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/generate.py

@@ -10,81 +10,39 @@
 # This source code is licensed under the terms described found in the
 # LICENSE file in the root directory of this source tree.
 
-import inspect
-
 from datetime import datetime
 from pathlib import Path
-from typing import Callable, Iterator, List, Tuple
 
 import fire
 import yaml
 
 from llama_models import schema_utils
-from pyopenapi import Info, operations, Options, Server, Specification
 
-# We do a series of monkey-patching to ensure our definitions only use the minimal
+# We do some monkey-patching to ensure our definitions only use the minimal
 # (json_schema_type, webmethod) definitions from the llama_models package. For
 # generation though, we need the full definitions and implementations from the
-#  (python-openapi, json-strong-typing) packages.
+#  (json-strong-typing) package.
 
 from strong_typing.schema import json_schema_type
-from termcolor import colored
+
+from .pyopenapi.options import Options
+from .pyopenapi.specification import Info, Server
+from .pyopenapi.utility import Specification
 
 schema_utils.json_schema_type = json_schema_type
 
-
 from llama_toolchain.stack import LlamaStack
 
 
-STREAMING_ENDPOINTS = [
-    "/agentic_system/turn/create"
-]
-
-
-def patched_get_endpoint_functions(
-    endpoint: type, prefixes: List[str]
-) -> Iterator[Tuple[str, str, str, Callable]]:
-    if not inspect.isclass(endpoint):
-        raise ValueError(f"object is not a class type: {endpoint}")
-
-    functions = inspect.getmembers(endpoint, inspect.isfunction)
-    for func_name, func_ref in functions:
-        webmethod = getattr(func_ref, "__webmethod__", None)
-        if not webmethod:
-            continue
-
-        print(f"Processing {colored(func_name, 'white')}...")
-        operation_name = func_name
-        if operation_name.startswith("get_") or operation_name.endswith("/get"):
-            prefix = "get"
-        elif (
-            operation_name.startswith("delete_")
-            or operation_name.startswith("remove_")
-            or operation_name.endswith("/delete")
-            or operation_name.endswith("/remove")
-        ):
-            prefix = "delete"
-        else:
-            if webmethod.method == "GET":
-                prefix = "get"
-            elif webmethod.method == "DELETE":
-                prefix = "delete"
-            else:
-                # by default everything else is a POST
-                prefix = "post"
-
-        yield prefix, operation_name, func_name, func_ref
-
-
-# Patch this so all methods are correctly parsed with correct HTTP methods
-operations._get_endpoint_functions = patched_get_endpoint_functions
+# TODO: this should be fixed in the generator itself so it reads appropriate annotations
+STREAMING_ENDPOINTS = ["/agentic_system/turn/create"]
 
 
 def patch_sse_stream_responses(spec: Specification):
     for path, path_item in spec.document.paths.items():
         if path in STREAMING_ENDPOINTS:
-            content = path_item.post.responses['200'].content.pop('application/json')
-            path_item.post.responses['200'].content['text/event-stream'] = content
+            content = path_item.post.responses["200"].content.pop("application/json")
+            path_item.post.responses["200"].content["text/event-stream"] = content
 
 
 def main(output_dir: str):