API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command (#51)

* 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>

rfcs/openapi_generator/pyopenapi/options.py

@@ -0,0 +1,75 @@
+# 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 dataclasses
+from dataclasses import dataclass
+from http import HTTPStatus
+from typing import Callable, ClassVar, Dict, List, Optional, Tuple, Union
+
+from .specification import (
+    Info,
+    SecurityScheme,
+    SecuritySchemeAPI,
+    SecuritySchemeHTTP,
+    SecuritySchemeOpenIDConnect,
+    Server,
+)
+
+HTTPStatusCode = Union[HTTPStatus, int, str]
+
+
+@dataclass
+class Options:
+    """
+    :param server: Base URL for the API endpoint.
+    :param info: Meta-information for the endpoint specification.
+    :param version: OpenAPI specification version as a tuple of major, minor, revision.
+    :param default_security_scheme: Security scheme to apply to endpoints, unless overridden on a per-endpoint basis.
+    :param extra_types: Extra types in addition to those found in operation signatures. Use a dictionary to group related types.
+    :param use_examples: Whether to emit examples for operations.
+    :param success_responses: Associates operation response types with HTTP status codes.
+    :param error_responses: Associates error response types with HTTP status codes.
+    :param error_wrapper: True if errors are encapsulated in an error object wrapper.
+    :param property_description_fun: Custom transformation function to apply to class property documentation strings.
+    :param captions: User-defined captions for sections such as "Operations" or "Types", and (if applicable) groups of extra types.
+    """
+
+    server: Server
+    info: Info
+    version: Tuple[int, int, int] = (3, 1, 0)
+    default_security_scheme: Optional[SecurityScheme] = None
+    extra_types: Union[List[type], Dict[str, List[type]], None] = None
+    use_examples: bool = True
+    success_responses: Dict[type, HTTPStatusCode] = dataclasses.field(
+        default_factory=dict
+    )
+    error_responses: Dict[type, HTTPStatusCode] = dataclasses.field(
+        default_factory=dict
+    )
+    error_wrapper: bool = False
+    property_description_fun: Optional[Callable[[type, str, str], str]] = None
+    captions: Optional[Dict[str, str]] = None
+
+    default_captions: ClassVar[Dict[str, str]] = {
+        "Operations": "Operations",
+        "Types": "Types",
+        "Events": "Events",
+        "AdditionalTypes": "Additional types",
+    }
+
+    def map(self, id: str) -> str:
+        "Maps a language-neutral placeholder string to language-dependent text."
+
+        if self.captions is not None:
+            caption = self.captions.get(id)
+            if caption is not None:
+                return caption
+
+        caption = self.__class__.default_captions.get(id)
+        if caption is not None:
+            return caption
+
+        raise KeyError(f"no caption found for ID: {id}")