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/build.py
+++ b/llama_toolchain/cli/stack/build.py
@ -0,0 +1,133 @@
+# 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 llama_toolchain.cli.subcommand import Subcommand
+from llama_toolchain.core.datatypes import *  # noqa: F403
+
+
+def parse_api_provider_tuples(
+    tuples: str, parser: argparse.ArgumentParser
+) -> Dict[str, ProviderSpec]:
+    from llama_toolchain.core.distribution import api_providers
+
+    all_providers = api_providers()
+
+    deps = {}
+    for dep in tuples.split(","):
+        dep = dep.strip()
+        if not dep:
+            continue
+        api_str, provider = dep.split("=")
+        api = Api(api_str)
+
+        provider = provider.strip()
+        if provider not in all_providers[api]:
+            parser.error(f"Provider `{provider}` is not available for API `{api}`")
+            return
+        deps[api] = all_providers[api][provider]
+
+    return deps
+
+
+class StackBuild(Subcommand):
+    def __init__(self, subparsers: argparse._SubParsersAction):
+        super().__init__()
+        self.parser = subparsers.add_parser(
+            "build",
+            prog="llama stack build",
+            description="Build a Llama stack container",
+            formatter_class=argparse.RawTextHelpFormatter,
+        )
+        self._add_arguments()
+        self.parser.set_defaults(func=self._run_stack_build_command)
+
+    def _add_arguments(self):
+        from llama_toolchain.core.distribution_registry import available_distribution_specs
+        from llama_toolchain.core.package import (
+            BuildType,
+        )
+
+        allowed_ids = [d.distribution_id for d in available_distribution_specs()]
+        self.parser.add_argument(
+            "distribution",
+            type=str,
+            help="Distribution to build (either \"adhoc\" OR one of: {})".format(allowed_ids),
+        )
+        self.parser.add_argument(
+            "api_providers",
+            nargs='?',
+            help="Comma separated list of (api=provider) tuples",
+        )
+
+        self.parser.add_argument(
+            "--name",
+            type=str,
+            help="Name of the build target (image, conda env)",
+            required=True,
+        )
+        self.parser.add_argument(
+            "--type",
+            type=str,
+            default="conda_env",
+            choices=[v.value for v in BuildType],
+        )
+
+    def _run_stack_build_command(self, args: argparse.Namespace) -> None:
+        from llama_toolchain.core.distribution_registry import resolve_distribution_spec
+        from llama_toolchain.core.package import (
+            ApiInput,
+            BuildType,
+            build_package,
+        )
+
+        api_inputs = []
+        if args.distribution == "adhoc":
+            if not args.api_providers:
+                self.parser.error("You must specify API providers with (api=provider,...) for building an adhoc distribution")
+                return
+
+            parsed = parse_api_provider_tuples(args.api_providers, self.parser)
+            for api, provider_spec in parsed.items():
+                for dep in provider_spec.api_dependencies:
+                    if dep not in parsed:
+                        self.parser.error(f"API {api} needs dependency {dep} provided also")
+                        return
+
+                api_inputs.append(
+                    ApiInput(
+                        api=api,
+                        provider=provider_spec.provider_id,
+                    )
+                )
+            docker_image = None
+        else:
+            if args.api_providers:
+                self.parser.error("You cannot specify API providers for pre-registered distributions")
+                return
+
+            dist = resolve_distribution_spec(args.distribution)
+            if dist is None:
+                self.parser.error(f"Could not find distribution {args.distribution}")
+                return
+
+            for api, provider_id in dist.providers.items():
+                api_inputs.append(
+                    ApiInput(
+                        api=api,
+                        provider=provider_id,
+                    )
+                )
+            docker_image = dist.docker_image
+
+        build_package(
+            api_inputs,
+            build_type=BuildType(args.type),
+            name=args.name,
+            distribution_id=args.distribution,
+            docker_image=docker_image,
+        )