llama-stack/llama_toolchain/core/build_container.sh
Ashwin Bharambe 7bc7785b0d
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

120 lines
2.9 KiB
Bash
Executable file

#!/bin/bash
LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
LLAMA_TOOLCHAIN_DIR=${LLAMA_TOOLCHAIN_DIR:-}
TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
if [ "$#" -ne 4 ]; then
echo "Usage: $0 <distribution_id> <build_name> <docker_base> <pip_dependencies>
echo "Example: $0 distribution_id my-fastapi-app python:3.9-slim 'fastapi uvicorn'
exit 1
fi
distribution_id=$1
build_name="$2"
image_name="llamastack-$build_name"
docker_base=$3
pip_dependencies=$4
# Define color codes
RED='\033[0;31m'
GREEN='\033[0;32m'
NC='\033[0m' # No Color
set -euo pipefail
SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
REPO_DIR=$(dirname $(dirname "$SCRIPT_DIR"))
TEMP_DIR=$(mktemp -d)
add_to_docker() {
local input
output_file="$TEMP_DIR/Dockerfile"
if [ -t 0 ]; then
printf '%s\n' "$1" >>"$output_file"
else
# If stdin is not a terminal, read from it (heredoc)
cat >>"$output_file"
fi
}
add_to_docker <<EOF
FROM $docker_base
WORKDIR /app
RUN apt-get update && apt-get install -y \
iputils-ping net-tools iproute2 dnsutils telnet \
curl wget telnet \
procps psmisc lsof \
traceroute \
&& rm -rf /var/lib/apt/lists/*
EOF
toolchain_mount="/app/llama-toolchain-source"
models_mount="/app/llama-models-source"
if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
if [ ! -d "$LLAMA_TOOLCHAIN_DIR" ]; then
echo "${RED}Warning: LLAMA_TOOLCHAIN_DIR is set but directory does not exist: $LLAMA_TOOLCHAIN_DIR${NC}" >&2
exit 1
fi
add_to_docker "RUN pip install $toolchain_mount"
else
add_to_docker "RUN pip install llama-toolchain"
fi
if [ -n "$LLAMA_MODELS_DIR" ]; then
if [ ! -d "$LLAMA_MODELS_DIR" ]; then
echo "${RED}Warning: LLAMA_MODELS_DIR is set but directory does not exist: $LLAMA_MODELS_DIR${NC}" >&2
exit 1
fi
add_to_docker <<EOF
RUN pip uninstall -y llama-models
RUN pip install $models_mount
EOF
fi
if [ -n "$pip_dependencies" ]; then
add_to_docker "RUN pip install $pip_dependencies"
fi
add_to_docker <<EOF
# This would be good in production but for debugging flexibility lets not add it right now
# We need a more solid production ready entrypoint.sh anyway
#
# ENTRYPOINT ["python", "-m", "llama_toolchain.core.server"]
EOF
printf "Dockerfile created successfully in $TEMP_DIR/Dockerfile"
cat $TEMP_DIR/Dockerfile
printf "\n"
mounts=""
if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
mounts="$mounts -v $(readlink -f $LLAMA_TOOLCHAIN_DIR):$toolchain_mount"
fi
if [ -n "$LLAMA_MODELS_DIR" ]; then
mounts="$mounts -v $(readlink -f $LLAMA_MODELS_DIR):$models_mount"
fi
set -x
podman build -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
set +x
printf "${GREEN}Succesfully setup Podman image. Configuring build...${NC}"
echo "You can run it with: podman run -p 8000:8000 $image_name"
if [ "$distribution_id" = "adhoc" ]; then
subcommand="api"
target=""
else
subcommand="stack"
target="$distribution_id"
fi
$CONDA_PREFIX/bin/python3 -m llama_toolchain.cli.llama $subcommand configure $target --name "$build_name" --type container