mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
84 lines
2.7 KiB
Python
84 lines
2.7 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 llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.inference import * # noqa: F403
|
|
from llama_models.llama3.prompt_templates import (
|
|
BuiltinToolGenerator,
|
|
FunctionTagCustomToolGenerator,
|
|
JsonCustomToolGenerator,
|
|
SystemDefaultGenerator,
|
|
)
|
|
|
|
|
|
def prepare_messages(request: ChatCompletionRequest) -> List[Message]:
|
|
|
|
assert request.tool_choice == ToolChoice.auto, "Only `ToolChoice.auto` supported"
|
|
|
|
existing_messages = request.messages
|
|
existing_system_message = None
|
|
if existing_messages[0].role == Role.system.value:
|
|
existing_system_message = existing_messages.pop(0)
|
|
|
|
assert (
|
|
existing_messages[0].role != Role.system.value
|
|
), "Should only have 1 system message"
|
|
|
|
messages = []
|
|
|
|
default_gen = SystemDefaultGenerator()
|
|
default_template = default_gen.gen()
|
|
|
|
sys_content = ""
|
|
|
|
tool_template = None
|
|
if request.tools:
|
|
tool_gen = BuiltinToolGenerator()
|
|
tool_template = tool_gen.gen(request.tools)
|
|
|
|
sys_content += tool_template.render()
|
|
sys_content += "\n"
|
|
|
|
sys_content += default_template.render()
|
|
|
|
if existing_system_message:
|
|
# TODO: this fn is needed in many places
|
|
def _process(c):
|
|
if isinstance(c, str):
|
|
return c
|
|
else:
|
|
return "<media>"
|
|
|
|
sys_content += "\n"
|
|
|
|
if isinstance(existing_system_message.content, str):
|
|
sys_content += _process(existing_system_message.content)
|
|
elif isinstance(existing_system_message.content, list):
|
|
sys_content += "\n".join(
|
|
[_process(c) for c in existing_system_message.content]
|
|
)
|
|
|
|
messages.append(SystemMessage(content=sys_content))
|
|
|
|
has_custom_tools = any(isinstance(dfn.tool_name, str) for dfn in request.tools)
|
|
if has_custom_tools:
|
|
if request.tool_prompt_format == ToolPromptFormat.json:
|
|
tool_gen = JsonCustomToolGenerator()
|
|
elif request.tool_prompt_format == ToolPromptFormat.function_tag:
|
|
tool_gen = FunctionTagCustomToolGenerator()
|
|
else:
|
|
raise ValueError(
|
|
f"Non supported ToolPromptFormat {request.tool_prompt_format}"
|
|
)
|
|
|
|
custom_tools = [t for t in request.tools if isinstance(t.tool_name, str)]
|
|
custom_template = tool_gen.gen(custom_tools)
|
|
messages.append(UserMessage(content=custom_template.render()))
|
|
|
|
# Add back existing messages from the request
|
|
messages += existing_messages
|
|
|
|
return messages
|