Fix bug janhq#2005 docker blank website (janhq#2093)

* Web: change API_BASE_URL to build time env * Update Dockerfile and Docker Compose by adding env API_BASE_URL * Update make clean * INFERENCE_URL get from baseApiUrl * Fix error settings/settings.json not found when start server at the first time * Update README docker --------- Co-authored-by: Hien To <[email protected]>
johnny-rice · Feb 19, 2024 · 2cbbe1b · 2cbbe1b
1 parent c17dc2e
commit 2cbbe1b
Show file tree

Hide file tree

Showing 10 changed files with 210 additions and 85 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -14,9 +14,6 @@ COPY . ./
 RUN export NITRO_VERSION=$(cat extensions/inference-nitro-extension/bin/version.txt) && \
     jq --arg nitroVersion $NITRO_VERSION '(.scripts."downloadnitro:linux" | gsub("\\${NITRO_VERSION}"; $nitroVersion)) | gsub("\r"; "")' extensions/inference-nitro-extension/package.json > /tmp/newcommand.txt && export NEW_COMMAND=$(sed 's/^"//;s/"$//' /tmp/newcommand.txt) && jq --arg newCommand "$NEW_COMMAND" '.scripts."downloadnitro:linux" = $newCommand' extensions/inference-nitro-extension/package.json > /tmp/package.json && mv /tmp/package.json extensions/inference-nitro-extension/package.json
 RUN make install-and-build
-RUN yarn workspace jan-web install
-
-RUN export NODE_ENV=production && yarn workspace jan-web build
 
 # # 2. Rebuild the source code only when needed
 FROM base AS runner
@@ -42,20 +39,23 @@ COPY --from=builder /app/docs/openapi ./docs/openapi/
 COPY --from=builder /app/pre-install ./pre-install/
 
 # Copy the package.json, yarn.lock, and output of web yarn space to leverage Docker cache
-COPY --from=builder /app/web/out ./web/out/
-COPY --from=builder /app/web/.next ./web/.next/
-COPY --from=builder /app/web/package.json ./web/package.json
-COPY --from=builder /app/web/yarn.lock ./web/yarn.lock
+COPY --from=builder /app/uikit ./uikit/
+COPY --from=builder /app/web ./web/
 COPY --from=builder /app/models ./models/
 
+RUN yarn workspace @janhq/uikit install && yarn workspace @janhq/uikit build
+RUN yarn workspace jan-web install
+
 RUN npm install -g serve@latest
 
 EXPOSE 1337 3000 3928
 
 ENV JAN_API_HOST 0.0.0.0
 ENV JAN_API_PORT 1337
 
-CMD ["sh", "-c", "cd server && node build/main.js & cd web && npx serve out"]
+ENV API_BASE_URL http://localhost:1337
+
+CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out & cd server && node build/main.js"]
 
 # docker build -t jan .
 # docker run -p 1337:1337 -p 3000:3000 -p 3928:3928 jan
diff --git a/Dockerfile.gpu b/Dockerfile.gpu
@@ -28,9 +28,6 @@ COPY . ./
 RUN export NITRO_VERSION=$(cat extensions/inference-nitro-extension/bin/version.txt) && \
     jq --arg nitroVersion $NITRO_VERSION '(.scripts."downloadnitro:linux" | gsub("\\${NITRO_VERSION}"; $nitroVersion)) | gsub("\r"; "")' extensions/inference-nitro-extension/package.json > /tmp/newcommand.txt && export NEW_COMMAND=$(sed 's/^"//;s/"$//' /tmp/newcommand.txt) && jq --arg newCommand "$NEW_COMMAND" '.scripts."downloadnitro:linux" = $newCommand' extensions/inference-nitro-extension/package.json > /tmp/package.json && mv /tmp/package.json extensions/inference-nitro-extension/package.json
 RUN make install-and-build
-RUN yarn workspace jan-web install
-
-RUN export NODE_ENV=production && yarn workspace jan-web build
 
 # # 2. Rebuild the source code only when needed
 FROM base AS runner
@@ -66,12 +63,13 @@ COPY --from=builder /app/docs/openapi ./docs/openapi/
 COPY --from=builder /app/pre-install ./pre-install/
 
 # Copy the package.json, yarn.lock, and output of web yarn space to leverage Docker cache
-COPY --from=builder /app/web/out ./web/out/
-COPY --from=builder /app/web/.next ./web/.next/
-COPY --from=builder /app/web/package.json ./web/package.json
-COPY --from=builder /app/web/yarn.lock ./web/yarn.lock
+COPY --from=builder /app/uikit ./uikit/
+COPY --from=builder /app/web ./web/
 COPY --from=builder /app/models ./models/
 
+RUN yarn workspace @janhq/uikit install && yarn workspace @janhq/uikit build
+RUN yarn workspace jan-web install
+
 RUN npm install -g serve@latest
 
 EXPOSE 1337 3000 3928
@@ -81,7 +79,9 @@ ENV LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib:/usr/local/cuda-12.
 ENV JAN_API_HOST 0.0.0.0
 ENV JAN_API_PORT 1337
 
-CMD ["sh", "-c", "cd server && node build/main.js & cd web && npx serve out"]
+ENV API_BASE_URL http://localhost:1337
+
+CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out & cd server && node build/main.js"]
 
 # pre-requisites: nvidia-docker
 # docker build -t jan-gpu . -f Dockerfile.gpu

diff --git a/Makefile b/Makefile
@@ -52,18 +52,28 @@ build: check-file-counts
 
 clean:
 ifeq ($(OS),Windows_NT)
-	powershell -Command "Get-ChildItem -Path . -Include node_modules, .next, dist -Recurse -Directory | Remove-Item -Recurse -Force"
+	powershell -Command "Get-ChildItem -Path . -Include node_modules, .next, dist, build, out -Recurse -Directory | Remove-Item -Recurse -Force"
+	powershell -Command "Remove-Item -Recurse -Force ./pre-install/*.tgz"
+	powershell -Command "Remove-Item -Recurse -Force ./electron/pre-install/*.tgz"
 	rmdir /s /q "%USERPROFILE%\jan\extensions"
 else ifeq ($(shell uname -s),Linux)
 	find . -name "node_modules" -type d -prune -exec rm -rf '{}' +
 	find . -name ".next" -type d -exec rm -rf '{}' +
 	find . -name "dist" -type d -exec rm -rf '{}' +
+	find . -name "build" -type d -exec rm -rf '{}' +
+	find . -name "out" -type d -exec rm -rf '{}' +
+	rm -rf ./pre-install/*.tgz
+	rm -rf ./electron/pre-install/*.tgz
 	rm -rf "~/jan/extensions"
 	rm -rf "~/.cache/jan*"
 else
 	find . -name "node_modules" -type d -prune -exec rm -rf '{}' +
 	find . -name ".next" -type d -exec rm -rf '{}' +
 	find . -name "dist" -type d -exec rm -rf '{}' +
+	find . -name "build" -type d -exec rm -rf '{}' +
+	find . -name "out" -type d -exec rm -rf '{}' +
+	rm -rf ./pre-install/*.tgz
+	rm -rf ./electron/pre-install/*.tgz
 	rm -rf ~/jan/extensions
 	rm -rf ~/Library/Caches/jan*
 endif
diff --git a/README.md b/README.md
@@ -235,61 +235,84 @@ This will build the app MacOS m1/m2 for production (with code signing already do
 
 - Run Jan in Docker mode
 
-  - **Option 1**: Run Jan in CPU mode
+| Docker compose Profile | Description                                  |
+| ---------------------- | -------------------------------------------- |
+| `cpu-fs`               | Run Jan in CPU mode with default file system |
+| `cpu-s3fs`             | Run Jan in CPU mode with S3 file system      |
+| `gpu-fs`               | Run Jan in GPU mode with default file system |
+| `gpu-s3fs`             | Run Jan in GPU mode with S3 file system      |
+
+| Environment Variable    | Description                                                                                             |
+| ----------------------- | ------------------------------------------------------------------------------------------------------- |
+| `S3_BUCKET_NAME`        | S3 bucket name - leave blank for default file system                                                    |
+| `AWS_ACCESS_KEY_ID`     | AWS access key ID - leave blank for default file system                                                 |
+| `AWS_SECRET_ACCESS_KEY` | AWS secret access key - leave blank for default file system                                             |
+| `AWS_ENDPOINT`          | AWS endpoint URL - leave blank for default file system                                                  |
+| `AWS_REGION`            | AWS region - leave blank for default file system                                                        |
+| `API_BASE_URL`          | Jan Server URL, please modify it as your public ip address or domain name default http://localhost:1377 |
+
+- **Option 1**: Run Jan in CPU mode
+
+  ```bash
+  # cpu mode with default file system
+  docker compose --profile cpu-fs up -d
+
+  # cpu mode with S3 file system
+  docker compose --profile cpu-s3fs up -d
+  ```
+
+- **Option 2**: Run Jan in GPU mode
+
+  - **Step 1**: Check CUDA compatibility with your NVIDIA driver by running `nvidia-smi` and check the CUDA version in the output
+
+    ```bash
+    nvidia-smi
+
+    # Output
+    +---------------------------------------------------------------------------------------+
+    | NVIDIA-SMI 531.18                 Driver Version: 531.18       CUDA Version: 12.1     |
+    |-----------------------------------------+----------------------+----------------------+
+    | GPU  Name                      TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
+    | Fan  Temp  Perf            Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
+    |                                         |                      |               MIG M. |
+    |=========================================+======================+======================|
+    |   0  NVIDIA GeForce RTX 4070 Ti    WDDM | 00000000:01:00.0  On |                  N/A |
+    |  0%   44C    P8               16W / 285W|   1481MiB / 12282MiB |      2%      Default |
+    |                                         |                      |                  N/A |
+    +-----------------------------------------+----------------------+----------------------+
+    |   1  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:02:00.0 Off |                  N/A |
+    |  0%   49C    P8               14W / 120W|      0MiB /  6144MiB |      0%      Default |
+    |                                         |                      |                  N/A |
+    +-----------------------------------------+----------------------+----------------------+
+    |   2  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:05:00.0 Off |                  N/A |
+    | 29%   38C    P8               11W / 120W|      0MiB /  6144MiB |      0%      Default |
+    |                                         |                      |                  N/A |
+    +-----------------------------------------+----------------------+----------------------+
+
+    +---------------------------------------------------------------------------------------+
+    | Processes:                                                                            |
+    |  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
+    |        ID   ID                                                             Usage      |
+    |=======================================================================================|
+    ```
+
+  - **Step 2**: Visit [NVIDIA NGC Catalog ](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags) and find the smallest minor version of image tag that matches your CUDA version (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:12.2.0-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
-    docker compose --profile cpu up -d
+    # GPU mode with default file system
+    docker compose --profile gpu up -d
+
+    # GPU mode with S3 file system
+    docker compose --profile gpu-s3fs up -d
     ```
 
-  - **Option 2**: Run Jan in GPU mode
-
-    - **Step 1**: Check CUDA compatibility with your NVIDIA driver by running `nvidia-smi` and check the CUDA version in the output
-
-      ```bash
-      nvidia-smi
-
-      # Output
-      +---------------------------------------------------------------------------------------+
-      | NVIDIA-SMI 531.18                 Driver Version: 531.18       CUDA Version: 12.1     |
-      |-----------------------------------------+----------------------+----------------------+
-      | GPU  Name                      TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
-      | Fan  Temp  Perf            Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
-      |                                         |                      |               MIG M. |
-      |=========================================+======================+======================|
-      |   0  NVIDIA GeForce RTX 4070 Ti    WDDM | 00000000:01:00.0  On |                  N/A |
-      |  0%   44C    P8               16W / 285W|   1481MiB / 12282MiB |      2%      Default |
-      |                                         |                      |                  N/A |
-      +-----------------------------------------+----------------------+----------------------+
-      |   1  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:02:00.0 Off |                  N/A |
-      |  0%   49C    P8               14W / 120W|      0MiB /  6144MiB |      0%      Default |
-      |                                         |                      |                  N/A |
-      +-----------------------------------------+----------------------+----------------------+
-      |   2  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:05:00.0 Off |                  N/A |
-      | 29%   38C    P8               11W / 120W|      0MiB /  6144MiB |      0%      Default |
-      |                                         |                      |                  N/A |
-      +-----------------------------------------+----------------------+----------------------+
-
-      +---------------------------------------------------------------------------------------+
-      | Processes:                                                                            |
-      |  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
-      |        ID   ID                                                             Usage      |
-      |=======================================================================================|
-      ```
-
-    - **Step 2**: Visit [NVIDIA NGC Catalog ](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags) and find the smallest minor version of image tag that matches your CUDA version (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:12.2.0-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 -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.
+This will start the web server and you can access Jan at `http://localhost:3000`.
+
+> Note: RAG feature is not supported in Docker mode with s3fs yet.
 
 ## Acknowledgements
 

diff --git a/docker-compose.yml b/docker-compose.yml
@@ -42,10 +42,10 @@ services:
       vpcbr:
 
   # app_cpu service for running the CPU version of the application
-  app_cpu:
+  app_cpu_s3fs:
     image: jan:latest
     volumes:
-      - app_data:/app/server/build/jan
+      - app_data_cpu_s3fs:/app/server/build/jan
     build:
       context: .
       dockerfile: Dockerfile
@@ -56,9 +56,10 @@ services:
       S3_BUCKET_NAME: mybucket
       AWS_ENDPOINT: http://10.5.0.2:9000
       AWS_REGION: us-east-1
+      API_BASE_URL: http://localhost:1337
     restart: always
     profiles:
-      - cpu
+      - cpu-s3fs
     ports:
       - "3000:3000"
       - "1337:1337"
@@ -68,7 +69,7 @@ services:
         ipv4_address: 10.5.0.3
 
   # app_gpu service for running the GPU version of the application
-  app_gpu:
+  app_gpu_s3fs:
     deploy:
       resources:
         reservations:
@@ -78,7 +79,7 @@ services:
             capabilities: [gpu]
     image: jan-gpu:latest
     volumes:
-      - app_data:/app/server/build/jan
+      - app_data_gpu_s3fs:/app/server/build/jan
     build:
       context: .
       dockerfile: Dockerfile.gpu
@@ -90,8 +91,9 @@ services:
       S3_BUCKET_NAME: mybucket
       AWS_ENDPOINT: http://10.5.0.2:9000
       AWS_REGION: us-east-1
+      API_BASE_URL: http://localhost:1337
     profiles:
-      - gpu
+      - gpu-s3fs
     ports:
       - "3000:3000"
       - "1337:1337"
@@ -100,9 +102,60 @@ services:
       vpcbr:
         ipv4_address: 10.5.0.4
 
+  app_cpu_fs:
+    image: jan:latest
+    volumes:
+      - app_data_cpu_fs:/app/server/build/jan
+    build:
+      context: .
+      dockerfile: Dockerfile
+    environment:
+      API_BASE_URL: http://localhost:1337
+    restart: always
+    profiles:
+      - cpu-fs
+    ports:
+      - "3000:3000"
+      - "1337:1337"
+      - "3928:3928"
+    networks:
+      vpcbr:
+        ipv4_address: 10.5.0.5
+
+  # app_gpu service for running the GPU version of the application
+  app_gpu_fs:
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: all
+            capabilities: [gpu]
+    image: jan-gpu:latest
+    volumes:
+      - app_data_gpu_fs:/app/server/build/jan
+    build:
+      context: .
+      dockerfile: Dockerfile.gpu
+    restart: always
+    environment:
+      API_BASE_URL: http://localhost:1337
+    profiles:
+      - gpu-fs
+    ports:
+      - "3000:3000"
+      - "1337:1337"
+      - "3928:3928"
+    networks:
+      vpcbr:
+        ipv4_address: 10.5.0.6
+
 volumes:
   minio_data:
-  app_data:
+  app_data_cpu_s3fs:
+  app_data_gpu_s3fs:
+  app_data_cpu_fs:
+  app_data_gpu_fs:
 
 networks:
   vpcbr:
@@ -113,5 +166,7 @@ networks:
          gateway: 10.5.0.1
 
 # Usage:
-# - 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
+# - Run 'docker compose --profile cpu-s3fs up -d' to start the app_cpu service
+# - Run 'docker compose --profile gpu-s3fs up -d' to start the app_gpu service
+# - Run 'docker compose --profile cpu-fs up -d' to start the app_cpu service
+# - Run 'docker compose --profile gpu-fs up -d' to start the app_gpu service
diff --git a/extensions/inference-nitro-extension/src/index.ts b/extensions/inference-nitro-extension/src/index.ts
@@ -88,7 +88,7 @@ export default class JanInferenceNitroExtension extends InferenceExtension {
     const electronApi = window?.electronAPI
     this.inferenceUrl = INFERENCE_URL
     if (!electronApi) {
-      this.inferenceUrl = JAN_SERVER_INFERENCE_URL
+      this.inferenceUrl = `${window.core?.api?.baseApiUrl}/v1/chat/completions`
     }
     console.debug('Inference url: ', this.inferenceUrl)