Introduce Llama stack distributions (#22)

* Add distribution CLI scaffolding

* More progress towards `llama distribution install`

* getting closer to a distro definition, distro install + configure works

* Distribution server now functioning

* read existing configuration, save enums properly

* Remove inference uvicorn server entrypoint and llama inference CLI command

* updated dependency and client model name

* Improved exception handling

* local imports for faster cli

* undo a typo, add a passthrough distribution

* implement full-passthrough in the server

* add safety adapters, configuration handling, server + clients

* cleanup, moving stuff to common, nuke utils

* Add a Path() wrapper at the earliest place

* fixes

* Bring agentic system api to toolchain

Add adapter dependencies and resolve adapters using a topological sort

* refactor to reduce size of `agentic_system`

* move straggler files and fix some important existing bugs

* ApiSurface -> Api

* refactor a method out

* Adapter -> Provider

* Make each inference provider into its own subdirectory

* installation fixes

* Rename Distribution -> DistributionSpec, simplify RemoteProviders

* dict key instead of attr

* update inference config to take model and not model_dir

* Fix passthrough streaming, send headers properly not part of body :facepalm

* update safety to use model sku ids and not model dirs

* Update cli_reference.md

* minor fixes

* add DistributionConfig, fix a bug in model download

* Make install + start scripts do proper configuration automatically

* Update CLI_reference

* Nuke fp8_requirements, fold fbgemm into common requirements

* Update README, add newline between API surface configurations

* Refactor download functionality out of the Command so can be reused

* Add `llama model download` alias for `llama download`

* Show message about checksum file so users can check themselves

* Simpler intro statements

* get ollama working

* Reduce a bunch of dependencies from toolchain

Some improvements to the distribution install script

* Avoid using `conda run` since it buffers everything

* update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes

* add validation for configuration input

* resort imports

* make optional subclasses default to yes for configuration

* Remove additional_pip_packages; move deps to providers

* for inline make 8b model the default

* Add scripts to MANIFEST

* allow installing from test.pypi.org

* Fix #2 to help with testing packages

* Must install llama-models at that same version first

* fix PIP_ARGS

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Hardik Shah <hjshah@meta.com>

llama_toolchain/agentic_system/client.py

@@ -0,0 +1,130 @@
+# 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.
+
+import asyncio
+import json
+
+from typing import AsyncGenerator
+
+import fire
+
+import httpx
+
+from llama_models.llama3_1.api.datatypes import BuiltinTool, SamplingParams
+
+from .api import (
+    AgenticSystem,
+    AgenticSystemCreateRequest,
+    AgenticSystemCreateResponse,
+    AgenticSystemInstanceConfig,
+    AgenticSystemSessionCreateRequest,
+    AgenticSystemSessionCreateResponse,
+    AgenticSystemToolDefinition,
+    AgenticSystemTurnCreateRequest,
+    AgenticSystemTurnResponseStreamChunk,
+)
+
+
+async def get_client_impl(base_url: str):
+    return AgenticSystemClient(base_url)
+
+
+class AgenticSystemClient(AgenticSystem):
+    def __init__(self, base_url: str):
+        self.base_url = base_url
+
+    async def create_agentic_system(
+        self, request: AgenticSystemCreateRequest
+    ) -> AgenticSystemCreateResponse:
+        async with httpx.AsyncClient() as client:
+            response = await client.post(
+                f"{self.base_url}/agentic_system/create",
+                data=request.json(),
+                headers={"Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            return AgenticSystemCreateResponse(**response.json())
+
+    async def create_agentic_system_session(
+        self,
+        request: AgenticSystemSessionCreateRequest,
+    ) -> AgenticSystemSessionCreateResponse:
+        async with httpx.AsyncClient() as client:
+            response = await client.post(
+                f"{self.base_url}/agentic_system/session/create",
+                data=request.json(),
+                headers={"Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            return AgenticSystemSessionCreateResponse(**response.json())
+
+    async def create_agentic_system_turn(
+        self,
+        request: AgenticSystemTurnCreateRequest,
+    ) -> AsyncGenerator:
+        async with httpx.AsyncClient() as client:
+            async with client.stream(
+                "POST",
+                f"{self.base_url}/agentic_system/turn/create",
+                data=request.json(),
+                headers={"Content-Type": "application/json"},
+                timeout=20,
+            ) as response:
+                async for line in response.aiter_lines():
+                    if line.startswith("data:"):
+                        data = line[len("data: ") :]
+                        try:
+                            yield AgenticSystemTurnResponseStreamChunk(
+                                **json.loads(data)
+                            )
+                        except Exception as e:
+                            print(data)
+                            print(f"Error with parsing or validation: {e}")
+
+
+async def run_main(host: str, port: int):
+    # client to test remote impl of agentic system
+    api = await AgenticSystemClient(f"http://{host}:{port}")
+
+    tool_definitions = [
+        AgenticSystemToolDefinition(
+            tool_name=BuiltinTool.brave_search,
+        ),
+        AgenticSystemToolDefinition(
+            tool_name=BuiltinTool.wolfram_alpha,
+        ),
+        AgenticSystemToolDefinition(
+            tool_name=BuiltinTool.photogen,
+        ),
+        AgenticSystemToolDefinition(
+            tool_name=BuiltinTool.code_interpreter,
+        ),
+    ]
+
+    create_request = AgenticSystemCreateRequest(
+        model="Meta-Llama3.1-8B-Instruct",
+        instance_config=AgenticSystemInstanceConfig(
+            instructions="You are a helpful assistant",
+            sampling_params=SamplingParams(),
+            available_tools=tool_definitions,
+            input_shields=[],
+            output_shields=[],
+            quantization_config=None,
+            debug_prefix_messages=[],
+        ),
+    )
+
+    create_response = await api.create_agentic_system(create_request)
+    print(create_response)
+    # TODO: Add chat session / turn apis to test e2e
+
+
+def main(host: str, port: int):
+    asyncio.run(run_main(host, port))
+
+
+if __name__ == "__main__":
+    fire.Fire(main)