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

llama_stack/apis/inference/__init__.py

@@ -0,0 +1,7 @@
+# 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 .inference import *  # noqa: F401 F403

llama_stack/apis/inference/client.py

@@ -0,0 +1,107 @@
+# 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 Any, AsyncGenerator
+
+import fire
+import httpx
+
+from llama_stack.core.datatypes import RemoteProviderConfig
+from pydantic import BaseModel
+from termcolor import cprint
+
+from .event_logger import EventLogger
+
+from .inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionResponseStreamChunk,
+    CompletionRequest,
+    Inference,
+    UserMessage,
+)
+
+
+async def get_client_impl(config: RemoteProviderConfig, _deps: Any) -> Inference:
+    return InferenceClient(config.url)
+
+
+def encodable_dict(d: BaseModel):
+    return json.loads(d.json())
+
+
+class InferenceClient(Inference):
+    def __init__(self, base_url: str):
+        self.base_url = base_url
+
+    async def initialize(self) -> None:
+        pass
+
+    async def shutdown(self) -> None:
+        pass
+
+    async def completion(self, request: CompletionRequest) -> AsyncGenerator:
+        raise NotImplementedError()
+
+    async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
+        async with httpx.AsyncClient() as client:
+            async with client.stream(
+                "POST",
+                f"{self.base_url}/inference/chat_completion",
+                json=encodable_dict(request),
+                headers={"Content-Type": "application/json"},
+                timeout=20,
+            ) as response:
+                if response.status_code != 200:
+                    content = await response.aread()
+                    cprint(
+                        f"Error: HTTP {response.status_code} {content.decode()}", "red"
+                    )
+                    return
+
+                async for line in response.aiter_lines():
+                    if line.startswith("data:"):
+                        data = line[len("data: ") :]
+                        try:
+                            if request.stream:
+                                if "error" in data:
+                                    cprint(data, "red")
+                                    continue
+
+                                yield ChatCompletionResponseStreamChunk(
+                                    **json.loads(data)
+                                )
+                            else:
+                                yield ChatCompletionResponse(**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, stream: bool):
+    client = InferenceClient(f"http://{host}:{port}")
+
+    message = UserMessage(content="hello world, troll me in two-paragraphs about 42")
+    cprint(f"User>{message.content}", "green")
+    iterator = client.chat_completion(
+        ChatCompletionRequest(
+            model="Meta-Llama3.1-8B-Instruct",
+            messages=[message],
+            stream=stream,
+        )
+    )
+    async for log in EventLogger().log(iterator):
+        log.print()
+
+
+def main(host: str, port: int, stream: bool = True):
+    asyncio.run(run_main(host, port, stream))
+
+
+if __name__ == "__main__":
+    fire.Fire(main)

llama_stack/apis/inference/inference.py

@@ -0,0 +1,205 @@
+# 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 enum import Enum
+
+from typing import List, Literal, Optional, Protocol, Union
+
+from llama_models.schema_utils import json_schema_type, webmethod
+
+from pydantic import BaseModel, Field
+from typing_extensions import Annotated
+
+from llama_models.llama3.api.datatypes import *  # noqa: F403
+
+
+class LogProbConfig(BaseModel):
+    top_k: Optional[int] = 0
+
+
+@json_schema_type
+class QuantizationType(Enum):
+    bf16 = "bf16"
+    fp8 = "fp8"
+
+
+@json_schema_type
+class Fp8QuantizationConfig(BaseModel):
+    type: Literal[QuantizationType.fp8.value] = QuantizationType.fp8.value
+
+
+@json_schema_type
+class Bf16QuantizationConfig(BaseModel):
+    type: Literal[QuantizationType.bf16.value] = QuantizationType.bf16.value
+
+
+QuantizationConfig = Annotated[
+    Union[Bf16QuantizationConfig, Fp8QuantizationConfig],
+    Field(discriminator="type"),
+]
+
+
+@json_schema_type
+class ChatCompletionResponseEventType(Enum):
+    start = "start"
+    complete = "complete"
+    progress = "progress"
+
+
+@json_schema_type
+class ToolCallParseStatus(Enum):
+    started = "started"
+    in_progress = "in_progress"
+    failure = "failure"
+    success = "success"
+
+
+@json_schema_type
+class ToolCallDelta(BaseModel):
+    content: Union[str, ToolCall]
+    parse_status: ToolCallParseStatus
+
+
+@json_schema_type
+class ChatCompletionResponseEvent(BaseModel):
+    """Chat completion response event."""
+
+    event_type: ChatCompletionResponseEventType
+    delta: Union[str, ToolCallDelta]
+    logprobs: Optional[List[TokenLogProbs]] = None
+    stop_reason: Optional[StopReason] = None
+
+
+@json_schema_type
+class CompletionRequest(BaseModel):
+    model: str
+    content: InterleavedTextMedia
+    sampling_params: Optional[SamplingParams] = SamplingParams()
+
+    stream: Optional[bool] = False
+    logprobs: Optional[LogProbConfig] = None
+
+
+@json_schema_type
+class CompletionResponse(BaseModel):
+    """Completion response."""
+
+    completion_message: CompletionMessage
+    logprobs: Optional[List[TokenLogProbs]] = None
+
+
+@json_schema_type
+class CompletionResponseStreamChunk(BaseModel):
+    """streamed completion response."""
+
+    delta: str
+    stop_reason: Optional[StopReason] = None
+    logprobs: Optional[List[TokenLogProbs]] = None
+
+
+@json_schema_type
+class BatchCompletionRequest(BaseModel):
+    model: str
+    content_batch: List[InterleavedTextMedia]
+    sampling_params: Optional[SamplingParams] = SamplingParams()
+    logprobs: Optional[LogProbConfig] = None
+
+
+@json_schema_type
+class BatchCompletionResponse(BaseModel):
+    """Batch completion response."""
+
+    completion_message_batch: List[CompletionMessage]
+
+
+@json_schema_type
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: List[Message]
+    sampling_params: Optional[SamplingParams] = SamplingParams()
+
+    # zero-shot tool definitions as input to the model
+    tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
+    tool_choice: Optional[ToolChoice] = Field(default=ToolChoice.auto)
+    tool_prompt_format: Optional[ToolPromptFormat] = Field(
+        default=ToolPromptFormat.json
+    )
+
+    stream: Optional[bool] = False
+    logprobs: Optional[LogProbConfig] = None
+
+
+@json_schema_type
+class ChatCompletionResponseStreamChunk(BaseModel):
+    """SSE-stream of these events."""
+
+    event: ChatCompletionResponseEvent
+
+
+@json_schema_type
+class ChatCompletionResponse(BaseModel):
+    """Chat completion response."""
+
+    completion_message: CompletionMessage
+    logprobs: Optional[List[TokenLogProbs]] = None
+
+
+@json_schema_type
+class BatchChatCompletionRequest(BaseModel):
+    model: str
+    messages_batch: List[List[Message]]
+    sampling_params: Optional[SamplingParams] = SamplingParams()
+
+    # zero-shot tool definitions as input to the model
+    tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
+    tool_choice: Optional[ToolChoice] = Field(default=ToolChoice.auto)
+    tool_prompt_format: Optional[ToolPromptFormat] = Field(
+        default=ToolPromptFormat.json
+    )
+    logprobs: Optional[LogProbConfig] = None
+
+
+@json_schema_type
+class BatchChatCompletionResponse(BaseModel):
+    completion_message_batch: List[CompletionMessage]
+
+
+@json_schema_type
+class EmbeddingsResponse(BaseModel):
+    embeddings: List[List[float]]
+
+
+class Inference(Protocol):
+    @webmethod(route="/inference/completion")
+    async def completion(
+        self,
+        model: str,
+        content: InterleavedTextMedia,
+        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        stream: Optional[bool] = False,
+        logprobs: Optional[LogProbConfig] = None,
+    ) -> Union[CompletionResponse, CompletionResponseStreamChunk]: ...
+
+    @webmethod(route="/inference/chat_completion")
+    async def chat_completion(
+        self,
+        model: str,
+        messages: List[Message],
+        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        # zero-shot tool definitions as input to the model
+        tools: Optional[List[ToolDefinition]] = list,
+        tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+        tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+        stream: Optional[bool] = False,
+        logprobs: Optional[LogProbConfig] = None,
+    ) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]: ...
+
+    @webmethod(route="/inference/embeddings")
+    async def embeddings(
+        self,
+        model: str,
+        contents: List[InterleavedTextMedia],
+    ) -> EmbeddingsResponse: ...