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/tools/ipython_tool/matplotlib_custom_backend.py

@@ -0,0 +1,87 @@
+# 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.
+
+"""
+A custom Matplotlib backend that overrides the show method to return image bytes.
+"""
+
+import base64
+import io
+import json as _json
+
+import matplotlib
+from matplotlib.backend_bases import FigureManagerBase
+
+# Import necessary components from Matplotlib
+from matplotlib.backends.backend_agg import FigureCanvasAgg
+
+
+class CustomFigureCanvas(FigureCanvasAgg):
+    def show(self):
+        # Save the figure to a BytesIO object
+        buf = io.BytesIO()
+        self.print_png(buf)
+        image_bytes = buf.getvalue()
+        buf.close()
+        return image_bytes
+
+
+class CustomFigureManager(FigureManagerBase):
+    def __init__(self, canvas, num):
+        super().__init__(canvas, num)
+
+
+# Mimic module initialization that integrates with the Matplotlib backend system
+def _create_figure_manager(num, *args, **kwargs):
+    """
+    Create a custom figure manager instance.
+    """
+    FigureClass = kwargs.pop("FigureClass", None)  # noqa: N806
+    if FigureClass is None:
+        from matplotlib.figure import Figure
+
+        FigureClass = Figure  # noqa: N806
+    fig = FigureClass(*args, **kwargs)
+    canvas = CustomFigureCanvas(fig)
+    manager = CustomFigureManager(canvas, num)
+    return manager
+
+
+def show():
+    """
+    Handle all figures and potentially return their images as bytes.
+
+    This function iterates over all figures registered with the custom backend,
+    renders them as images in bytes format, and could return a list of bytes objects,
+    one for each figure, or handle them as needed.
+    """
+    image_data = []
+    for manager in matplotlib._pylab_helpers.Gcf.get_all_fig_managers():
+        # Get the figure from the manager
+        fig = manager.canvas.figure
+        buf = io.BytesIO()  # Create a buffer for the figure
+        fig.savefig(buf, format="png")  # Save the figure to the buffer in PNG format
+        buf.seek(0)  # Go to the beginning of the buffer
+        image_bytes = buf.getvalue()  # Retrieve bytes value
+        image_base64 = base64.b64encode(image_bytes).decode("utf-8")
+        image_data.append({"image_base64": image_base64})
+        buf.close()
+
+    req_con, resp_con = _open_connections()
+
+    _json_dump = _json.dumps(
+        {
+            "type": "matplotlib",
+            "image_data": image_data,
+        }
+    )
+    req_con.send_bytes(_json_dump.encode("utf-8"))
+    resp = _json.loads(resp_con.recv_bytes().decode("utf-8"))
+    print(resp)
+
+
+FigureCanvas = CustomFigureCanvas
+FigureManager = CustomFigureManager