Change env Dockerfile.gpu and update README (#1963)

Co-authored-by: Hien To <tominhhien97@gmail.com>

Dockerfile.gpu

@@ -2,7 +2,7 @@
 # Run nvidia-smi to check the CUDA version and the corresponding driver version
 # Then update the base image to the appropriate CUDA version refer https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags
 
-FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04 AS base 
+FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base 
 
 # 1. Install dependencies only when needed
 FROM base AS builder
@@ -73,7 +73,7 @@ RUN npm install -g serve@latest
 
 EXPOSE 1337 3000 3928
 
-ENV LD_LIBRARY_PATH=/usr/local/cuda-12.0/targets/x86_64-linux/lib:/usr/local/cuda-12.0/compat${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
+ENV LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib:/usr/local/cuda-12.0/compat${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
 
 ENV JAN_API_HOST 0.0.0.0
 ENV JAN_API_PORT 1337

README.md

@@ -236,7 +236,7 @@ This will build the app MacOS m1/m2 for production (with code signing already do
   - **Option 1**: Run Jan in CPU mode
 
     ```bash
-    docker compose --profile cpu up
+    docker compose --profile cpu up -d
     ```
 
   - **Option 2**: Run Jan in GPU mode
@@ -274,18 +274,19 @@ This will build the app MacOS m1/m2 for production (with code signing already do
       |=======================================================================================|
       ```
 
-    - **Step 2**: Go to https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags and find the lates minor version of image tag that matches the cuda version from the output of `nvidia-smi` (e.g. 12.1 -> 12.1.0)
+    - **Step 2**: Go to https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags and find the smallest minor version of image tag that matches the cuda version from the output of `nvidia-smi` (e.g. 12.1 -> 12.1.0)
 
-    - **Step 3**: Update the `Dockerfile.gpu` line number 5 with the latest minor version of the image tag from step 2 (e.g. change `FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04 AS base` to `FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS base`)
+    - **Step 3**: Update the `Dockerfile.gpu` line number 5 with the latest minor version of the image tag from step 2 (e.g. change `FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base` to `FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS base`)
 
     - **Step 4**: Run command to start Jan in GPU mode
 
       ```bash
       # GPU mode
-      docker compose --profile gpu up
+      docker compose --profile gpu up -d
       ```
 
   This will start the web server and you can access Jan at `http://localhost:3000`.
+  > Note: Currently, Docker mode is only work for development and localhost, production is not supported yet. RAG feature is not supported in Docker mode yet.
 
 ## Acknowledgements
 

docker-compose.yml

@@ -1,6 +1,9 @@
+# Docker Compose file for setting up Minio, createbuckets, app_cpu, and app_gpu services
+
 version: '3.7'
 
 services:
+  # Minio service for object storage
   minio:
     image: minio/minio
     volumes:
@@ -9,6 +12,7 @@ services:
       - "9000:9000"
       - "9001:9001"
     environment:
+      # Set the root user and password for Minio
       MINIO_ROOT_USER: minioadmin # This acts as AWS_ACCESS_KEY
       MINIO_ROOT_PASSWORD: minioadmin # This acts as AWS_SECRET_ACCESS_KEY
     command: server --console-address ":9001" /data
@@ -22,6 +26,7 @@ services:
       vpcbr:
         ipv4_address: 10.5.0.2
 
+  # createbuckets service to create a bucket and set its policy
   createbuckets:
     image: minio/mc
     depends_on:
@@ -36,7 +41,7 @@ services:
     networks:
       vpcbr:
 
-
+  # app_cpu service for running the CPU version of the application
   app_cpu:
     image: jan:latest
     volumes:
@@ -45,6 +50,7 @@ services:
       context: .
       dockerfile: Dockerfile
     environment:
+      # Set the AWS access key, secret access key, bucket name, endpoint, and region for app_cpu
       AWS_ACCESS_KEY_ID: minioadmin
       AWS_SECRET_ACCESS_KEY: minioadmin
       S3_BUCKET_NAME: mybucket
@@ -60,8 +66,8 @@ services:
     networks:
       vpcbr:
         ipv4_address: 10.5.0.3
-       
 
+  # app_gpu service for running the GPU version of the application
   app_gpu:
     deploy:
       resources:
@@ -78,12 +84,12 @@ services:
       dockerfile: Dockerfile.gpu
     restart: always
     environment:
+      # Set the AWS access key, secret access key, bucket name, endpoint, and region for app_gpu
       AWS_ACCESS_KEY_ID: minioadmin
       AWS_SECRET_ACCESS_KEY: minioadmin
       S3_BUCKET_NAME: mybucket
       AWS_ENDPOINT: http://10.5.0.2:9000
       AWS_REGION: us-east-1
-    
     profiles:
       - gpu
     ports:
@@ -106,5 +112,6 @@ networks:
        - subnet: 10.5.0.0/16
          gateway: 10.5.0.1
 
-# docker compose --profile cpu up
+# Usage:
-# docker compose --profile gpu up
+# - Run 'docker-compose --profile cpu up -d' to start the app_cpu service
+# - Run 'docker-compose --profile gpu up -d' to start the app_gpu service