mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
* 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>
101 lines
3.1 KiB
Python
101 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.
|
|
|
|
import inspect
|
|
from typing import Dict, List
|
|
|
|
from llama_toolchain.agentic_system.api import AgenticSystem
|
|
from llama_toolchain.agentic_system.providers import available_agentic_system_providers
|
|
from llama_toolchain.inference.api import Inference
|
|
from llama_toolchain.inference.providers import available_inference_providers
|
|
from llama_toolchain.memory.api import Memory
|
|
from llama_toolchain.memory.providers import available_memory_providers
|
|
from llama_toolchain.safety.api import Safety
|
|
from llama_toolchain.safety.providers import available_safety_providers
|
|
|
|
from .datatypes import (
|
|
Api,
|
|
ApiEndpoint,
|
|
DistributionSpec,
|
|
InlineProviderSpec,
|
|
ProviderSpec,
|
|
remote_provider_spec,
|
|
)
|
|
|
|
# These are the dependencies needed by the distribution server.
|
|
# `llama-toolchain` is automatically installed by the installation script.
|
|
SERVER_DEPENDENCIES = [
|
|
"fastapi",
|
|
"uvicorn",
|
|
]
|
|
|
|
|
|
def distribution_dependencies(distribution: DistributionSpec) -> List[str]:
|
|
# only consider InlineProviderSpecs when calculating dependencies
|
|
return [
|
|
dep
|
|
for provider_spec in distribution.provider_specs.values()
|
|
if isinstance(provider_spec, InlineProviderSpec)
|
|
for dep in provider_spec.pip_packages
|
|
] + SERVER_DEPENDENCIES
|
|
|
|
|
|
def stack_apis() -> List[Api]:
|
|
return [Api.inference, Api.safety, Api.agentic_system, Api.memory]
|
|
|
|
|
|
def api_endpoints() -> Dict[Api, List[ApiEndpoint]]:
|
|
apis = {}
|
|
|
|
protocols = {
|
|
Api.inference: Inference,
|
|
Api.safety: Safety,
|
|
Api.agentic_system: AgenticSystem,
|
|
Api.memory: Memory,
|
|
}
|
|
|
|
for api, protocol in protocols.items():
|
|
endpoints = []
|
|
protocol_methods = inspect.getmembers(protocol, predicate=inspect.isfunction)
|
|
|
|
for name, method in protocol_methods:
|
|
if not hasattr(method, "__webmethod__"):
|
|
continue
|
|
|
|
webmethod = method.__webmethod__
|
|
route = webmethod.route
|
|
|
|
if webmethod.method == "GET":
|
|
method = "get"
|
|
elif webmethod.method == "DELETE":
|
|
method = "delete"
|
|
else:
|
|
method = "post"
|
|
endpoints.append(ApiEndpoint(route=route, method=method, name=name))
|
|
|
|
apis[api] = endpoints
|
|
|
|
return apis
|
|
|
|
|
|
def api_providers() -> Dict[Api, Dict[str, ProviderSpec]]:
|
|
inference_providers_by_id = {
|
|
a.provider_id: a for a in available_inference_providers()
|
|
}
|
|
safety_providers_by_id = {a.provider_id: a for a in available_safety_providers()}
|
|
agentic_system_providers_by_id = {
|
|
a.provider_id: a for a in available_agentic_system_providers()
|
|
}
|
|
|
|
ret = {
|
|
Api.inference: inference_providers_by_id,
|
|
Api.safety: safety_providers_by_id,
|
|
Api.agentic_system: agentic_system_providers_by_id,
|
|
Api.memory: {a.provider_id: a for a in available_memory_providers()},
|
|
}
|
|
for k, v in ret.items():
|
|
v["remote"] = remote_provider_spec(k)
|
|
return ret
|