mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-20 19:56:59 +00:00
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>
This commit is contained in:
Ashwin Bharambe
GitHub
parent
35093c0b6f
commit
7bc7785b0d
141 changed files with 8252 additions and 4032 deletions
120
llama_toolchain/core/build_container.sh
Executable file
120
llama_toolchain/core/build_container.sh
Executable file
|
|
@ -0,0 +1,120 @@
|
|||
#!/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
|
||||
Loading…
Add table
Add a link
Reference in a new issue