instance.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/agents.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/persistence.py (100%) rename llama_stack/providers/{adapters/safety => inline/meta_reference/agents/rag}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/rag/context_retriever.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/safety.py (100%) rename llama_stack/providers/{adapters/telemetry => inline/meta_reference/agents/tests}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tests/code_execution.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tests/test_chat_agent.py (100%) rename llama_stack/providers/{impls => inline/meta_reference/agents/tools}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/base.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/builtin.py (100%) rename llama_stack/providers/{impls/braintrust/scoring/scoring_fn => inline/meta_reference/agents/tools/ipython_tool}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/ipython_tool/code_env_prefix.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/ipython_tool/code_execution.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/ipython_tool/matplotlib_custom_backend.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/ipython_tool/utils.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/agents/tools/safety.py (93%) rename llama_stack/providers/{impls => inline}/meta_reference/codeshield/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/codeshield/code_scanner.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/codeshield/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/datasetio/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/datasetio/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/datasetio/datasetio.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/eval/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/eval/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/eval/eval.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/generation.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/inference.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/model_parallel.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/parallel_utils.py (100%) rename llama_stack/providers/{impls/braintrust/scoring/scoring_fn/fn_defs => inline/meta_reference/inference/quantization}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/fp8_impls.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/fp8_txest_disabled.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/hadamard_utils.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/loader.py (99%) rename llama_stack/providers/{impls/meta_reference => inline/meta_reference/inference/quantization/scripts}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/scripts/build_conda.sh (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/scripts/quantize_checkpoint.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/inference/quantization/scripts/run_quantize_checkpoint.sh (100%) rename llama_stack/providers/{impls => inline}/meta_reference/memory/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/memory/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/memory/faiss.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/memory/tests/test_faiss.py (93%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/base.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/llama_guard.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/prompt_guard.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/safety/safety.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring.py (94%) rename llama_stack/providers/{impls/meta_reference/agents/rag => inline/meta_reference/scoring/scoring_fn}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/base_scoring_fn.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/common.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/equality_scoring_fn.py (85%) rename llama_stack/providers/{impls/meta_reference/agents/tests => inline/meta_reference/scoring/scoring_fn/fn_defs}/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/fn_defs/equality.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/fn_defs/llm_as_judge_8b_correctness.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/fn_defs/subset_of.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py (90%) rename llama_stack/providers/{impls => inline}/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py (83%) rename llama_stack/providers/{impls => inline}/meta_reference/telemetry/__init__.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/telemetry/config.py (100%) rename llama_stack/providers/{impls => inline}/meta_reference/telemetry/console.py (100%) rename llama_stack/providers/{impls => inline}/vllm/__init__.py (100%) rename llama_stack/providers/{impls => inline}/vllm/config.py (100%) rename llama_stack/providers/{impls => inline}/vllm/vllm.py (100%) rename llama_stack/providers/{impls/meta_reference/agents/tools => remote}/__init__.py (100%) rename llama_stack/providers/{impls/meta_reference/agents/tools/ipython_tool => remote/agents}/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/agents/sample/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/agents/sample/config.py (100%) rename llama_stack/providers/{adapters => remote}/agents/sample/sample.py (100%) rename llama_stack/providers/{impls/meta_reference/inference/quantization => remote/inference}/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/bedrock/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/bedrock/bedrock.py (99%) rename llama_stack/providers/{adapters => remote}/inference/bedrock/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/databricks/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/databricks/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/databricks/databricks.py (100%) rename llama_stack/providers/{adapters => remote}/inference/fireworks/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/fireworks/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/fireworks/fireworks.py (100%) rename llama_stack/providers/{adapters => remote}/inference/ollama/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/ollama/ollama.py (100%) rename llama_stack/providers/{adapters => remote}/inference/sample/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/sample/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/sample/sample.py (100%) rename llama_stack/providers/{adapters => remote}/inference/tgi/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/tgi/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/tgi/tgi.py (100%) rename llama_stack/providers/{adapters => remote}/inference/together/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/together/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/together/together.py (100%) rename llama_stack/providers/{adapters => remote}/inference/vllm/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/inference/vllm/config.py (100%) rename llama_stack/providers/{adapters => remote}/inference/vllm/vllm.py (100%) rename llama_stack/providers/{impls/meta_reference/inference/quantization/scripts => remote/memory}/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/chroma/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/chroma/chroma.py (100%) rename llama_stack/providers/{adapters => remote}/memory/pgvector/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/pgvector/config.py (100%) rename llama_stack/providers/{adapters => remote}/memory/pgvector/pgvector.py (100%) rename llama_stack/providers/{adapters => remote}/memory/qdrant/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/qdrant/config.py (100%) rename llama_stack/providers/{adapters => remote}/memory/qdrant/qdrant.py (98%) rename llama_stack/providers/{adapters => remote}/memory/sample/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/sample/config.py (100%) rename llama_stack/providers/{adapters => remote}/memory/sample/sample.py (100%) rename llama_stack/providers/{adapters => remote}/memory/weaviate/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/memory/weaviate/config.py (100%) rename llama_stack/providers/{adapters => remote}/memory/weaviate/weaviate.py (100%) rename llama_stack/providers/{impls/meta_reference/scoring/scoring_fn => remote/safety}/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/safety/bedrock/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/safety/bedrock/bedrock.py (100%) rename llama_stack/providers/{adapters => remote}/safety/bedrock/config.py (100%) rename llama_stack/providers/{adapters => remote}/safety/sample/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/safety/sample/config.py (100%) rename llama_stack/providers/{adapters => remote}/safety/sample/sample.py (100%) rename llama_stack/providers/{adapters => remote}/safety/together/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/safety/together/config.py (100%) rename llama_stack/providers/{adapters => remote}/safety/together/together.py (100%) rename llama_stack/providers/{impls/meta_reference/scoring/scoring_fn/fn_defs => remote/telemetry}/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/opentelemetry/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/opentelemetry/config.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/opentelemetry/opentelemetry.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/sample/__init__.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/sample/config.py (100%) rename llama_stack/providers/{adapters => remote}/telemetry/sample/sample.py (100%) diff --git a/.gitmodules b/.gitmodules index f23f58cd8..611875287 100644 --- a/.gitmodules +++ b/.gitmodules @@ -1,3 +1,3 @@ [submodule "llama_stack/providers/impls/ios/inference/executorch"] - path = llama_stack/providers/impls/ios/inference/executorch + path = llama_stack/providers/inline/ios/inference/executorch url = https://github.com/pytorch/executorch diff --git a/docs/source/api_providers/new_api_provider.md b/docs/source/api_providers/new_api_provider.md index 6d75c38a6..868b5bec2 100644 --- a/docs/source/api_providers/new_api_provider.md +++ b/docs/source/api_providers/new_api_provider.md @@ -6,8 +6,8 @@ This guide contains references to walk you through adding a new API provider. 1. First, decide which API your provider falls into (e.g. Inference, Safety, Agents, Memory). 2. Decide whether your provider is a remote provider, or inline implmentation. A remote provider is a provider that makes a remote request to an service. An inline provider is a provider where implementation is executed locally. Checkout the examples, and follow the structure to add your own API provider. Please find the following code pointers: - - [Inference Remote Adapter](https://github.com/meta-llama/llama-stack/tree/docs/llama_stack/providers/adapters/inference) - - [Inference Inline Provider](https://github.com/meta-llama/llama-stack/tree/docs/llama_stack/providers/impls/meta_reference/inference) + - [Inference Remote Adapter](https://github.com/meta-llama/llama-stack/tree/docs/llama_stack/providers/remote/inference) + - [Inference Inline Provider](https://github.com/meta-llama/llama-stack/tree/docs/llama_stack/providers/inline/meta_reference/inference) 3. [Build a Llama Stack distribution](https://llama-stack.readthedocs.io/en/latest/distribution_dev/building_distro.html) with your API provider. 4. Test your code! diff --git a/docs/source/getting_started/distributions/ondevice_distro/ios_sdk.md b/docs/source/getting_started/distributions/ondevice_distro/ios_sdk.md index 08885ad73..ea65ecd82 100644 --- a/docs/source/getting_started/distributions/ondevice_distro/ios_sdk.md +++ b/docs/source/getting_started/distributions/ondevice_distro/ios_sdk.md @@ -3,7 +3,7 @@ We offer both remote and on-device use of Llama Stack in Swift via two components: 1. [llama-stack-client-swift](https://github.com/meta-llama/llama-stack-client-swift/) -2. [LocalInferenceImpl](https://github.com/meta-llama/llama-stack/tree/main/llama_stack/providers/impls/ios/inference) +2. [LocalInferenceImpl](https://github.com/meta-llama/llama-stack/tree/main/llama_stack/providers/inline/ios/inference) ```{image} ../../../../_static/remote_or_local.gif :alt: Seamlessly switching between local, on-device inference and remote hosted inference diff --git a/docs/source/getting_started/distributions/self_hosted_distro/ollama.md b/docs/source/getting_started/distributions/self_hosted_distro/ollama.md index 003656e2b..0d4d90ee6 100644 --- a/docs/source/getting_started/distributions/self_hosted_distro/ollama.md +++ b/docs/source/getting_started/distributions/self_hosted_distro/ollama.md @@ -102,7 +102,7 @@ ollama pull llama3.1:70b-instruct-fp16 ``` > [!NOTE] -> Please check the [OLLAMA_SUPPORTED_MODELS](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/adapters/inference/ollama/ollama.py) for the supported Ollama models. +> Please check the [OLLAMA_SUPPORTED_MODELS](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers.remote/inference/ollama/ollama.py) for the supported Ollama models. To serve a new model with `ollama` diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md index c79a6dce7..c99b5f8f9 100644 --- a/docs/source/getting_started/index.md +++ b/docs/source/getting_started/index.md @@ -386,7 +386,7 @@ ollama pull llama3.1:8b-instruct-fp16 ollama pull llama3.1:70b-instruct-fp16 ``` -> Please check the [OLLAMA_SUPPORTED_MODELS](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/adapters/inference/ollama/ollama.py) for the supported Ollama models. +> Please check the [OLLAMA_SUPPORTED_MODELS](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers.remote/inference/ollama/ollama.py) for the supported Ollama models. To serve a new model with `ollama` diff --git a/llama_stack/providers/adapters/__init__.py b/llama_stack/providers/inline/__init__.py similarity index 100% rename from llama_stack/providers/adapters/__init__.py rename to llama_stack/providers/inline/__init__.py diff --git a/llama_stack/providers/impls/braintrust/scoring/__init__.py b/llama_stack/providers/inline/braintrust/scoring/__init__.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/__init__.py rename to llama_stack/providers/inline/braintrust/scoring/__init__.py diff --git a/llama_stack/providers/impls/braintrust/scoring/braintrust.py b/llama_stack/providers/inline/braintrust/scoring/braintrust.py similarity index 98% rename from llama_stack/providers/impls/braintrust/scoring/braintrust.py rename to llama_stack/providers/inline/braintrust/scoring/braintrust.py index 826d60379..6488a63eb 100644 --- a/llama_stack/providers/impls/braintrust/scoring/braintrust.py +++ b/llama_stack/providers/inline/braintrust/scoring/braintrust.py @@ -16,7 +16,7 @@ from llama_stack.apis.datasets import * # noqa: F403 from autoevals.llm import Factuality from autoevals.ragas import AnswerCorrectness from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.common import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.common import ( aggregate_average, ) diff --git a/llama_stack/providers/impls/braintrust/scoring/config.py b/llama_stack/providers/inline/braintrust/scoring/config.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/config.py rename to llama_stack/providers/inline/braintrust/scoring/config.py diff --git a/llama_stack/providers/adapters/agents/__init__.py b/llama_stack/providers/inline/braintrust/scoring/scoring_fn/__init__.py similarity index 100% rename from llama_stack/providers/adapters/agents/__init__.py rename to llama_stack/providers/inline/braintrust/scoring/scoring_fn/__init__.py diff --git a/llama_stack/providers/adapters/inference/__init__.py b/llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/__init__.py rename to llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/__init__.py diff --git a/llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/answer_correctness.py b/llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/answer_correctness.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/answer_correctness.py rename to llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/answer_correctness.py diff --git a/llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/factuality.py b/llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/factuality.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/factuality.py rename to llama_stack/providers/inline/braintrust/scoring/scoring_fn/fn_defs/factuality.py diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl/LocalInference.h b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.h similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl/LocalInference.h rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.h diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl/LocalInference.swift b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.swift similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl/LocalInference.swift rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.swift diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl/Parsing.swift b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl/Parsing.swift similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl/Parsing.swift rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl/Parsing.swift diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl/PromptTemplate.swift b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl/PromptTemplate.swift similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl/PromptTemplate.swift rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl/PromptTemplate.swift diff --git a/llama_stack/providers/impls/ios/inference/LocalInferenceImpl/SystemPrompts.swift b/llama_stack/providers/inline/ios/inference/LocalInferenceImpl/SystemPrompts.swift similarity index 100% rename from llama_stack/providers/impls/ios/inference/LocalInferenceImpl/SystemPrompts.swift rename to llama_stack/providers/inline/ios/inference/LocalInferenceImpl/SystemPrompts.swift diff --git a/llama_stack/providers/impls/ios/inference/executorch b/llama_stack/providers/inline/ios/inference/executorch similarity index 100% rename from llama_stack/providers/impls/ios/inference/executorch rename to llama_stack/providers/inline/ios/inference/executorch diff --git a/llama_stack/providers/adapters/memory/__init__.py b/llama_stack/providers/inline/meta_reference/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/__init__.py rename to llama_stack/providers/inline/meta_reference/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/__init__.py b/llama_stack/providers/inline/meta_reference/agents/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/__init__.py rename to llama_stack/providers/inline/meta_reference/agents/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/agent_instance.py b/llama_stack/providers/inline/meta_reference/agents/agent_instance.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/agent_instance.py rename to llama_stack/providers/inline/meta_reference/agents/agent_instance.py diff --git a/llama_stack/providers/impls/meta_reference/agents/agents.py b/llama_stack/providers/inline/meta_reference/agents/agents.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/agents.py rename to llama_stack/providers/inline/meta_reference/agents/agents.py diff --git a/llama_stack/providers/impls/meta_reference/agents/config.py b/llama_stack/providers/inline/meta_reference/agents/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/config.py rename to llama_stack/providers/inline/meta_reference/agents/config.py diff --git a/llama_stack/providers/impls/meta_reference/agents/persistence.py b/llama_stack/providers/inline/meta_reference/agents/persistence.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/persistence.py rename to llama_stack/providers/inline/meta_reference/agents/persistence.py diff --git a/llama_stack/providers/adapters/safety/__init__.py b/llama_stack/providers/inline/meta_reference/agents/rag/__init__.py similarity index 100% rename from llama_stack/providers/adapters/safety/__init__.py rename to llama_stack/providers/inline/meta_reference/agents/rag/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/rag/context_retriever.py b/llama_stack/providers/inline/meta_reference/agents/rag/context_retriever.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/rag/context_retriever.py rename to llama_stack/providers/inline/meta_reference/agents/rag/context_retriever.py diff --git a/llama_stack/providers/impls/meta_reference/agents/safety.py b/llama_stack/providers/inline/meta_reference/agents/safety.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/safety.py rename to llama_stack/providers/inline/meta_reference/agents/safety.py diff --git a/llama_stack/providers/adapters/telemetry/__init__.py b/llama_stack/providers/inline/meta_reference/agents/tests/__init__.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/__init__.py rename to llama_stack/providers/inline/meta_reference/agents/tests/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tests/code_execution.py b/llama_stack/providers/inline/meta_reference/agents/tests/code_execution.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tests/code_execution.py rename to llama_stack/providers/inline/meta_reference/agents/tests/code_execution.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tests/test_chat_agent.py b/llama_stack/providers/inline/meta_reference/agents/tests/test_chat_agent.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tests/test_chat_agent.py rename to llama_stack/providers/inline/meta_reference/agents/tests/test_chat_agent.py diff --git a/llama_stack/providers/impls/__init__.py b/llama_stack/providers/inline/meta_reference/agents/tools/__init__.py similarity index 100% rename from llama_stack/providers/impls/__init__.py rename to llama_stack/providers/inline/meta_reference/agents/tools/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/base.py b/llama_stack/providers/inline/meta_reference/agents/tools/base.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/base.py rename to llama_stack/providers/inline/meta_reference/agents/tools/base.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/builtin.py b/llama_stack/providers/inline/meta_reference/agents/tools/builtin.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/builtin.py rename to llama_stack/providers/inline/meta_reference/agents/tools/builtin.py diff --git a/llama_stack/providers/impls/braintrust/scoring/scoring_fn/__init__.py b/llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/__init__.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/scoring_fn/__init__.py rename to llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/code_env_prefix.py b/llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/code_env_prefix.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/code_env_prefix.py rename to llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/code_env_prefix.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/code_execution.py b/llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/code_execution.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/code_execution.py rename to llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/code_execution.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/matplotlib_custom_backend.py b/llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/matplotlib_custom_backend.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/matplotlib_custom_backend.py rename to llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/matplotlib_custom_backend.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/utils.py b/llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/utils.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/utils.py rename to llama_stack/providers/inline/meta_reference/agents/tools/ipython_tool/utils.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/safety.py b/llama_stack/providers/inline/meta_reference/agents/tools/safety.py similarity index 93% rename from llama_stack/providers/impls/meta_reference/agents/tools/safety.py rename to llama_stack/providers/inline/meta_reference/agents/tools/safety.py index fb95786d1..72530f0e6 100644 --- a/llama_stack/providers/impls/meta_reference/agents/tools/safety.py +++ b/llama_stack/providers/inline/meta_reference/agents/tools/safety.py @@ -9,7 +9,7 @@ from typing import List from llama_stack.apis.inference import Message from llama_stack.apis.safety import * # noqa: F403 -from llama_stack.providers.impls.meta_reference.agents.safety import ShieldRunnerMixin +from llama_stack.providers.inline.meta_reference.agents.safety import ShieldRunnerMixin from .builtin import BaseTool diff --git a/llama_stack/providers/impls/meta_reference/codeshield/__init__.py b/llama_stack/providers/inline/meta_reference/codeshield/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/codeshield/__init__.py rename to llama_stack/providers/inline/meta_reference/codeshield/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/codeshield/code_scanner.py b/llama_stack/providers/inline/meta_reference/codeshield/code_scanner.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/codeshield/code_scanner.py rename to llama_stack/providers/inline/meta_reference/codeshield/code_scanner.py diff --git a/llama_stack/providers/impls/meta_reference/codeshield/config.py b/llama_stack/providers/inline/meta_reference/codeshield/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/codeshield/config.py rename to llama_stack/providers/inline/meta_reference/codeshield/config.py diff --git a/llama_stack/providers/impls/meta_reference/datasetio/__init__.py b/llama_stack/providers/inline/meta_reference/datasetio/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/datasetio/__init__.py rename to llama_stack/providers/inline/meta_reference/datasetio/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/datasetio/config.py b/llama_stack/providers/inline/meta_reference/datasetio/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/datasetio/config.py rename to llama_stack/providers/inline/meta_reference/datasetio/config.py diff --git a/llama_stack/providers/impls/meta_reference/datasetio/datasetio.py b/llama_stack/providers/inline/meta_reference/datasetio/datasetio.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/datasetio/datasetio.py rename to llama_stack/providers/inline/meta_reference/datasetio/datasetio.py diff --git a/llama_stack/providers/impls/meta_reference/eval/__init__.py b/llama_stack/providers/inline/meta_reference/eval/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/eval/__init__.py rename to llama_stack/providers/inline/meta_reference/eval/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/eval/config.py b/llama_stack/providers/inline/meta_reference/eval/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/eval/config.py rename to llama_stack/providers/inline/meta_reference/eval/config.py diff --git a/llama_stack/providers/impls/meta_reference/eval/eval.py b/llama_stack/providers/inline/meta_reference/eval/eval.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/eval/eval.py rename to llama_stack/providers/inline/meta_reference/eval/eval.py diff --git a/llama_stack/providers/impls/meta_reference/inference/__init__.py b/llama_stack/providers/inline/meta_reference/inference/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/__init__.py rename to llama_stack/providers/inline/meta_reference/inference/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/inference/config.py b/llama_stack/providers/inline/meta_reference/inference/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/config.py rename to llama_stack/providers/inline/meta_reference/inference/config.py diff --git a/llama_stack/providers/impls/meta_reference/inference/generation.py b/llama_stack/providers/inline/meta_reference/inference/generation.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/generation.py rename to llama_stack/providers/inline/meta_reference/inference/generation.py diff --git a/llama_stack/providers/impls/meta_reference/inference/inference.py b/llama_stack/providers/inline/meta_reference/inference/inference.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/inference.py rename to llama_stack/providers/inline/meta_reference/inference/inference.py diff --git a/llama_stack/providers/impls/meta_reference/inference/model_parallel.py b/llama_stack/providers/inline/meta_reference/inference/model_parallel.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/model_parallel.py rename to llama_stack/providers/inline/meta_reference/inference/model_parallel.py diff --git a/llama_stack/providers/impls/meta_reference/inference/parallel_utils.py b/llama_stack/providers/inline/meta_reference/inference/parallel_utils.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/parallel_utils.py rename to llama_stack/providers/inline/meta_reference/inference/parallel_utils.py diff --git a/llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/__init__.py b/llama_stack/providers/inline/meta_reference/inference/quantization/__init__.py similarity index 100% rename from llama_stack/providers/impls/braintrust/scoring/scoring_fn/fn_defs/__init__.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/fp8_impls.py b/llama_stack/providers/inline/meta_reference/inference/quantization/fp8_impls.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/fp8_impls.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/fp8_impls.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/fp8_txest_disabled.py b/llama_stack/providers/inline/meta_reference/inference/quantization/fp8_txest_disabled.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/fp8_txest_disabled.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/fp8_txest_disabled.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/hadamard_utils.py b/llama_stack/providers/inline/meta_reference/inference/quantization/hadamard_utils.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/hadamard_utils.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/hadamard_utils.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/loader.py b/llama_stack/providers/inline/meta_reference/inference/quantization/loader.py similarity index 99% rename from llama_stack/providers/impls/meta_reference/inference/quantization/loader.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/loader.py index 9f30354bb..3492ab043 100644 --- a/llama_stack/providers/impls/meta_reference/inference/quantization/loader.py +++ b/llama_stack/providers/inline/meta_reference/inference/quantization/loader.py @@ -27,7 +27,7 @@ from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear from llama_stack.apis.inference import QuantizationType -from llama_stack.providers.impls.meta_reference.inference.config import ( +from llama_stack.providers.inline.meta_reference.inference.config import ( MetaReferenceQuantizedInferenceConfig, ) diff --git a/llama_stack/providers/impls/meta_reference/__init__.py b/llama_stack/providers/inline/meta_reference/inference/quantization/scripts/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/__init__.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/scripts/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/scripts/build_conda.sh b/llama_stack/providers/inline/meta_reference/inference/quantization/scripts/build_conda.sh similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/scripts/build_conda.sh rename to llama_stack/providers/inline/meta_reference/inference/quantization/scripts/build_conda.sh diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/scripts/quantize_checkpoint.py b/llama_stack/providers/inline/meta_reference/inference/quantization/scripts/quantize_checkpoint.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/scripts/quantize_checkpoint.py rename to llama_stack/providers/inline/meta_reference/inference/quantization/scripts/quantize_checkpoint.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/scripts/run_quantize_checkpoint.sh b/llama_stack/providers/inline/meta_reference/inference/quantization/scripts/run_quantize_checkpoint.sh similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/scripts/run_quantize_checkpoint.sh rename to llama_stack/providers/inline/meta_reference/inference/quantization/scripts/run_quantize_checkpoint.sh diff --git a/llama_stack/providers/impls/meta_reference/memory/__init__.py b/llama_stack/providers/inline/meta_reference/memory/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/memory/__init__.py rename to llama_stack/providers/inline/meta_reference/memory/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/memory/config.py b/llama_stack/providers/inline/meta_reference/memory/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/memory/config.py rename to llama_stack/providers/inline/meta_reference/memory/config.py diff --git a/llama_stack/providers/impls/meta_reference/memory/faiss.py b/llama_stack/providers/inline/meta_reference/memory/faiss.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/memory/faiss.py rename to llama_stack/providers/inline/meta_reference/memory/faiss.py diff --git a/llama_stack/providers/impls/meta_reference/memory/tests/test_faiss.py b/llama_stack/providers/inline/meta_reference/memory/tests/test_faiss.py similarity index 93% rename from llama_stack/providers/impls/meta_reference/memory/tests/test_faiss.py rename to llama_stack/providers/inline/meta_reference/memory/tests/test_faiss.py index b09abc2ed..7b944319f 100644 --- a/llama_stack/providers/impls/meta_reference/memory/tests/test_faiss.py +++ b/llama_stack/providers/inline/meta_reference/memory/tests/test_faiss.py @@ -8,9 +8,9 @@ import tempfile import pytest from llama_stack.apis.memory import MemoryBankType, VectorMemoryBankDef -from llama_stack.providers.impls.meta_reference.memory.config import FaissImplConfig +from llama_stack.providers.inline.meta_reference.memory.config import FaissImplConfig -from llama_stack.providers.impls.meta_reference.memory.faiss import FaissMemoryImpl +from llama_stack.providers.inline.meta_reference.memory.faiss import FaissMemoryImpl from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig diff --git a/llama_stack/providers/impls/meta_reference/safety/__init__.py b/llama_stack/providers/inline/meta_reference/safety/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/__init__.py rename to llama_stack/providers/inline/meta_reference/safety/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/safety/base.py b/llama_stack/providers/inline/meta_reference/safety/base.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/base.py rename to llama_stack/providers/inline/meta_reference/safety/base.py diff --git a/llama_stack/providers/impls/meta_reference/safety/config.py b/llama_stack/providers/inline/meta_reference/safety/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/config.py rename to llama_stack/providers/inline/meta_reference/safety/config.py diff --git a/llama_stack/providers/impls/meta_reference/safety/llama_guard.py b/llama_stack/providers/inline/meta_reference/safety/llama_guard.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/llama_guard.py rename to llama_stack/providers/inline/meta_reference/safety/llama_guard.py diff --git a/llama_stack/providers/impls/meta_reference/safety/prompt_guard.py b/llama_stack/providers/inline/meta_reference/safety/prompt_guard.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/prompt_guard.py rename to llama_stack/providers/inline/meta_reference/safety/prompt_guard.py diff --git a/llama_stack/providers/impls/meta_reference/safety/safety.py b/llama_stack/providers/inline/meta_reference/safety/safety.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/safety/safety.py rename to llama_stack/providers/inline/meta_reference/safety/safety.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/__init__.py b/llama_stack/providers/inline/meta_reference/scoring/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/__init__.py rename to llama_stack/providers/inline/meta_reference/scoring/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/config.py b/llama_stack/providers/inline/meta_reference/scoring/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/config.py rename to llama_stack/providers/inline/meta_reference/scoring/config.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring.py b/llama_stack/providers/inline/meta_reference/scoring/scoring.py similarity index 94% rename from llama_stack/providers/impls/meta_reference/scoring/scoring.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring.py index 41b24a512..709b2f0c6 100644 --- a/llama_stack/providers/impls/meta_reference/scoring/scoring.py +++ b/llama_stack/providers/inline/meta_reference/scoring/scoring.py @@ -13,15 +13,15 @@ from llama_stack.apis.datasetio import * # noqa: F403 from llama_stack.apis.datasets import * # noqa: F403 from llama_stack.apis.inference.inference import Inference from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.equality_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.equality_scoring_fn import ( EqualityScoringFn, ) -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.llm_as_judge_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.llm_as_judge_scoring_fn import ( LlmAsJudgeScoringFn, ) -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.subset_of_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.subset_of_scoring_fn import ( SubsetOfScoringFn, ) diff --git a/llama_stack/providers/impls/meta_reference/agents/rag/__init__.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/rag/__init__.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/base_scoring_fn.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/base_scoring_fn.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/base_scoring_fn.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/base_scoring_fn.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/common.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/common.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/common.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/common.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/equality_scoring_fn.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/equality_scoring_fn.py similarity index 85% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/equality_scoring_fn.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/equality_scoring_fn.py index 556436286..2a0cd0578 100644 --- a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/equality_scoring_fn.py +++ b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/equality_scoring_fn.py @@ -4,18 +4,18 @@ # 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.impls.meta_reference.scoring.scoring_fn.base_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.base_scoring_fn import ( BaseScoringFn, ) from llama_stack.apis.scoring_functions import * # noqa: F401, F403 from llama_stack.apis.scoring import * # noqa: F401, F403 from llama_stack.apis.common.type_system import * # noqa: F403 -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.common import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.common import ( aggregate_accuracy, ) -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.fn_defs.equality import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.fn_defs.equality import ( equality, ) diff --git a/llama_stack/providers/impls/meta_reference/agents/tests/__init__.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tests/__init__.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/equality.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/equality.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/equality.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/equality.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/llm_as_judge_8b_correctness.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/llm_as_judge_8b_correctness.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/llm_as_judge_8b_correctness.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/llm_as_judge_8b_correctness.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/subset_of.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/subset_of.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/subset_of.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/fn_defs/subset_of.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py similarity index 90% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py index 5a5ce2550..84dd28fd7 100644 --- a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py +++ b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/llm_as_judge_scoring_fn.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. from llama_stack.apis.inference.inference import Inference -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.base_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.base_scoring_fn import ( BaseScoringFn, ) from llama_stack.apis.scoring_functions import * # noqa: F401, F403 @@ -12,10 +12,10 @@ from llama_stack.apis.scoring import * # noqa: F401, F403 from llama_stack.apis.common.type_system import * # noqa: F403 import re -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.common import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.common import ( aggregate_average, ) -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.fn_defs.llm_as_judge_8b_correctness import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.fn_defs.llm_as_judge_8b_correctness import ( llm_as_judge_8b_correctness, ) diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py similarity index 83% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py rename to llama_stack/providers/inline/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py index fcef2ead7..f42964c1f 100644 --- a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py +++ b/llama_stack/providers/inline/meta_reference/scoring/scoring_fn/subset_of_scoring_fn.py @@ -4,17 +4,17 @@ # 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.impls.meta_reference.scoring.scoring_fn.base_scoring_fn import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.base_scoring_fn import ( BaseScoringFn, ) from llama_stack.apis.scoring_functions import * # noqa: F401, F403 from llama_stack.apis.scoring import * # noqa: F401, F403 from llama_stack.apis.common.type_system import * # noqa: F403 -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.common import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.common import ( aggregate_accuracy, ) -from llama_stack.providers.impls.meta_reference.scoring.scoring_fn.fn_defs.subset_of import ( +from llama_stack.providers.inline.meta_reference.scoring.scoring_fn.fn_defs.subset_of import ( subset_of, ) diff --git a/llama_stack/providers/impls/meta_reference/telemetry/__init__.py b/llama_stack/providers/inline/meta_reference/telemetry/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/telemetry/__init__.py rename to llama_stack/providers/inline/meta_reference/telemetry/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/telemetry/config.py b/llama_stack/providers/inline/meta_reference/telemetry/config.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/telemetry/config.py rename to llama_stack/providers/inline/meta_reference/telemetry/config.py diff --git a/llama_stack/providers/impls/meta_reference/telemetry/console.py b/llama_stack/providers/inline/meta_reference/telemetry/console.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/telemetry/console.py rename to llama_stack/providers/inline/meta_reference/telemetry/console.py diff --git a/llama_stack/providers/impls/vllm/__init__.py b/llama_stack/providers/inline/vllm/__init__.py similarity index 100% rename from llama_stack/providers/impls/vllm/__init__.py rename to llama_stack/providers/inline/vllm/__init__.py diff --git a/llama_stack/providers/impls/vllm/config.py b/llama_stack/providers/inline/vllm/config.py similarity index 100% rename from llama_stack/providers/impls/vllm/config.py rename to llama_stack/providers/inline/vllm/config.py diff --git a/llama_stack/providers/impls/vllm/vllm.py b/llama_stack/providers/inline/vllm/vllm.py similarity index 100% rename from llama_stack/providers/impls/vllm/vllm.py rename to llama_stack/providers/inline/vllm/vllm.py diff --git a/llama_stack/providers/registry/agents.py b/llama_stack/providers/registry/agents.py index 8f4d3a03e..774dde858 100644 --- a/llama_stack/providers/registry/agents.py +++ b/llama_stack/providers/registry/agents.py @@ -22,8 +22,8 @@ def available_providers() -> List[ProviderSpec]: "scikit-learn", ] + kvstore_dependencies(), - module="llama_stack.providers.impls.meta_reference.agents", - config_class="llama_stack.providers.impls.meta_reference.agents.MetaReferenceAgentsImplConfig", + module="llama_stack.providers.inline.meta_reference.agents", + config_class="llama_stack.providers.inline.meta_reference.agents.MetaReferenceAgentsImplConfig", api_dependencies=[ Api.inference, Api.safety, @@ -36,8 +36,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="sample", pip_packages=[], - module="llama_stack.providers.adapters.agents.sample", - config_class="llama_stack.providers.adapters.agents.sample.SampleConfig", + module="llama_stack.providers.remote.agents.sample", + config_class="llama_stack.providers.remote.agents.sample.SampleConfig", ), ), ] diff --git a/llama_stack/providers/registry/datasetio.py b/llama_stack/providers/registry/datasetio.py index 27e80ff57..976bbd448 100644 --- a/llama_stack/providers/registry/datasetio.py +++ b/llama_stack/providers/registry/datasetio.py @@ -15,8 +15,8 @@ def available_providers() -> List[ProviderSpec]: api=Api.datasetio, provider_type="meta-reference", pip_packages=["pandas"], - module="llama_stack.providers.impls.meta_reference.datasetio", - config_class="llama_stack.providers.impls.meta_reference.datasetio.MetaReferenceDatasetIOConfig", + module="llama_stack.providers.inline.meta_reference.datasetio", + config_class="llama_stack.providers.inline.meta_reference.datasetio.MetaReferenceDatasetIOConfig", api_dependencies=[], ), ] diff --git a/llama_stack/providers/registry/eval.py b/llama_stack/providers/registry/eval.py index fc7c923d9..9b9ba6409 100644 --- a/llama_stack/providers/registry/eval.py +++ b/llama_stack/providers/registry/eval.py @@ -15,8 +15,8 @@ def available_providers() -> List[ProviderSpec]: api=Api.eval, provider_type="meta-reference", pip_packages=[], - module="llama_stack.providers.impls.meta_reference.eval", - config_class="llama_stack.providers.impls.meta_reference.eval.MetaReferenceEvalConfig", + module="llama_stack.providers.inline.meta_reference.eval", + config_class="llama_stack.providers.inline.meta_reference.eval.MetaReferenceEvalConfig", api_dependencies=[ Api.datasetio, Api.datasets, diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py index 717ff78a8..8a3619118 100644 --- a/llama_stack/providers/registry/inference.py +++ b/llama_stack/providers/registry/inference.py @@ -27,8 +27,8 @@ def available_providers() -> List[ProviderSpec]: api=Api.inference, provider_type="meta-reference", pip_packages=META_REFERENCE_DEPS, - module="llama_stack.providers.impls.meta_reference.inference", - config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceInferenceConfig", + module="llama_stack.providers.inline.meta_reference.inference", + config_class="llama_stack.providers.inline.meta_reference.inference.MetaReferenceInferenceConfig", ), InlineProviderSpec( api=Api.inference, @@ -40,16 +40,16 @@ def available_providers() -> List[ProviderSpec]: "torchao==0.5.0", ] ), - module="llama_stack.providers.impls.meta_reference.inference", - config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceQuantizedInferenceConfig", + module="llama_stack.providers.inline.meta_reference.inference", + config_class="llama_stack.providers.inline.meta_reference.inference.MetaReferenceQuantizedInferenceConfig", ), remote_provider_spec( api=Api.inference, adapter=AdapterSpec( adapter_type="sample", pip_packages=[], - module="llama_stack.providers.adapters.inference.sample", - config_class="llama_stack.providers.adapters.inference.sample.SampleConfig", + module="llama_stack.providers.remote.inference.sample", + config_class="llama_stack.providers.remote.inference.sample.SampleConfig", ), ), remote_provider_spec( @@ -57,8 +57,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="ollama", pip_packages=["ollama", "aiohttp"], - config_class="llama_stack.providers.adapters.inference.ollama.OllamaImplConfig", - module="llama_stack.providers.adapters.inference.ollama", + config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig", + module="llama_stack.providers.remote.inference.ollama", ), ), remote_provider_spec( @@ -66,8 +66,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="vllm", pip_packages=["openai"], - module="llama_stack.providers.adapters.inference.vllm", - config_class="llama_stack.providers.adapters.inference.vllm.VLLMInferenceAdapterConfig", + module="llama_stack.providers.remote.inference.vllm", + config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig", ), ), remote_provider_spec( @@ -75,8 +75,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="tgi", pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.adapters.inference.tgi", - config_class="llama_stack.providers.adapters.inference.tgi.TGIImplConfig", + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig", ), ), remote_provider_spec( @@ -84,8 +84,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="hf::serverless", pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.adapters.inference.tgi", - config_class="llama_stack.providers.adapters.inference.tgi.InferenceAPIImplConfig", + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig", ), ), remote_provider_spec( @@ -93,8 +93,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="hf::endpoint", pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.adapters.inference.tgi", - config_class="llama_stack.providers.adapters.inference.tgi.InferenceEndpointImplConfig", + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig", ), ), remote_provider_spec( @@ -104,8 +104,8 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "fireworks-ai", ], - module="llama_stack.providers.adapters.inference.fireworks", - config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig", + module="llama_stack.providers.remote.inference.fireworks", + config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig", ), ), remote_provider_spec( @@ -115,9 +115,9 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "together", ], - module="llama_stack.providers.adapters.inference.together", - config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig", - provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator", + module="llama_stack.providers.remote.inference.together", + config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig", + provider_data_validator="llama_stack.providers.remote.safety.together.TogetherProviderDataValidator", ), ), remote_provider_spec( @@ -125,8 +125,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="bedrock", pip_packages=["boto3"], - module="llama_stack.providers.adapters.inference.bedrock", - config_class="llama_stack.providers.adapters.inference.bedrock.BedrockConfig", + module="llama_stack.providers.remote.inference.bedrock", + config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig", ), ), remote_provider_spec( @@ -136,8 +136,8 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "openai", ], - module="llama_stack.providers.adapters.inference.databricks", - config_class="llama_stack.providers.adapters.inference.databricks.DatabricksImplConfig", + module="llama_stack.providers.remote.inference.databricks", + config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig", ), ), InlineProviderSpec( @@ -146,7 +146,7 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "vllm", ], - module="llama_stack.providers.impls.vllm", - config_class="llama_stack.providers.impls.vllm.VLLMConfig", + module="llama_stack.providers.inline.vllm", + config_class="llama_stack.providers.inline.vllm.VLLMConfig", ), ] diff --git a/llama_stack/providers/registry/memory.py b/llama_stack/providers/registry/memory.py index a0fbf1636..c2740017a 100644 --- a/llama_stack/providers/registry/memory.py +++ b/llama_stack/providers/registry/memory.py @@ -36,15 +36,15 @@ def available_providers() -> List[ProviderSpec]: api=Api.memory, provider_type="meta-reference", pip_packages=EMBEDDING_DEPS + ["faiss-cpu"], - module="llama_stack.providers.impls.meta_reference.memory", - config_class="llama_stack.providers.impls.meta_reference.memory.FaissImplConfig", + module="llama_stack.providers.inline.meta_reference.memory", + config_class="llama_stack.providers.inline.meta_reference.memory.FaissImplConfig", ), remote_provider_spec( Api.memory, AdapterSpec( adapter_type="chromadb", pip_packages=EMBEDDING_DEPS + ["chromadb-client"], - module="llama_stack.providers.adapters.memory.chroma", + module="llama_stack.providers.remote.memory.chroma", ), ), remote_provider_spec( @@ -52,8 +52,8 @@ def available_providers() -> List[ProviderSpec]: AdapterSpec( adapter_type="pgvector", pip_packages=EMBEDDING_DEPS + ["psycopg2-binary"], - module="llama_stack.providers.adapters.memory.pgvector", - config_class="llama_stack.providers.adapters.memory.pgvector.PGVectorConfig", + module="llama_stack.providers.remote.memory.pgvector", + config_class="llama_stack.providers.remote.memory.pgvector.PGVectorConfig", ), ), remote_provider_spec( @@ -61,9 +61,9 @@ def available_providers() -> List[ProviderSpec]: AdapterSpec( adapter_type="weaviate", pip_packages=EMBEDDING_DEPS + ["weaviate-client"], - module="llama_stack.providers.adapters.memory.weaviate", - config_class="llama_stack.providers.adapters.memory.weaviate.WeaviateConfig", - provider_data_validator="llama_stack.providers.adapters.memory.weaviate.WeaviateRequestProviderData", + module="llama_stack.providers.remote.memory.weaviate", + config_class="llama_stack.providers.remote.memory.weaviate.WeaviateConfig", + provider_data_validator="llama_stack.providers.remote.memory.weaviate.WeaviateRequestProviderData", ), ), remote_provider_spec( @@ -71,8 +71,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="sample", pip_packages=[], - module="llama_stack.providers.adapters.memory.sample", - config_class="llama_stack.providers.adapters.memory.sample.SampleConfig", + module="llama_stack.providers.remote.memory.sample", + config_class="llama_stack.providers.remote.memory.sample.SampleConfig", ), ), remote_provider_spec( @@ -80,8 +80,8 @@ def available_providers() -> List[ProviderSpec]: AdapterSpec( adapter_type="qdrant", pip_packages=EMBEDDING_DEPS + ["qdrant-client"], - module="llama_stack.providers.adapters.memory.qdrant", - config_class="llama_stack.providers.adapters.memory.qdrant.QdrantConfig", + module="llama_stack.providers.remote.memory.qdrant", + config_class="llama_stack.providers.remote.memory.qdrant.QdrantConfig", ), ), ] diff --git a/llama_stack/providers/registry/safety.py b/llama_stack/providers/registry/safety.py index 3fa62479a..9279d8df9 100644 --- a/llama_stack/providers/registry/safety.py +++ b/llama_stack/providers/registry/safety.py @@ -24,8 +24,8 @@ def available_providers() -> List[ProviderSpec]: "transformers", "torch --index-url https://download.pytorch.org/whl/cpu", ], - module="llama_stack.providers.impls.meta_reference.safety", - config_class="llama_stack.providers.impls.meta_reference.safety.SafetyConfig", + module="llama_stack.providers.inline.meta_reference.safety", + config_class="llama_stack.providers.inline.meta_reference.safety.SafetyConfig", api_dependencies=[ Api.inference, ], @@ -35,8 +35,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="sample", pip_packages=[], - module="llama_stack.providers.adapters.safety.sample", - config_class="llama_stack.providers.adapters.safety.sample.SampleConfig", + module="llama_stack.providers.remote.safety.sample", + config_class="llama_stack.providers.remote.safety.sample.SampleConfig", ), ), remote_provider_spec( @@ -44,8 +44,8 @@ def available_providers() -> List[ProviderSpec]: adapter=AdapterSpec( adapter_type="bedrock", pip_packages=["boto3"], - module="llama_stack.providers.adapters.safety.bedrock", - config_class="llama_stack.providers.adapters.safety.bedrock.BedrockSafetyConfig", + module="llama_stack.providers.remote.safety.bedrock", + config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig", ), ), remote_provider_spec( @@ -55,9 +55,9 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "together", ], - module="llama_stack.providers.adapters.safety.together", - config_class="llama_stack.providers.adapters.safety.together.TogetherSafetyConfig", - provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator", + module="llama_stack.providers.remote.safety.together", + config_class="llama_stack.providers.remote.safety.together.TogetherSafetyConfig", + provider_data_validator="llama_stack.providers.remote.safety.together.TogetherProviderDataValidator", ), ), InlineProviderSpec( @@ -66,8 +66,8 @@ def available_providers() -> List[ProviderSpec]: pip_packages=[ "codeshield", ], - module="llama_stack.providers.impls.meta_reference.codeshield", - config_class="llama_stack.providers.impls.meta_reference.codeshield.CodeShieldConfig", + module="llama_stack.providers.inline.meta_reference.codeshield", + config_class="llama_stack.providers.inline.meta_reference.codeshield.CodeShieldConfig", api_dependencies=[], ), ] diff --git a/llama_stack/providers/registry/scoring.py b/llama_stack/providers/registry/scoring.py index 81cb47764..2586083f6 100644 --- a/llama_stack/providers/registry/scoring.py +++ b/llama_stack/providers/registry/scoring.py @@ -15,8 +15,8 @@ def available_providers() -> List[ProviderSpec]: api=Api.scoring, provider_type="meta-reference", pip_packages=[], - module="llama_stack.providers.impls.meta_reference.scoring", - config_class="llama_stack.providers.impls.meta_reference.scoring.MetaReferenceScoringConfig", + module="llama_stack.providers.inline.meta_reference.scoring", + config_class="llama_stack.providers.inline.meta_reference.scoring.MetaReferenceScoringConfig", api_dependencies=[ Api.datasetio, Api.datasets, @@ -27,8 +27,8 @@ def available_providers() -> List[ProviderSpec]: api=Api.scoring, provider_type="braintrust", pip_packages=["autoevals", "openai"], - module="llama_stack.providers.impls.braintrust.scoring", - config_class="llama_stack.providers.impls.braintrust.scoring.BraintrustScoringConfig", + module="llama_stack.providers.inline.braintrust.scoring", + config_class="llama_stack.providers.inline.braintrust.scoring.BraintrustScoringConfig", api_dependencies=[ Api.datasetio, Api.datasets, diff --git a/llama_stack/providers/registry/telemetry.py b/llama_stack/providers/registry/telemetry.py index 39bcb75d8..050d890aa 100644 --- a/llama_stack/providers/registry/telemetry.py +++ b/llama_stack/providers/registry/telemetry.py @@ -15,16 +15,16 @@ def available_providers() -> List[ProviderSpec]: api=Api.telemetry, provider_type="meta-reference", pip_packages=[], - module="llama_stack.providers.impls.meta_reference.telemetry", - config_class="llama_stack.providers.impls.meta_reference.telemetry.ConsoleConfig", + module="llama_stack.providers.inline.meta_reference.telemetry", + config_class="llama_stack.providers.inline.meta_reference.telemetry.ConsoleConfig", ), remote_provider_spec( api=Api.telemetry, adapter=AdapterSpec( adapter_type="sample", pip_packages=[], - module="llama_stack.providers.adapters.telemetry.sample", - config_class="llama_stack.providers.adapters.telemetry.sample.SampleConfig", + module="llama_stack.providers.remote.telemetry.sample", + config_class="llama_stack.providers.remote.telemetry.sample.SampleConfig", ), ), remote_provider_spec( @@ -37,8 +37,8 @@ def available_providers() -> List[ProviderSpec]: "opentelemetry-exporter-jaeger", "opentelemetry-semantic-conventions", ], - module="llama_stack.providers.adapters.telemetry.opentelemetry", - config_class="llama_stack.providers.adapters.telemetry.opentelemetry.OpenTelemetryConfig", + module="llama_stack.providers.remote.telemetry.opentelemetry", + config_class="llama_stack.providers.remote.telemetry.opentelemetry.OpenTelemetryConfig", ), ), ] diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/__init__.py b/llama_stack/providers/remote/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/__init__.py rename to llama_stack/providers/remote/__init__.py diff --git a/llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/__init__.py b/llama_stack/providers/remote/agents/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/agents/tools/ipython_tool/__init__.py rename to llama_stack/providers/remote/agents/__init__.py diff --git a/llama_stack/providers/adapters/agents/sample/__init__.py b/llama_stack/providers/remote/agents/sample/__init__.py similarity index 100% rename from llama_stack/providers/adapters/agents/sample/__init__.py rename to llama_stack/providers/remote/agents/sample/__init__.py diff --git a/llama_stack/providers/adapters/agents/sample/config.py b/llama_stack/providers/remote/agents/sample/config.py similarity index 100% rename from llama_stack/providers/adapters/agents/sample/config.py rename to llama_stack/providers/remote/agents/sample/config.py diff --git a/llama_stack/providers/adapters/agents/sample/sample.py b/llama_stack/providers/remote/agents/sample/sample.py similarity index 100% rename from llama_stack/providers/adapters/agents/sample/sample.py rename to llama_stack/providers/remote/agents/sample/sample.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/__init__.py b/llama_stack/providers/remote/inference/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/__init__.py rename to llama_stack/providers/remote/inference/__init__.py diff --git a/llama_stack/providers/adapters/inference/bedrock/__init__.py b/llama_stack/providers/remote/inference/bedrock/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/bedrock/__init__.py rename to llama_stack/providers/remote/inference/bedrock/__init__.py diff --git a/llama_stack/providers/adapters/inference/bedrock/bedrock.py b/llama_stack/providers/remote/inference/bedrock/bedrock.py similarity index 99% rename from llama_stack/providers/adapters/inference/bedrock/bedrock.py rename to llama_stack/providers/remote/inference/bedrock/bedrock.py index 87b374de1..f569e0093 100644 --- a/llama_stack/providers/adapters/inference/bedrock/bedrock.py +++ b/llama_stack/providers/remote/inference/bedrock/bedrock.py @@ -15,7 +15,7 @@ from llama_stack.providers.utils.inference.model_registry import ModelRegistryHe from llama_stack.apis.inference import * # noqa: F403 -from llama_stack.providers.adapters.inference.bedrock.config import BedrockConfig +from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig from llama_stack.providers.utils.bedrock.client import create_bedrock_client diff --git a/llama_stack/providers/adapters/inference/bedrock/config.py b/llama_stack/providers/remote/inference/bedrock/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/bedrock/config.py rename to llama_stack/providers/remote/inference/bedrock/config.py diff --git a/llama_stack/providers/adapters/inference/databricks/__init__.py b/llama_stack/providers/remote/inference/databricks/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/databricks/__init__.py rename to llama_stack/providers/remote/inference/databricks/__init__.py diff --git a/llama_stack/providers/adapters/inference/databricks/config.py b/llama_stack/providers/remote/inference/databricks/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/databricks/config.py rename to llama_stack/providers/remote/inference/databricks/config.py diff --git a/llama_stack/providers/adapters/inference/databricks/databricks.py b/llama_stack/providers/remote/inference/databricks/databricks.py similarity index 100% rename from llama_stack/providers/adapters/inference/databricks/databricks.py rename to llama_stack/providers/remote/inference/databricks/databricks.py diff --git a/llama_stack/providers/adapters/inference/fireworks/__init__.py b/llama_stack/providers/remote/inference/fireworks/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/fireworks/__init__.py rename to llama_stack/providers/remote/inference/fireworks/__init__.py diff --git a/llama_stack/providers/adapters/inference/fireworks/config.py b/llama_stack/providers/remote/inference/fireworks/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/fireworks/config.py rename to llama_stack/providers/remote/inference/fireworks/config.py diff --git a/llama_stack/providers/adapters/inference/fireworks/fireworks.py b/llama_stack/providers/remote/inference/fireworks/fireworks.py similarity index 100% rename from llama_stack/providers/adapters/inference/fireworks/fireworks.py rename to llama_stack/providers/remote/inference/fireworks/fireworks.py diff --git a/llama_stack/providers/adapters/inference/ollama/__init__.py b/llama_stack/providers/remote/inference/ollama/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/ollama/__init__.py rename to llama_stack/providers/remote/inference/ollama/__init__.py diff --git a/llama_stack/providers/adapters/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py similarity index 100% rename from llama_stack/providers/adapters/inference/ollama/ollama.py rename to llama_stack/providers/remote/inference/ollama/ollama.py diff --git a/llama_stack/providers/adapters/inference/sample/__init__.py b/llama_stack/providers/remote/inference/sample/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/sample/__init__.py rename to llama_stack/providers/remote/inference/sample/__init__.py diff --git a/llama_stack/providers/adapters/inference/sample/config.py b/llama_stack/providers/remote/inference/sample/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/sample/config.py rename to llama_stack/providers/remote/inference/sample/config.py diff --git a/llama_stack/providers/adapters/inference/sample/sample.py b/llama_stack/providers/remote/inference/sample/sample.py similarity index 100% rename from llama_stack/providers/adapters/inference/sample/sample.py rename to llama_stack/providers/remote/inference/sample/sample.py diff --git a/llama_stack/providers/adapters/inference/tgi/__init__.py b/llama_stack/providers/remote/inference/tgi/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/tgi/__init__.py rename to llama_stack/providers/remote/inference/tgi/__init__.py diff --git a/llama_stack/providers/adapters/inference/tgi/config.py b/llama_stack/providers/remote/inference/tgi/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/tgi/config.py rename to llama_stack/providers/remote/inference/tgi/config.py diff --git a/llama_stack/providers/adapters/inference/tgi/tgi.py b/llama_stack/providers/remote/inference/tgi/tgi.py similarity index 100% rename from llama_stack/providers/adapters/inference/tgi/tgi.py rename to llama_stack/providers/remote/inference/tgi/tgi.py diff --git a/llama_stack/providers/adapters/inference/together/__init__.py b/llama_stack/providers/remote/inference/together/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/together/__init__.py rename to llama_stack/providers/remote/inference/together/__init__.py diff --git a/llama_stack/providers/adapters/inference/together/config.py b/llama_stack/providers/remote/inference/together/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/together/config.py rename to llama_stack/providers/remote/inference/together/config.py diff --git a/llama_stack/providers/adapters/inference/together/together.py b/llama_stack/providers/remote/inference/together/together.py similarity index 100% rename from llama_stack/providers/adapters/inference/together/together.py rename to llama_stack/providers/remote/inference/together/together.py diff --git a/llama_stack/providers/adapters/inference/vllm/__init__.py b/llama_stack/providers/remote/inference/vllm/__init__.py similarity index 100% rename from llama_stack/providers/adapters/inference/vllm/__init__.py rename to llama_stack/providers/remote/inference/vllm/__init__.py diff --git a/llama_stack/providers/adapters/inference/vllm/config.py b/llama_stack/providers/remote/inference/vllm/config.py similarity index 100% rename from llama_stack/providers/adapters/inference/vllm/config.py rename to llama_stack/providers/remote/inference/vllm/config.py diff --git a/llama_stack/providers/adapters/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py similarity index 100% rename from llama_stack/providers/adapters/inference/vllm/vllm.py rename to llama_stack/providers/remote/inference/vllm/vllm.py diff --git a/llama_stack/providers/impls/meta_reference/inference/quantization/scripts/__init__.py b/llama_stack/providers/remote/memory/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/inference/quantization/scripts/__init__.py rename to llama_stack/providers/remote/memory/__init__.py diff --git a/llama_stack/providers/adapters/memory/chroma/__init__.py b/llama_stack/providers/remote/memory/chroma/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/chroma/__init__.py rename to llama_stack/providers/remote/memory/chroma/__init__.py diff --git a/llama_stack/providers/adapters/memory/chroma/chroma.py b/llama_stack/providers/remote/memory/chroma/chroma.py similarity index 100% rename from llama_stack/providers/adapters/memory/chroma/chroma.py rename to llama_stack/providers/remote/memory/chroma/chroma.py diff --git a/llama_stack/providers/adapters/memory/pgvector/__init__.py b/llama_stack/providers/remote/memory/pgvector/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/pgvector/__init__.py rename to llama_stack/providers/remote/memory/pgvector/__init__.py diff --git a/llama_stack/providers/adapters/memory/pgvector/config.py b/llama_stack/providers/remote/memory/pgvector/config.py similarity index 100% rename from llama_stack/providers/adapters/memory/pgvector/config.py rename to llama_stack/providers/remote/memory/pgvector/config.py diff --git a/llama_stack/providers/adapters/memory/pgvector/pgvector.py b/llama_stack/providers/remote/memory/pgvector/pgvector.py similarity index 100% rename from llama_stack/providers/adapters/memory/pgvector/pgvector.py rename to llama_stack/providers/remote/memory/pgvector/pgvector.py diff --git a/llama_stack/providers/adapters/memory/qdrant/__init__.py b/llama_stack/providers/remote/memory/qdrant/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/qdrant/__init__.py rename to llama_stack/providers/remote/memory/qdrant/__init__.py diff --git a/llama_stack/providers/adapters/memory/qdrant/config.py b/llama_stack/providers/remote/memory/qdrant/config.py similarity index 100% rename from llama_stack/providers/adapters/memory/qdrant/config.py rename to llama_stack/providers/remote/memory/qdrant/config.py diff --git a/llama_stack/providers/adapters/memory/qdrant/qdrant.py b/llama_stack/providers/remote/memory/qdrant/qdrant.py similarity index 98% rename from llama_stack/providers/adapters/memory/qdrant/qdrant.py rename to llama_stack/providers/remote/memory/qdrant/qdrant.py index 45a8024ac..0f0df3dca 100644 --- a/llama_stack/providers/adapters/memory/qdrant/qdrant.py +++ b/llama_stack/providers/remote/memory/qdrant/qdrant.py @@ -16,7 +16,7 @@ from llama_stack.providers.datatypes import MemoryBanksProtocolPrivate from llama_stack.apis.memory import * # noqa: F403 -from llama_stack.providers.adapters.memory.qdrant.config import QdrantConfig +from llama_stack.providers.remote.memory.qdrant.config import QdrantConfig from llama_stack.providers.utils.memory.vector_store import ( BankWithIndex, EmbeddingIndex, diff --git a/llama_stack/providers/adapters/memory/sample/__init__.py b/llama_stack/providers/remote/memory/sample/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/sample/__init__.py rename to llama_stack/providers/remote/memory/sample/__init__.py diff --git a/llama_stack/providers/adapters/memory/sample/config.py b/llama_stack/providers/remote/memory/sample/config.py similarity index 100% rename from llama_stack/providers/adapters/memory/sample/config.py rename to llama_stack/providers/remote/memory/sample/config.py diff --git a/llama_stack/providers/adapters/memory/sample/sample.py b/llama_stack/providers/remote/memory/sample/sample.py similarity index 100% rename from llama_stack/providers/adapters/memory/sample/sample.py rename to llama_stack/providers/remote/memory/sample/sample.py diff --git a/llama_stack/providers/adapters/memory/weaviate/__init__.py b/llama_stack/providers/remote/memory/weaviate/__init__.py similarity index 100% rename from llama_stack/providers/adapters/memory/weaviate/__init__.py rename to llama_stack/providers/remote/memory/weaviate/__init__.py diff --git a/llama_stack/providers/adapters/memory/weaviate/config.py b/llama_stack/providers/remote/memory/weaviate/config.py similarity index 100% rename from llama_stack/providers/adapters/memory/weaviate/config.py rename to llama_stack/providers/remote/memory/weaviate/config.py diff --git a/llama_stack/providers/adapters/memory/weaviate/weaviate.py b/llama_stack/providers/remote/memory/weaviate/weaviate.py similarity index 100% rename from llama_stack/providers/adapters/memory/weaviate/weaviate.py rename to llama_stack/providers/remote/memory/weaviate/weaviate.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/__init__.py b/llama_stack/providers/remote/safety/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/__init__.py rename to llama_stack/providers/remote/safety/__init__.py diff --git a/llama_stack/providers/adapters/safety/bedrock/__init__.py b/llama_stack/providers/remote/safety/bedrock/__init__.py similarity index 100% rename from llama_stack/providers/adapters/safety/bedrock/__init__.py rename to llama_stack/providers/remote/safety/bedrock/__init__.py diff --git a/llama_stack/providers/adapters/safety/bedrock/bedrock.py b/llama_stack/providers/remote/safety/bedrock/bedrock.py similarity index 100% rename from llama_stack/providers/adapters/safety/bedrock/bedrock.py rename to llama_stack/providers/remote/safety/bedrock/bedrock.py diff --git a/llama_stack/providers/adapters/safety/bedrock/config.py b/llama_stack/providers/remote/safety/bedrock/config.py similarity index 100% rename from llama_stack/providers/adapters/safety/bedrock/config.py rename to llama_stack/providers/remote/safety/bedrock/config.py diff --git a/llama_stack/providers/adapters/safety/sample/__init__.py b/llama_stack/providers/remote/safety/sample/__init__.py similarity index 100% rename from llama_stack/providers/adapters/safety/sample/__init__.py rename to llama_stack/providers/remote/safety/sample/__init__.py diff --git a/llama_stack/providers/adapters/safety/sample/config.py b/llama_stack/providers/remote/safety/sample/config.py similarity index 100% rename from llama_stack/providers/adapters/safety/sample/config.py rename to llama_stack/providers/remote/safety/sample/config.py diff --git a/llama_stack/providers/adapters/safety/sample/sample.py b/llama_stack/providers/remote/safety/sample/sample.py similarity index 100% rename from llama_stack/providers/adapters/safety/sample/sample.py rename to llama_stack/providers/remote/safety/sample/sample.py diff --git a/llama_stack/providers/adapters/safety/together/__init__.py b/llama_stack/providers/remote/safety/together/__init__.py similarity index 100% rename from llama_stack/providers/adapters/safety/together/__init__.py rename to llama_stack/providers/remote/safety/together/__init__.py diff --git a/llama_stack/providers/adapters/safety/together/config.py b/llama_stack/providers/remote/safety/together/config.py similarity index 100% rename from llama_stack/providers/adapters/safety/together/config.py rename to llama_stack/providers/remote/safety/together/config.py diff --git a/llama_stack/providers/adapters/safety/together/together.py b/llama_stack/providers/remote/safety/together/together.py similarity index 100% rename from llama_stack/providers/adapters/safety/together/together.py rename to llama_stack/providers/remote/safety/together/together.py diff --git a/llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/__init__.py b/llama_stack/providers/remote/telemetry/__init__.py similarity index 100% rename from llama_stack/providers/impls/meta_reference/scoring/scoring_fn/fn_defs/__init__.py rename to llama_stack/providers/remote/telemetry/__init__.py diff --git a/llama_stack/providers/adapters/telemetry/opentelemetry/__init__.py b/llama_stack/providers/remote/telemetry/opentelemetry/__init__.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/opentelemetry/__init__.py rename to llama_stack/providers/remote/telemetry/opentelemetry/__init__.py diff --git a/llama_stack/providers/adapters/telemetry/opentelemetry/config.py b/llama_stack/providers/remote/telemetry/opentelemetry/config.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/opentelemetry/config.py rename to llama_stack/providers/remote/telemetry/opentelemetry/config.py diff --git a/llama_stack/providers/adapters/telemetry/opentelemetry/opentelemetry.py b/llama_stack/providers/remote/telemetry/opentelemetry/opentelemetry.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/opentelemetry/opentelemetry.py rename to llama_stack/providers/remote/telemetry/opentelemetry/opentelemetry.py diff --git a/llama_stack/providers/adapters/telemetry/sample/__init__.py b/llama_stack/providers/remote/telemetry/sample/__init__.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/sample/__init__.py rename to llama_stack/providers/remote/telemetry/sample/__init__.py diff --git a/llama_stack/providers/adapters/telemetry/sample/config.py b/llama_stack/providers/remote/telemetry/sample/config.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/sample/config.py rename to llama_stack/providers/remote/telemetry/sample/config.py diff --git a/llama_stack/providers/adapters/telemetry/sample/sample.py b/llama_stack/providers/remote/telemetry/sample/sample.py similarity index 100% rename from llama_stack/providers/adapters/telemetry/sample/sample.py rename to llama_stack/providers/remote/telemetry/sample/sample.py diff --git a/llama_stack/providers/tests/agents/fixtures.py b/llama_stack/providers/tests/agents/fixtures.py index 153ade0da..86ecae1e9 100644 --- a/llama_stack/providers/tests/agents/fixtures.py +++ b/llama_stack/providers/tests/agents/fixtures.py @@ -11,7 +11,7 @@ import pytest_asyncio from llama_stack.distribution.datatypes import Api, Provider -from llama_stack.providers.impls.meta_reference.agents import ( +from llama_stack.providers.inline.meta_reference.agents import ( MetaReferenceAgentsImplConfig, ) diff --git a/llama_stack/providers/tests/inference/fixtures.py b/llama_stack/providers/tests/inference/fixtures.py index acff151cf..9db70888e 100644 --- a/llama_stack/providers/tests/inference/fixtures.py +++ b/llama_stack/providers/tests/inference/fixtures.py @@ -10,15 +10,16 @@ import pytest import pytest_asyncio from llama_stack.distribution.datatypes import Api, Provider - -from llama_stack.providers.adapters.inference.fireworks import FireworksImplConfig -from llama_stack.providers.adapters.inference.ollama import OllamaImplConfig -from llama_stack.providers.adapters.inference.together import TogetherImplConfig -from llama_stack.providers.adapters.inference.vllm import VLLMInferenceAdapterConfig -from llama_stack.providers.impls.meta_reference.inference import ( +from llama_stack.providers.inline.meta_reference.inference import ( MetaReferenceInferenceConfig, ) + +from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig +from llama_stack.providers.remote.inference.ollama import OllamaImplConfig +from llama_stack.providers.remote.inference.together import TogetherImplConfig +from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2 + from ..conftest import ProviderFixture, remote_stack_fixture from ..env import get_env_or_fail diff --git a/llama_stack/providers/tests/memory/fixtures.py b/llama_stack/providers/tests/memory/fixtures.py index c5e41d32d..b30e0fae4 100644 --- a/llama_stack/providers/tests/memory/fixtures.py +++ b/llama_stack/providers/tests/memory/fixtures.py @@ -11,9 +11,9 @@ import pytest import pytest_asyncio from llama_stack.distribution.datatypes import Api, Provider -from llama_stack.providers.adapters.memory.pgvector import PGVectorConfig -from llama_stack.providers.adapters.memory.weaviate import WeaviateConfig -from llama_stack.providers.impls.meta_reference.memory import FaissImplConfig +from llama_stack.providers.inline.meta_reference.memory import FaissImplConfig +from llama_stack.providers.remote.memory.pgvector import PGVectorConfig +from llama_stack.providers.remote.memory.weaviate import WeaviateConfig from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2 from llama_stack.providers.utils.kvstore import SqliteKVStoreConfig diff --git a/llama_stack/providers/tests/safety/fixtures.py b/llama_stack/providers/tests/safety/fixtures.py index 74f8ef503..4789558ff 100644 --- a/llama_stack/providers/tests/safety/fixtures.py +++ b/llama_stack/providers/tests/safety/fixtures.py @@ -8,11 +8,11 @@ import pytest import pytest_asyncio from llama_stack.distribution.datatypes import Api, Provider -from llama_stack.providers.adapters.safety.together import TogetherSafetyConfig -from llama_stack.providers.impls.meta_reference.safety import ( +from llama_stack.providers.inline.meta_reference.safety import ( LlamaGuardShieldConfig, SafetyConfig, ) +from llama_stack.providers.remote.safety.together import TogetherSafetyConfig from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2