Update Dockerfile

Dockerfile

@@ -1,164 +1,28 @@
-#!/bin/sh
+FROM ghcr.io/open-webui/open-webui:main
 
-# 检查环境变量
-if [ -z "$HF_TOKEN" ] || [ -z "$DATASET_ID" ]; then
-    echo "未检测到 HF_TOKEN 或 DATASET_ID，备份功能不可用"
-    # 修改为返回 0，避免容器启动失败
-    exit 0
-fi
+# 安装必要的依赖
+RUN apt-get update && apt-get install -y python3 python3-pip
 
-# 激活虚拟环境（如果需要）
-if [ -d "$HOME/venv" ]; then
-    echo "激活虚拟环境..."
-    . $HOME/venv/bin/activate
-else
-    echo "未找到虚拟环境，使用系统 Python..."
-fi
+# 安装 huggingface_hub 库
+RUN pip3 install --no-cache-dir huggingface_hub
 
-# 生成同步脚本
-cat > /app/hf_sync.py << 'EOL'
-# HuggingFace 同步脚本
-from huggingface_hub import HfApi
-import sys
-import os
-import tarfile
-import tempfile
+# 设置必要的环境变量（根据实际需求调整）
+ENV HF_HOME="/app/data/huggingface"
+ENV HUGGINGFACE_HUB_CACHE="/app/data/huggingface"
 
-# 管理备份文件数量，超出最大数量则自动删除最旧的备份
-def manage_backups(api, repo_id, max_files=50):
-    files = api.list_repo_files(repo_id=repo_id, repo_type="dataset")
-    backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
-    backup_files.sort()
-    if len(backup_files) >= max_files:
-        files_to_delete = backup_files[:(len(backup_files) - max_files + 1)]
-        for file_to_delete in files_to_delete:
-            try:
-                api.delete_file(path_in_repo=file_to_delete, repo_id=repo_id, repo_type="dataset")
-                print(f'已删除旧备份: {file_to_delete}')
-            except Exception as e:
-                print(f'删除 {file_to_delete} 时出错: {str(e)}')
+# 复制同步数据脚本
+COPY sync_data.sh /app/
 
-# 上传备份文件到 HuggingFace
-def upload_backup(file_path, file_name, token, repo_id):
-    api = HfApi(token=token)
-    try:
-        api.upload_file(
-            path_or_fileobj=file_path,
-            path_in_repo=file_name,
-            repo_id=repo_id,
-            repo_type="dataset"
-        )
-        print(f"成功上传 {file_name}")
-        manage_backups(api, repo_id)
-    except Exception as e:
-        print(f"上传文件出错: {str(e)}")
+# 设置权限
+RUN chmod -R 777 /app/data && \
+    chmod -R 777 /app/open_webui && \
+    chmod +x /app/sync_data.sh
 
-# 下载最新备份
-def download_latest_backup(token, repo_id, extract_path):
-    try:
-        api = HfApi(token=token)
-        files = api.list_repo_files(repo_id=repo_id, repo_type="dataset")
-        backup_files = [f for f in files if f.startswith('backup_') and f.endswith('.tar.gz')]
-        if not backup_files:
-            print("未找到任何备份文件")
-            return
-        latest_backup = sorted(backup_files)[-1]
-        with tempfile.TemporaryDirectory() as temp_dir:
-            filepath = api.hf_hub_download(
-                repo_id=repo_id,
-                filename=latest_backup,
-                repo_type="dataset",
-                local_dir=temp_dir
-            )
-            if filepath and os.path.exists(filepath):
-                with tarfile.open(filepath, 'r:gz') as tar:
-                    tar.extractall(extract_path)
-                print(f"已成功恢复备份: {latest_backup}")
-    except Exception as e:
-        print(f"下载备份出错: {str(e)}")
+# 修改启动脚本，确保同步脚本在启动时执行
+RUN sed -i "1r /app/sync_data.sh" /app/start.sh
 
-# 合并历史提交
-def super_squash_history(token, repo_id):
-    try:
-        api = HfApi(token=token)
-        api.super_squash_history(repo_id=repo_id, repo_type="dataset")
-        print("历史合并完成。")
-    except Exception as e:
-        print(f"合并历史出错: {str(e)}")
+# 暴露端口（根据应用需求调整）
+EXPOSE 3000
 
-# 主函数
-if __name__ == "__main__":
-    action = sys.argv[1]
-    token = sys.argv[2]
-    repo_id = sys.argv[3]
-    if action == "upload":
-        file_path = sys.argv[4]
-        file_name = sys.argv[5]
-        upload_backup(file_path, file_name, token, repo_id)
-    elif action == "download":
-        extract_path = sys.argv[4] if len(sys.argv) > 4 else '.'
-        download_latest_backup(token, repo_id, extract_path)
-    elif action == "super_squash":
-        super_squash_history(token, repo_id)
-EOL
-
-# 首次启动时从 HuggingFace 下载最新备份（解压到应用目录）
-echo "正在从 HuggingFace 下载最新备份..."
-python3 /app/hf_sync.py download "${HF_TOKEN}" "${DATASET_ID}" "/app/data"  
-
-# 同步函数
-sync_data() {
-    while true; do
-        echo "同步进程启动于 $(date)"
-        
-        # 确保数据目录存在
-        DATA_DIR="/app/data"
-        DB_FILE="${DATA_DIR}/webui.db"
-        
-        if [ -f "${DB_FILE}" ]; then
-            # 创建备份
-            timestamp=$(date +%Y%m%d_%H%M%S)
-            backup_file="backup_${timestamp}.tar.gz"
-            
-            # 压缩文件
-            tar -czf "/tmp/${backup_file}" -C "${DATA_DIR}" "webui.db"
-            
-            # 上传到 HuggingFace
-            echo "正在上传备份到 HuggingFace..."
-            python3 /app/hf_sync.py upload "${HF_TOKEN}" "${DATASET_ID}" "/tmp/${backup_file}" "${backup_file}"
-            
-            # 合并历史提交
-            SQUASH_FLAG_FILE="/tmp/last_squash_time"
-            NOW=$(date +%s)
-            SEVEN_DAYS=$((7*24*60*60))
-            if [ ! -f "$SQUASH_FLAG_FILE" ]; then
-                echo $NOW > "$SQUASH_FLAG_FILE"
-                echo "首次合并历史提交..."
-                python3 /app/hf_sync.py super_squash "${HF_TOKEN}" "${DATASET_ID}"
-            else
-                LAST=$(cat "$SQUASH_FLAG_FILE")
-                DIFF=$((NOW - LAST))
-                if [ $DIFF -ge $SEVEN_DAYS ]; then
-                    echo $NOW > "$SQUASH_FLAG_FILE"
-                    echo "距离上次合并已超过7天，正在合并历史提交..."
-                    python3 /app/hf_sync.py super_squash "${HF_TOKEN}" "${DATASET_ID}"
-                else
-                    echo "距离上次合并未满7天，本次跳过合并历史提交。"
-                fi
-            fi
-
-            # 清理临时文件
-            rm -f "/tmp/${backup_file}"
-        else
-            echo "数据库文件 ${DB_FILE} 不存在，等待中..."
-        fi
-        
-        # 同步间隔
-        SYNC_INTERVAL=${SYNC_INTERVAL:-7200}
-        echo "下次同步将在 ${SYNC_INTERVAL} 秒后进行..."
-        sleep $SYNC_INTERVAL
-    done
-}
-
-# 启动同步进程（在后台运行）
-sync_data &
+# 启动应用
+CMD ["/app/start.sh"]