61 lines
2.3 KiB
YAML
61 lines
2.3 KiB
YAML
version: '3'
|
|
|
|
services:
|
|
|
|
# Service to download a model file.
|
|
downloader:
|
|
image: busybox
|
|
# The command extracts the model filename from MODEL_URL and downloads it if it doesn't exist.
|
|
command: /bin/sh -c "LLM_MODEL_FILE=$(basename ${MODEL_URL}); if [ ! -f /models/$LLM_MODEL_FILE ]; then wget -O /models/$LLM_MODEL_FILE ${MODEL_URL}; fi"
|
|
# Mount a local directory to store the downloaded model.
|
|
volumes:
|
|
- ./models:/models
|
|
|
|
# Service to wait for the downloader service to finish downloading the model.
|
|
wait-for-downloader:
|
|
image: busybox
|
|
# The command waits until the model file (specified in MODEL_URL) exists.
|
|
command: /bin/sh -c "LLM_MODEL_FILE=$(basename ${MODEL_URL}); echo 'Waiting for downloader to finish'; while [ ! -f /models/$LLM_MODEL_FILE ]; do sleep 1; done; echo 'Model downloaded!'"
|
|
# Specifies that this service should start after the downloader service has started.
|
|
depends_on:
|
|
downloader:
|
|
condition: service_started
|
|
# Mount the same local directory to check for the downloaded model.
|
|
volumes:
|
|
- ./models:/models
|
|
|
|
# Service to run the Llama web application.
|
|
llm:
|
|
image: ghcr.io/abetlen/llama-cpp-python:latest
|
|
# Mount the directory that contains the downloaded model.
|
|
volumes:
|
|
- ./models:/models
|
|
ports:
|
|
- 8000:8000
|
|
environment:
|
|
# Specify the path to the model for the web application.
|
|
MODEL: /models/llama-2-7b-chat.ggmlv3.q4_1.bin
|
|
PYTHONUNBUFFERED: 1
|
|
# Health check configuration
|
|
# healthcheck:
|
|
# test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:8000"]
|
|
# interval: 30s
|
|
# timeout: 10s
|
|
# retries: 3
|
|
# start_period: 30s
|
|
# Restart policy configuration
|
|
restart: on-failure
|
|
# Specifies that this service should start only after wait-for-downloader has completed successfully.
|
|
depends_on:
|
|
wait-for-downloader:
|
|
condition: service_completed_successfully
|
|
# Connect this service to two networks: inference_net and traefik_public.
|
|
networks:
|
|
- traefik_public
|
|
|
|
# Define networks used in this docker-compose file.
|
|
networks:
|
|
# Public-facing network that Traefik uses. Marked as external to indicate it may be defined outside this file.
|
|
traefik_public:
|
|
external: true
|