llama-stack/llama_toolchain/evaluations/api/api.py
Ashwin Bharambe 7bc7785b0d
API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command (#51)
* 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>
2024-09-03 22:39:39 -07:00

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: ...