Merge branch 'v0.1.0' of github.com:kuwaai/genai-os into v0.1.0

docker/README.md

@@ -120,4 +120,27 @@ The files are as follows:
 Start the basic Kuwa GenAI OS system, PostgreSQL and Gemini-Pro Executor using Docker Compose
 ```sh
 docker compose -f compose.yaml -f pgsql.yaml -f gemini.yaml up --build
+```
+
+## Advanced Usage
+
+### 1. Launch Debug Mode
+The docker version will not display any error message on the Multi-Chat web frontend by default. If you encounter an error, you can use the following command to enable the debug mode.
+```sh
+docker compose -f compose.yaml -f dev.yaml -f <other yaml files...> up --build
+```
+
+### 2. Run Multiple Executors
+The settings for each Executor are already written in the corresponding YAML files (gemini.yaml, chatgpt.yaml, huggingface.yaml, llamacpp.yaml), please refer to these configuration files and extend them according to your needs.  
+You may need to refer to the [Executor documentation](../src/executor/README.md).  
+Once the configuration files are complete, you can use the following command to start the entire system
+```sh
+docker compose -f compose.yaml -f pgsql.yaml -f <executor1 configuration file> -f <executor2 configuration file...> up --build
+```
+
+### 3. Force Upgrade
+If your database is accidentally lost or damaged, you can force upgrade it  
+Please make sure the system is running, then use the following command to force upgrade the database  
+```sh
+docker exec -it kuwa-multi-chat-1 docker-entrypoint force-upgrade
 ```

docker/README_TW.md

@@ -131,11 +131,11 @@ docker compose -f compose.yaml -f dev.yaml -f <其他 yaml 檔案...> up --build
 ```
 
 ### 2. 執行多個 Executor
-每種 Executor 的設定都已寫在對應的 YAML 檔案中 (gemini.yaml, chatgpt.yaml, huggingface.yaml)，請參考這些設定檔按照您的需求擴充。  
+每種 Executor 的設定都已寫在對應的 YAML 檔案中 (gemini.yaml, chatgpt.yaml, huggingface.yaml, llamacpp.yaml)，請參考這些設定檔按照您的需求擴充。  
 您可能需要參考 [Executor 說明文件](../src/executor/README_TW.md)。  
 完成設定檔後可使用以下指令啟動整個系統
 ```sh
-docker compose -f compose.yaml -f pgsql.yaml -f <Executor1設定檔> -f <Executor2設定檔...> up --build
+docker compose -f compose.yaml -f pgsql.yaml -f <executor1設定檔> -f <executor2設定檔...> up --build
 ```
 
 ### 3. 強制更新

docker/llamacpp.yaml

@@ -0,0 +1,24 @@
+services:
+  llamacpp-executor:
+    build:
+      context: ../
+      dockerfile: docker/executor/Dockerfile
+    image: kuwa-executor
+    environment:
+      EXECUTOR_TYPE: llamacpp
+      EXECUTOR_ACCESS_CODE: taide-4bit
+      EXECUTOR_NAME: TAIDE 4bit
+    depends_on:
+      - kernel
+      - multi-chat
+    command: ["--model_path", "/var/model/taide-4bit.gguf", "--ngl", "-1", "--temperature", "0"]
+    restart: unless-stopped
+    volumes: ["/path/to/taide/model.gguf:/var/model/taide-4bit.gguf"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            device_ids: ['0']
+            capabilities: [gpu]
+    networks: ["backend"]