forked from phoenix-oss/llama-stack-mirror
* add tools to chat completion request * use templates for generating system prompts * Moved ToolPromptFormat and jinja templates to llama_models.llama3.api * <WIP> memory changes - inlined AgenticSystemInstanceConfig so API feels more ergonomic - renamed it to AgentConfig, AgentInstance -> Agent - added a MemoryConfig and `memory` parameter - added `attachments` to input and `output_attachments` to the response - some naming changes * InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool * flesh out memory banks API * agentic loop has a RAG implementation * faiss provider implementation * memory client works * re-work tool definitions, fix FastAPI issues, fix tool regressions * fix agentic_system utils * basic RAG seems to work * small bug fixes for inline attachments * Refactor custom tool execution utilities * Bug fix, show memory retrieval steps in EventLogger * No need for api_key for Remote providers * add special unicode character ↵ to showcase newlines in model prompt templates * remove api.endpoints imports * combine datatypes.py and endpoints.py into api.py * Attachment / add TTL api * split batch_inference from inference * minor import fixes * use a single impl for ChatFormat.decode_assistant_mesage * use interleaved_text_media_as_str() utilityt * Fix api.datatypes imports * Add blobfile for tiktoken * Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly * templates take optional --format={json,function_tag} * Rag Updates * Add `api build` subcommand -- WIP * fix * build + run image seems to work * <WIP> adapters * bunch more work to make adapters work * api build works for conda now * ollama remote adapter works * Several smaller fixes to make adapters work Also, reorganized the pattern of __init__ inside providers so configuration can stay lightweight * llama distribution -> llama stack + containers (WIP) * All the new CLI for api + stack work * Make Fireworks and Together into the Adapter format * Some quick fixes to the CLI behavior to make it consistent * Updated README phew * Update cli_reference.md * llama_toolchain/distribution -> llama_toolchain/core * Add termcolor * update paths * Add a log just for consistency * chmod +x scripts * Fix api dependencies not getting added to configuration * missing import lol * Delete utils.py; move to agentic system * Support downloading of URLs for attachments for code interpreter * Simplify and generalize `llama api build` yay * Update `llama stack configure` to be very simple also * Fix stack start * Allow building an "adhoc" distribution * Remote `llama api []` subcommands * Fixes to llama stack commands and update docs * Update documentation again and add error messages to llama stack start * llama stack start -> llama stack run * Change name of build for less confusion * Add pyopenapi fork to the repository, update RFC assets * Remove conflicting annotation * Added a "--raw" option for model template printing --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com> Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com>
122 lines
3 KiB
Python
122 lines
3 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 enum import Enum
|
|
from typing import List, Protocol
|
|
|
|
from llama_models.schema_utils import webmethod
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_toolchain.dataset.api import * # noqa: F403
|
|
from llama_toolchain.common.training_types import * # noqa: F403
|
|
|
|
|
|
class TextGenerationMetric(Enum):
|
|
perplexity = "perplexity"
|
|
rouge = "rouge"
|
|
bleu = "bleu"
|
|
|
|
|
|
class QuestionAnsweringMetric(Enum):
|
|
em = "em"
|
|
f1 = "f1"
|
|
|
|
|
|
class SummarizationMetric(Enum):
|
|
rouge = "rouge"
|
|
bleu = "bleu"
|
|
|
|
|
|
class EvaluationJob(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
class EvaluationJobLogStream(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
class EvaluateTaskRequestCommon(BaseModel):
|
|
job_uuid: str
|
|
dataset: TrainEvalDataset
|
|
|
|
checkpoint: Checkpoint
|
|
|
|
# generation params
|
|
sampling_params: SamplingParams = SamplingParams()
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateTextGenerationRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate text generation."""
|
|
|
|
metrics: List[TextGenerationMetric]
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateQuestionAnsweringRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate question answering."""
|
|
|
|
metrics: List[QuestionAnsweringMetric]
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateSummarizationRequest(EvaluateTaskRequestCommon):
|
|
"""Request to evaluate summarization."""
|
|
|
|
metrics: List[SummarizationMetric]
|
|
|
|
|
|
class EvaluationJobStatusResponse(BaseModel):
|
|
job_uuid: str
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluationJobArtifactsResponse(BaseModel):
|
|
"""Artifacts of a evaluation job."""
|
|
|
|
job_uuid: str
|
|
|
|
|
|
class Evaluations(Protocol):
|
|
@webmethod(route="/evaluate/text_generation/")
|
|
def evaluate_text_generation(
|
|
self,
|
|
request: EvaluateTextGenerationRequest,
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/question_answering/")
|
|
def evaluate_question_answering(
|
|
self,
|
|
request: EvaluateQuestionAnsweringRequest,
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/summarization/")
|
|
def evaluate_summarization(
|
|
self,
|
|
request: EvaluateSummarizationRequest,
|
|
) -> EvaluationJob: ...
|
|
|
|
@webmethod(route="/evaluate/jobs")
|
|
def get_evaluation_jobs(self) -> List[EvaluationJob]: ...
|
|
|
|
@webmethod(route="/evaluate/job/status")
|
|
def get_evaluation_job_status(
|
|
self, job_uuid: str
|
|
) -> EvaluationJobStatusResponse: ...
|
|
|
|
# sends SSE stream of logs
|
|
@webmethod(route="/evaluate/job/logs")
|
|
def get_evaluation_job_logstream(self, job_uuid: str) -> EvaluationJobLogStream: ...
|
|
|
|
@webmethod(route="/evaluate/job/cancel")
|
|
def cancel_evaluation_job(self, job_uuid: str) -> None: ...
|
|
|
|
@webmethod(route="/evaluate/job/artifacts")
|
|
def get_evaluation_job_artifacts(
|
|
self, job_uuid: str
|
|
) -> EvaluationJobArtifactsResponse: ...
|