llama-stack/llama_toolchain/observability/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

175 lines
4.1 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 datetime import datetime
from enum import Enum
from typing import Any, Dict, List, Optional, Protocol, Union
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel
@json_schema_type
class ExperimentStatus(Enum):
NOT_STARTED = "not_started"
RUNNING = "running"
COMPLETED = "completed"
FAILED = "failed"
@json_schema_type
class Experiment(BaseModel):
id: str
name: str
status: ExperimentStatus
created_at: datetime
updated_at: datetime
metadata: Dict[str, Any]
@json_schema_type
class Run(BaseModel):
id: str
experiment_id: str
status: str
started_at: datetime
ended_at: Optional[datetime]
metadata: Dict[str, Any]
@json_schema_type
class Metric(BaseModel):
name: str
value: Union[float, int, str, bool]
timestamp: datetime
run_id: str
@json_schema_type
class Log(BaseModel):
message: str
level: str
timestamp: datetime
additional_info: Dict[str, Any]
@json_schema_type
class ArtifactType(Enum):
MODEL = "model"
DATASET = "dataset"
CHECKPOINT = "checkpoint"
PLOT = "plot"
METRIC = "metric"
CONFIG = "config"
CODE = "code"
OTHER = "other"
@json_schema_type
class Artifact(BaseModel):
id: str
name: str
type: ArtifactType
size: int
created_at: datetime
metadata: Dict[str, Any]
@json_schema_type
class CreateExperimentRequest(BaseModel):
name: str
metadata: Optional[Dict[str, Any]] = None
@json_schema_type
class UpdateExperimentRequest(BaseModel):
experiment_id: str
status: Optional[ExperimentStatus] = None
metadata: Optional[Dict[str, Any]] = None
@json_schema_type
class CreateRunRequest(BaseModel):
experiment_id: str
metadata: Optional[Dict[str, Any]] = None
@json_schema_type
class UpdateRunRequest(BaseModel):
run_id: str
status: Optional[str] = None
ended_at: Optional[datetime] = None
metadata: Optional[Dict[str, Any]] = None
@json_schema_type
class LogMetricsRequest(BaseModel):
run_id: str
metrics: List[Metric]
@json_schema_type
class LogMessagesRequest(BaseModel):
logs: List[Log]
run_id: Optional[str] = None
@json_schema_type
class UploadArtifactRequest(BaseModel):
experiment_id: str
name: str
artifact_type: str
content: bytes
metadata: Optional[Dict[str, Any]] = None
@json_schema_type
class LogSearchRequest(BaseModel):
query: str
filters: Optional[Dict[str, Any]] = None
class Observability(Protocol):
@webmethod(route="/experiments/create")
def create_experiment(self, request: CreateExperimentRequest) -> Experiment: ...
@webmethod(route="/experiments/list")
def list_experiments(self) -> List[Experiment]: ...
@webmethod(route="/experiments/get")
def get_experiment(self, experiment_id: str) -> Experiment: ...
@webmethod(route="/experiments/update")
def update_experiment(self, request: UpdateExperimentRequest) -> Experiment: ...
@webmethod(route="/experiments/create_run")
def create_run(self, request: CreateRunRequest) -> Run: ...
@webmethod(route="/runs/update")
def update_run(self, request: UpdateRunRequest) -> Run: ...
@webmethod(route="/runs/log_metrics")
def log_metrics(self, request: LogMetricsRequest) -> None: ...
@webmethod(route="/runs/metrics", method="GET")
def get_metrics(self, run_id: str) -> List[Metric]: ...
@webmethod(route="/logging/log_messages")
def log_messages(self, request: LogMessagesRequest) -> None: ...
@webmethod(route="/logging/get_logs")
def get_logs(self, request: LogSearchRequest) -> List[Log]: ...
@webmethod(route="/experiments/artifacts/upload")
def upload_artifact(self, request: UploadArtifactRequest) -> Artifact: ...
@webmethod(route="/experiments/artifacts/get")
def list_artifacts(self, experiment_id: str) -> List[Artifact]: ...
@webmethod(route="/artifacts/get")
def get_artifact(self, artifact_id: str) -> Artifact: ...