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>
175 lines
4.1 KiB
Python
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: ...
|