forked from phoenix-oss/llama-stack-mirror
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
|
|
@ -1,112 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
# 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.
|
||||
|
||||
LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
|
||||
LLAMA_TOOLCHAIN_DIR=${LLAMA_TOOLCHAIN_DIR:-}
|
||||
TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
# Define color codes
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
NC='\033[0m' # No Color
|
||||
|
||||
error_handler() {
|
||||
echo "Error occurred in script at line: ${1}" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Set up the error trap
|
||||
trap 'error_handler ${LINENO}' ERR
|
||||
|
||||
ensure_conda_env_python310() {
|
||||
local env_name="$1"
|
||||
local pip_dependencies="$2"
|
||||
local python_version="3.10"
|
||||
|
||||
# Check if conda command is available
|
||||
if ! command -v conda &>/dev/null; then
|
||||
echo -e "${RED}Error: conda command not found. Is Conda installed and in your PATH?${NC}" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check if the environment exists
|
||||
if conda env list | grep -q "^${env_name} "; then
|
||||
echo "Conda environment '${env_name}' exists. Checking Python version..."
|
||||
|
||||
# Check Python version in the environment
|
||||
current_version=$(conda run -n "${env_name}" python --version 2>&1 | cut -d' ' -f2 | cut -d'.' -f1,2)
|
||||
|
||||
if [ "$current_version" = "$python_version" ]; then
|
||||
echo "Environment '${env_name}' already has Python ${python_version}. No action needed."
|
||||
else
|
||||
echo "Updating environment '${env_name}' to Python ${python_version}..."
|
||||
conda install -n "${env_name}" python="${python_version}" -y
|
||||
fi
|
||||
else
|
||||
echo "Conda environment '${env_name}' does not exist. Creating with Python ${python_version}..."
|
||||
conda create -n "${env_name}" python="${python_version}" -y
|
||||
fi
|
||||
|
||||
eval "$(conda shell.bash hook)"
|
||||
conda deactivate && conda activate "${env_name}"
|
||||
|
||||
if [ -n "$TEST_PYPI_VERSION" ]; then
|
||||
# these packages are damaged in test-pypi, so install them first
|
||||
pip install fastapi libcst
|
||||
pip install --extra-index-url https://test.pypi.org/simple/ llama-models==$TEST_PYPI_VERSION llama-toolchain==$TEST_PYPI_VERSION $pip_dependencies
|
||||
else
|
||||
# Re-installing llama-toolchain in the new conda environment
|
||||
if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
|
||||
if [ ! -d "$LLAMA_TOOLCHAIN_DIR" ]; then
|
||||
echo -e "${RED}Warning: LLAMA_TOOLCHAIN_DIR is set but directory does not exist: $LLAMA_TOOLCHAIN_DIR${NC}" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Installing from LLAMA_TOOLCHAIN_DIR: $LLAMA_TOOLCHAIN_DIR"
|
||||
pip install -e "$LLAMA_TOOLCHAIN_DIR"
|
||||
else
|
||||
pip install llama-toolchain
|
||||
fi
|
||||
|
||||
if [ -n "$LLAMA_MODELS_DIR" ]; then
|
||||
if [ ! -d "$LLAMA_MODELS_DIR" ]; then
|
||||
echo -e "${RED}Warning: LLAMA_MODELS_DIR is set but directory does not exist: $LLAMA_MODELS_DIR${NC}" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Installing from LLAMA_MODELS_DIR: $LLAMA_MODELS_DIR"
|
||||
pip uninstall -y llama-models
|
||||
pip install -e "$LLAMA_MODELS_DIR"
|
||||
fi
|
||||
|
||||
# Install pip dependencies
|
||||
if [ -n "$pip_dependencies" ]; then
|
||||
echo "Installing pip dependencies: $pip_dependencies"
|
||||
pip install $pip_dependencies
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
if [ "$#" -ne 3 ]; then
|
||||
echo "Usage: $0 <environment_name> <distribution_name> <pip_dependencies>" >&2
|
||||
echo "Example: $0 my_env local-llama-8b 'numpy pandas scipy'" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
env_name="$1"
|
||||
distribution_name="$2"
|
||||
pip_dependencies="$3"
|
||||
|
||||
ensure_conda_env_python310 "$env_name" "$pip_dependencies"
|
||||
|
||||
echo -e "${GREEN}Successfully setup distribution environment. Configuring...${NC}"
|
||||
|
||||
which python3
|
||||
python3 -m llama_toolchain.cli.llama distribution configure --name "$distribution_name"
|
||||
Loading…
Add table
Add a link
Reference in a new issue