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>

llama_toolchain/inference/meta_reference/inference.py

@@ -6,12 +6,11 @@
 
 import asyncio
 
-from typing import AsyncIterator, Dict, Union
+from typing import AsyncIterator, Union
 
 from llama_models.llama3.api.datatypes import StopReason
 from llama_models.sku_list import resolve_model
 
-from llama_toolchain.distribution.datatypes import Api, ProviderSpec
 from llama_toolchain.inference.api import (
     ChatCompletionRequest,
     ChatCompletionResponse,
@@ -22,23 +21,11 @@ from llama_toolchain.inference.api import (
     ToolCallDelta,
     ToolCallParseStatus,
 )
-
+from llama_toolchain.inference.prepare_messages import prepare_messages
 from .config import MetaReferenceImplConfig
 from .model_parallel import LlamaModelParallelGenerator
 
 
-async def get_provider_impl(
-    config: MetaReferenceImplConfig, _deps: Dict[Api, ProviderSpec]
-):
-    assert isinstance(
-        config, MetaReferenceImplConfig
-    ), f"Unexpected config type: {type(config)}"
-
-    impl = MetaReferenceInferenceImpl(config)
-    await impl.initialize()
-    return impl
-
-
 # there's a single model parallel process running serving the model. for now,
 # we don't support multiple concurrent requests to this process.
 SEMAPHORE = asyncio.Semaphore(1)
@@ -67,6 +54,7 @@ class MetaReferenceInferenceImpl(Inference):
     ) -> AsyncIterator[
         Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
     ]:
+        messages = prepare_messages(request)
         model = resolve_model(request.model)
         if model is None:
             raise RuntimeError(
@@ -98,11 +86,12 @@ class MetaReferenceInferenceImpl(Inference):
             ipython = False
 
             for token_result in self.generator.chat_completion(
-                messages=request.messages,
+                messages=messages,
                 temperature=request.sampling_params.temperature,
                 top_p=request.sampling_params.top_p,
                 max_gen_len=request.sampling_params.max_tokens,
                 logprobs=request.logprobs,
+                tool_prompt_format=request.tool_prompt_format,
             ):
                 buffer += token_result.text
                 tokens.append(token_result.token)