API Updates (#73)

* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

llama_stack/providers/registry/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.

llama_stack/providers/registry/agents.py

@@ -0,0 +1,33 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from llama_stack.distribution.datatypes import Api, InlineProviderSpec, ProviderSpec
+
+
+def available_providers() -> List[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.agents,
+            provider_id="meta-reference",
+            pip_packages=[
+                "matplotlib",
+                "pillow",
+                "pandas",
+                "scikit-learn",
+                "torch",
+                "transformers",
+            ],
+            module="llama_stack.providers.impls.meta_reference.agents",
+            config_class="llama_stack.providers.impls.meta_reference.agents.MetaReferenceImplConfig",
+            api_dependencies=[
+                Api.inference,
+                Api.safety,
+                Api.memory,
+            ],
+        ),
+    ]

llama_stack/providers/registry/inference.py

@@ -0,0 +1,68 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from llama_stack.distribution.datatypes import *  # noqa: F403
+
+
+def available_providers() -> List[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.inference,
+            provider_id="meta-reference",
+            pip_packages=[
+                "accelerate",
+                "blobfile",
+                "fairscale",
+                "fbgemm-gpu==0.8.0",
+                "torch",
+                "transformers",
+                "zmq",
+            ],
+            module="llama_stack.providers.impls.meta_reference.inference",
+            config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceImplConfig",
+        ),
+        remote_provider_spec(
+            api=Api.inference,
+            adapter=AdapterSpec(
+                adapter_id="ollama",
+                pip_packages=["ollama"],
+                module="llama_stack.providers.adapters.inference.ollama",
+            ),
+        ),
+        remote_provider_spec(
+            api=Api.inference,
+            adapter=AdapterSpec(
+                adapter_id="tgi",
+                pip_packages=["huggingface_hub"],
+                module="llama_stack.providers.adapters.inference.tgi",
+                config_class="llama_stack.providers.adapters.inference.tgi.TGIImplConfig",
+            ),
+        ),
+        remote_provider_spec(
+            api=Api.inference,
+            adapter=AdapterSpec(
+                adapter_id="fireworks",
+                pip_packages=[
+                    "fireworks-ai",
+                ],
+                module="llama_stack.providers.adapters.inference.fireworks",
+                config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig",
+            ),
+        ),
+        remote_provider_spec(
+            api=Api.inference,
+            adapter=AdapterSpec(
+                adapter_id="together",
+                pip_packages=[
+                    "together",
+                ],
+                module="llama_stack.providers.adapters.inference.together",
+                config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
+            ),
+        ),
+    ]

llama_stack/providers/registry/memory.py

@@ -0,0 +1,45 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from llama_stack.distribution.datatypes import *  # noqa: F403
+
+EMBEDDING_DEPS = [
+    "blobfile",
+    "chardet",
+    "pypdf",
+    "sentence-transformers",
+]
+
+
+def available_providers() -> List[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.memory,
+            provider_id="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",
+        ),
+        remote_provider_spec(
+            Api.memory,
+            AdapterSpec(
+                adapter_id="chromadb",
+                pip_packages=EMBEDDING_DEPS + ["chromadb-client"],
+                module="llama_stack.providers.adapters.memory.chroma",
+            ),
+        ),
+        remote_provider_spec(
+            Api.memory,
+            AdapterSpec(
+                adapter_id="pgvector",
+                pip_packages=EMBEDDING_DEPS + ["psycopg2-binary"],
+                module="llama_stack.providers.adapters.memory.pgvector",
+                config_class="llama_stack.providers.adapters.memory.pgvector.PGVectorConfig",
+            ),
+        ),
+    ]

llama_stack/providers/registry/safety.py

@@ -0,0 +1,26 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from llama_stack.distribution.datatypes import Api, InlineProviderSpec, ProviderSpec
+
+
+def available_providers() -> List[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.safety,
+            provider_id="meta-reference",
+            pip_packages=[
+                "accelerate",
+                "codeshield",
+                "torch",
+                "transformers",
+            ],
+            module="llama_stack.providers.impls.meta_reference.safety",
+            config_class="llama_stack.providers.impls.meta_reference.safety.SafetyConfig",
+        ),
+    ]

llama_stack/providers/registry/telemetry.py

@@ -0,0 +1,21 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from llama_stack.distribution.datatypes import *  # noqa: F403
+
+
+def available_providers() -> List[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.telemetry,
+            provider_id="meta-reference",
+            pip_packages=[],
+            module="llama_stack.providers.impls.meta_reference.telemetry",
+            config_class="llama_stack.providers.impls.meta_reference.telemetry.ConsoleConfig",
+        ),
+    ]