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>
125 lines
3.8 KiB
Python
125 lines
3.8 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.
|
|
|
|
|
|
import logging
|
|
import os
|
|
import uuid
|
|
from typing import AsyncGenerator
|
|
|
|
from llama_toolchain.inference.api import Inference
|
|
from llama_toolchain.memory.api import Memory
|
|
from llama_toolchain.safety.api import Safety
|
|
from llama_toolchain.agentic_system.api import * # noqa: F403
|
|
from llama_toolchain.tools.builtin import (
|
|
BraveSearchTool,
|
|
CodeInterpreterTool,
|
|
PhotogenTool,
|
|
WolframAlphaTool,
|
|
)
|
|
from llama_toolchain.tools.safety import with_safety
|
|
|
|
from .agent_instance import ChatAgent
|
|
from .config import MetaReferenceImplConfig
|
|
|
|
|
|
logger = logging.getLogger()
|
|
logger.setLevel(logging.INFO)
|
|
|
|
|
|
AGENT_INSTANCES_BY_ID = {}
|
|
|
|
|
|
class MetaReferenceAgenticSystemImpl(AgenticSystem):
|
|
def __init__(
|
|
self,
|
|
config: MetaReferenceImplConfig,
|
|
inference_api: Inference,
|
|
memory_api: Memory,
|
|
safety_api: Safety,
|
|
):
|
|
self.config = config
|
|
self.inference_api = inference_api
|
|
self.memory_api = memory_api
|
|
self.safety_api = safety_api
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def create_agentic_system(
|
|
self,
|
|
agent_config: AgentConfig,
|
|
) -> AgenticSystemCreateResponse:
|
|
agent_id = str(uuid.uuid4())
|
|
|
|
builtin_tools = []
|
|
for tool_defn in agent_config.tools:
|
|
if isinstance(tool_defn, WolframAlphaToolDefinition):
|
|
key = self.config.wolfram_api_key
|
|
if not key:
|
|
raise ValueError("Wolfram API key not defined in config")
|
|
tool = WolframAlphaTool(key)
|
|
elif isinstance(tool_defn, BraveSearchToolDefinition):
|
|
key = self.config.brave_search_api_key
|
|
if not key:
|
|
raise ValueError("Brave API key not defined in config")
|
|
tool = BraveSearchTool(key)
|
|
elif isinstance(tool_defn, CodeInterpreterToolDefinition):
|
|
tool = CodeInterpreterTool()
|
|
elif isinstance(tool_defn, PhotogenToolDefinition):
|
|
tool = PhotogenTool(
|
|
dump_dir="/tmp/photogen_dump_" + os.environ["USER"],
|
|
)
|
|
else:
|
|
continue
|
|
|
|
builtin_tools.append(
|
|
with_safety(
|
|
tool,
|
|
self.safety_api,
|
|
tool_defn.input_shields,
|
|
tool_defn.output_shields,
|
|
)
|
|
)
|
|
|
|
AGENT_INSTANCES_BY_ID[agent_id] = ChatAgent(
|
|
agent_config=agent_config,
|
|
inference_api=self.inference_api,
|
|
safety_api=self.safety_api,
|
|
memory_api=self.memory_api,
|
|
builtin_tools=builtin_tools,
|
|
)
|
|
|
|
return AgenticSystemCreateResponse(
|
|
agent_id=agent_id,
|
|
)
|
|
|
|
async def create_agentic_system_session(
|
|
self,
|
|
agent_id: str,
|
|
session_name: str,
|
|
) -> AgenticSystemSessionCreateResponse:
|
|
assert agent_id in AGENT_INSTANCES_BY_ID, f"System {agent_id} not found"
|
|
agent = AGENT_INSTANCES_BY_ID[agent_id]
|
|
|
|
session = agent.create_session(session_name)
|
|
return AgenticSystemSessionCreateResponse(
|
|
session_id=session.session_id,
|
|
)
|
|
|
|
async def create_agentic_system_turn(
|
|
self,
|
|
request: AgenticSystemTurnCreateRequest,
|
|
) -> AsyncGenerator:
|
|
agent_id = request.agent_id
|
|
assert agent_id in AGENT_INSTANCES_BY_ID, f"System {agent_id} not found"
|
|
agent = AGENT_INSTANCES_BY_ID[agent_id]
|
|
|
|
assert (
|
|
request.session_id in agent.sessions
|
|
), f"Session {request.session_id} not found"
|
|
async for event in agent.create_and_execute_turn(request):
|
|
yield event
|