forked from phoenix-oss/llama-stack-mirror
8de8eb03c8
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
72 lines
2.4 KiB
Python
72 lines
2.4 KiB
Python
# 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, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.inference import * # noqa: F403
|
|
|
|
|
|
@json_schema_type
|
|
class BatchCompletionRequest(BaseModel):
|
|
model: str
|
|
content_batch: List[InterleavedContent]
|
|
sampling_params: Optional[SamplingParams] = SamplingParams()
|
|
logprobs: Optional[LogProbConfig] = None
|
|
|
|
|
|
@json_schema_type
|
|
class BatchCompletionResponse(BaseModel):
|
|
completion_message_batch: List[CompletionMessage]
|
|
|
|
|
|
@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]
|
|
|
|
|
|
@runtime_checkable
|
|
class BatchInference(Protocol):
|
|
@webmethod(route="/batch-inference/completion")
|
|
async def batch_completion(
|
|
self,
|
|
model: str,
|
|
content_batch: List[InterleavedContent],
|
|
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchCompletionResponse: ...
|
|
|
|
@webmethod(route="/batch-inference/chat-completion")
|
|
async def batch_chat_completion(
|
|
self,
|
|
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]] = list,
|
|
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
|
|
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchChatCompletionResponse: ...
|