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/core/distribution.py

@@ -0,0 +1,101 @@
+# 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