From 858c872b1b0d451732b36d737ed676141e9c29ad Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Wed, 30 Aug 2023 16:44:34 +0700
Subject: [PATCH] fix: Update docker compose for sd and llm

---
 docker-compose.yml | 99 ++++++++++++++++++++++++++++------------------
 1 file changed, 61 insertions(+), 38 deletions(-)

diff --git a/docker-compose.yml b/docker-compose.yml
index 44db975fa..5b456f33e 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -125,7 +125,6 @@ services:
       timeout: 10s
       retries: 5
       start_period: 5s
-
     networks:
       jan_community:
         ipv4_address: 172.20.0.14
@@ -152,39 +151,9 @@ services:
       jan_community:
         ipv4_address: 172.20.0.15
 
-  # 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 ${MODEL_URL}; fi"
-    # Mount a local directory to store the downloaded model.
-    volumes:
-      - ./jan-inference/llm/models:/models
-
-    networks:
-      jan_community:
-        ipv4_address: 172.20.0.16
-
-  # Service to wait for the downloader service to finish downloading the model.
-  wait-for-downloader:
-    image: busybox
-    # The command waits until the model file (specified in MODEL_URL) exists.
-    command: /bin/sh -c "LLM_MODEL_FILE=$(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:
-      - ./jan-inference/llm/models:/models
-
-    networks:
-      jan_community:
-        ipv4_address: 172.20.0.17
-
   # Service to run the Llama web application.
   llm:
-    image: ghcr.io/abetlen/llama-cpp-python:latest
+    image: ghcr.io/abetlen/llama-cpp-python@sha256:b6d21ff8c4d9baad65e1fa741a0f8c898d68735fff3f3cd777e3f0c6a1839dd4
     # Mount the directory that contains the downloaded model.
     volumes:
       - ./jan-inference/llm/models:/models
@@ -192,20 +161,74 @@ services:
       - 8000:8000
     environment:
       # Specify the path to the model for the web application.
-      MODEL: /models/llama-2-7b-chat.ggmlv3.q4_1.bin
+      MODEL: /models/${LLM_MODEL_FILE}
       PYTHONUNBUFFERED: 1
     # 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:
       jan_community:
         ipv4_address: 172.20.0.18
 
+  sd-downloader:
+    build:
+      context: ./jan-inference/sd/
+      dockerfile: compile.Dockerfile
+    # The command extracts the model filename from MODEL_URL and downloads it if it doesn't exist.
+    command: /bin/sh -c "if [ ! -f /models/*.bin ]; then python /sd.cpp/sd_cpp/models/convert.py  --out_type q4_0 --out_file /models/${SD_MODEL_FILE}.q4_0.bin  /models/${SD_MODEL_FILE}; fi"
+    # Mount a local directory to store the downloaded model.
+    volumes:
+      - ./jan-inference/sd/models:/models
+    networks:
+      jan_community:
+        ipv4_address: 172.20.0.19
+
+  # Service to run the SD web application.
+  sd:
+    build:
+      context: ./jan-inference/sd/
+      dockerfile: inference.Dockerfile
+    # Mount the directory that contains the downloaded model.
+    volumes:
+      - ./jan-inference/sd/models:/models
+      - ./jan-inference/sd/output/:/serving/output
+    command:  /bin/bash -c "python -m uvicorn main:app --proxy-headers --host 0.0.0.0 --port 8000"
+    environment:
+      # Specify the path to the model for the web application.
+      BASE_URL: http://0.0.0.0:8000
+      MODEL_NAME: ${SD_MODEL_FILE}.q4_0.bin
+      MODEL_DIR: "/models"
+      SD_PATH: "/sd"
+      PYTHONUNBUFFERED: 1
+    ports:
+      - 8001:8000
+    # Restart policy configuration
+    restart: on-failure
+    # Specifies that this service should start only after wait-for-downloader has completed successfully.
+    depends_on:
+      sd-downloader:
+        condition: service_completed_successfully
+    networks:
+      jan_community:
+        ipv4_address: 172.20.0.21
+
+  # Service for Traefik, a modern HTTP reverse proxy and load balancer.
+  # traefik:
+  #   image: traefik:v2.10
+  #   ports:
+  #     # Map port 80 in the container to port 80 on the host.
+  #     - "80:80"
+  #     # Map port 8080 in the container (Traefik's dashboard) to port 8080 on the host.
+  #     - "8080:8080"
+  #   # Mount the Docker socket to allow Traefik to listen to Docker's API.
+  #   volumes:
+  #     - /var/run/docker.sock:/var/run/docker.sock:ro
+  #     - ./traefik/traefik.yml:/traefik.yml:ro
+  #     - ./traefik/config.yml:/config.yml:ro
+  #   networks:
+  #     jan_community:
+  #       ipv4_address: 172.20.0.22
+
 networks:  
   jan_community:
     driver: bridge