Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,19 +1,23 @@
-FROM python:3.12-bookworm
+FROM hectorqin/reader:latest
 
-RUN apt update && apt install -y git make
-RUN useradd -m -u 1000 user
-ENV PATH="/home/user/.local/bin:$PATH"
+RUN apk update && \
+    apk add --no-cache python3 python3-dev py3-pip curl libxml2-dev libxslt-dev gcc musl-dev && \
+    rm -rf /var/cache/apk/*
 
-RUN git clone https://github.com/embeddings-benchmark/mteb.git
-RUN chown -R user:user /mteb
+RUN mkdir -p /logs /storage /file-uploads /data
 
-USER user
-WORKDIR /mteb
+RUN chmod a+w /logs /storage /file-uploads /data
 
-RUN pip install "pydantic<2.11"
-RUN pip install ".[leaderboard]"
-# ENV XDG_CACHE_HOME=/home/user/.cache
-ENV GRADIO_SERVER_NAME="0.0.0.0"
-EXPOSE 7860
+ENV VIRTUAL_ENV=/opt/venv
+RUN python3 -m venv $VIRTUAL_ENV
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
-CMD ["make", "run-leaderboard"]
+RUN pip install --upgrade pip
+
+RUN pip install --no-cache-dir requests webdavclient3
+
+COPY sync_data.sh /sync_data.sh
+
+RUN chmod +x /sync_data.sh
+
+CMD ["/bin/sh", "/sync_data.sh"]

README.md

@@ -1,20 +1,15 @@
 ---
-title: MTEB Leaderboard
-emoji: 🥇
+title: "1"
+emoji: "🚀"
 colorFrom: blue
-colorTo: indigo
+colorTo: green
 sdk: docker
-app_port: 7860
-app_file: app.py
-pinned: true
-tags:
-- leaderboard
-startup_duration_timeout: 1h
-fullWidth: true
-license: mit
-short_description: Embedding Leaderboard
+app_port: 8080
 ---
 
-# MTEB Leaderboard
+### 🚀 一键部署
+[![Deploy with HFSpaceDeploy](https://img.shields.io/badge/Deploy_with-HFSpaceDeploy-green?style=social&logo=rocket)](https://github.com/kfcx/HFSpaceDeploy)
 
-Embedding Leaderboard
+本项目由[HFSpaceDeploy](https://github.com/kfcx/HFSpaceDeploy)一键部署
+
+Track, rank and evaluate open LLMs and chatbots

sync_data.sh

@@ -0,0 +1,112 @@
+#!/bin/sh
+
+# 检查环境变量
+if [ -z "$WEBDAV_URL" ] || [ -z "$WEBDAV_USERNAME" ] || [ -z "$WEBDAV_PASSWORD" ]; then
+    echo "Starting without backup functionality - missing WEBDAV_URL, WEBDAV_USERNAME, or WEBDAV_PASSWORD"
+    exec java -jar /app/bin/reader.jar
+    exit 0
+fi
+
+# 设置备份路径
+WEBDAV_BACKUP_PATH=${WEBDAV_BACKUP_PATH:-""}
+FULL_WEBDAV_URL="${WEBDAV_URL}"
+if [ -n "$WEBDAV_BACKUP_PATH" ]; then
+    FULL_WEBDAV_URL="${WEBDAV_URL}/${WEBDAV_BACKUP_PATH}"
+fi
+
+# 下载最新备份并恢复
+restore_backup() {
+    python3 -c "
+import sys
+import os
+import tarfile
+import requests
+from webdav3.client import Client
+options = {
+    'webdav_hostname': '$FULL_WEBDAV_URL',
+    'webdav_login': '$WEBDAV_USERNAME',
+    'webdav_password': '$WEBDAV_PASSWORD'
+}
+client = Client(options)
+backups = [file for file in client.list() if file.endswith('.tar.gz') and file.startswith('reader_backup_')]
+if not backups:
+    print('No backup files found')
+    sys.exit()
+latest_backup = sorted(backups)[-1]
+with requests.get(f'$FULL_WEBDAV_URL/{latest_backup}', auth=('$WEBDAV_USERNAME', '$WEBDAV_PASSWORD'), stream=True) as r:
+    if r.status_code == 200:
+        with open(f'/tmp/{latest_backup}', 'wb') as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+        
+        if os.path.exists(f'/tmp/{latest_backup}'):
+            with tarfile.open(f'/tmp/{latest_backup}', 'r:gz') as tar:
+                tar.extractall('/storage')
+            print(f'Successfully restored backup from {latest_backup}')
+        else:
+            print('Failed to download backup file')
+    else:
+        print(f'Failed to download backup: {r.status_code}')
+"
+}
+
+# 首次启动时下载最新备份
+echo "Downloading latest backup from WebDAV..."
+restore_backup
+
+# 同步函数
+sync_data() {
+    while true; do
+        echo "Starting sync process at $(date)"
+
+        if [ -d /storage ]; then
+            timestamp=$(date +%Y%m%d_%H%M%S)
+            backup_file="reader_backup_${timestamp}.tar.gz"
+
+            # 压缩数据目录
+            tar -czf "/tmp/${backup_file}" -C /storage .
+
+            # 上传新备份到WebDAV
+            curl -u "$WEBDAV_USERNAME:$WEBDAV_PASSWORD" -T "/tmp/${backup_file}" "$FULL_WEBDAV_URL/${backup_file}"
+            if [ $? -eq 0 ]; then
+                echo "Successfully uploaded ${backup_file} to WebDAV"
+            else
+                echo "Failed to upload ${backup_file} to WebDAV"
+            fi
+
+            # 清理旧备份文件
+            python3 -c "
+import sys
+from webdav3.client import Client
+options = {
+    'webdav_hostname': '$FULL_WEBDAV_URL',
+    'webdav_login': '$WEBDAV_USERNAME',
+    'webdav_password': '$WEBDAV_PASSWORD'
+}
+client = Client(options)
+backups = [file for file in client.list() if file.endswith('.tar.gz') and file.startswith('reader_backup_')]
+backups.sort()
+if len(backups) > 2:
+    to_delete = len(backups) - 2
+    for file in backups[:to_delete]:
+        client.clean(file)
+        print(f'Successfully deleted {file}.')
+else:
+    print('Only {} backups found, no need to clean.'.format(len(backups)))
+" 2>&1
+
+            rm -f "/tmp/${backup_file}"
+        else
+            echo "/storage directory does not exist, waiting for next sync..."
+        fi
+
+        SYNC_INTERVAL=${SYNC_INTERVAL:-600}
+        sleep $SYNC_INTERVAL
+    done
+}
+
+# 后台启动同步进程
+sync_data &
+
+# 启动应用程序主进程
+exec java -jar /app/bin/reader.jar