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>
2024-09-03 22:39:39 -07:00 · 2024-09-03 22:39:39 -07:00 · 7bc7785b0d
commit 7bc7785b0d
parent 35093c0b6f
141 changed files with 8252 additions and 4032 deletions
--- a/llama_toolchain/cli/stack/run.py
+++ b/llama_toolchain/cli/stack/run.py
@ -0,0 +1,106 @@
+# 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 argparse
+
+from pathlib import Path
+
+import pkg_resources
+import yaml
+
+from llama_toolchain.cli.subcommand import Subcommand
+from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_toolchain.common.config_dirs import BUILDS_BASE_DIR
+
+
+class StackRun(Subcommand):
+    def __init__(self, subparsers: argparse._SubParsersAction):
+        super().__init__()
+        self.parser = subparsers.add_parser(
+            "run",
+            prog="llama stack run",
+            description="""start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.""",
+            formatter_class=argparse.RawTextHelpFormatter,
+        )
+        self._add_arguments()
+        self.parser.set_defaults(func=self._run_stack_run_cmd)
+
+    def _add_arguments(self):
+        from llama_toolchain.core.package import BuildType
+
+        self.parser.add_argument(
+            "distribution",
+            type=str,
+            help="Distribution whose build you want to start",
+        )
+        self.parser.add_argument(
+            "--name",
+            type=str,
+            help="Name of the build you want to start",
+            required=True,
+        )
+        self.parser.add_argument(
+            "--type",
+            type=str,
+            default="conda_env",
+            choices=[v.value for v in BuildType],
+        )
+        self.parser.add_argument(
+            "--port",
+            type=int,
+            help="Port to run the server on. Defaults to 5000",
+            default=5000,
+        )
+        self.parser.add_argument(
+            "--disable-ipv6",
+            action="store_true",
+            help="Disable IPv6 support",
+            default=False,
+        )
+
+    def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
+        from llama_toolchain.common.exec import run_with_pty
+        from llama_toolchain.core.package import BuildType
+
+        build_type = BuildType(args.type)
+        build_dir = BUILDS_BASE_DIR / args.distribution / build_type.descriptor()
+        path = build_dir / f"{args.name}.yaml"
+
+        config_file = Path(path)
+
+        if not config_file.exists():
+            self.parser.error(
+                f"File {str(config_file)} does not exist. Did you run `llama stack build`?"
+            )
+            return
+
+        with open(config_file, "r") as f:
+            config = PackageConfig(**yaml.safe_load(f))
+
+        if not config.distribution_id:
+            raise ValueError("Build config appears to be corrupt.")
+
+        if config.docker_image:
+            script = pkg_resources.resource_filename(
+                "llama_toolchain",
+                "core/start_container.sh",
+            )
+            run_args = [script, config.docker_image]
+        else:
+            script = pkg_resources.resource_filename(
+                "llama_toolchain",
+                "core/start_conda_env.sh",
+            )
+            run_args = [
+                script,
+                config.conda_env,
+            ]
+
+        run_args.extend([str(config_file), str(args.port)])
+        if args.disable_ipv6:
+            run_args.append("--disable-ipv6")
+
+        run_with_pty(run_args)