mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
7bc7785b0d
* 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>
96 lines
3.1 KiB
Python
96 lines
3.1 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 typing import AsyncGenerator, List
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_toolchain.agentic_system.api import * # noqa: F403
|
|
from llama_toolchain.memory.api import * # noqa: F403
|
|
from llama_toolchain.safety.api import * # noqa: F403
|
|
|
|
from llama_toolchain.agentic_system.api import (
|
|
AgenticSystemTurnResponseEventType as EventType,
|
|
)
|
|
from llama_toolchain.tools.custom.datatypes import CustomTool
|
|
|
|
|
|
class AgentWithCustomToolExecutor:
|
|
def __init__(
|
|
self,
|
|
api: AgenticSystem,
|
|
agent_id: str,
|
|
session_id: str,
|
|
agent_config: AgentConfig,
|
|
custom_tools: List[CustomTool],
|
|
):
|
|
self.api = api
|
|
self.agent_id = agent_id
|
|
self.session_id = session_id
|
|
self.agent_config = agent_config
|
|
self.custom_tools = custom_tools
|
|
|
|
async def execute_turn(
|
|
self,
|
|
messages: List[Message],
|
|
attachments: Optional[List[Attachment]] = None,
|
|
max_iters: int = 5,
|
|
stream: bool = True,
|
|
) -> AsyncGenerator:
|
|
tools_dict = {t.get_name(): t for t in self.custom_tools}
|
|
|
|
current_messages = messages.copy()
|
|
n_iter = 0
|
|
while n_iter < max_iters:
|
|
n_iter += 1
|
|
|
|
request = AgenticSystemTurnCreateRequest(
|
|
agent_id=self.agent_id,
|
|
session_id=self.session_id,
|
|
messages=current_messages,
|
|
attachments=attachments,
|
|
stream=stream,
|
|
)
|
|
|
|
turn = None
|
|
async for chunk in self.api.create_agentic_system_turn(request):
|
|
if chunk.event.payload.event_type != EventType.turn_complete.value:
|
|
yield chunk
|
|
else:
|
|
turn = chunk.event.payload.turn
|
|
|
|
message = turn.output_message
|
|
if len(message.tool_calls) == 0:
|
|
yield chunk
|
|
return
|
|
|
|
if message.stop_reason == StopReason.out_of_tokens:
|
|
yield chunk
|
|
return
|
|
|
|
tool_call = message.tool_calls[0]
|
|
if tool_call.tool_name not in tools_dict:
|
|
m = ToolResponseMessage(
|
|
call_id=tool_call.call_id,
|
|
tool_name=tool_call.tool_name,
|
|
content=f"Unknown tool `{tool_call.tool_name}` was called. Try again with something else",
|
|
)
|
|
next_message = m
|
|
else:
|
|
tool = tools_dict[tool_call.tool_name]
|
|
result_messages = await execute_custom_tool(tool, message)
|
|
next_message = result_messages[0]
|
|
|
|
yield next_message
|
|
current_messages = [next_message]
|
|
|
|
|
|
async def execute_custom_tool(tool: CustomTool, message: Message) -> List[Message]:
|
|
result_messages = await tool.run([message])
|
|
assert (
|
|
len(result_messages) == 1
|
|
), f"Expected single message, got {len(result_messages)}"
|
|
|
|
return result_messages
|