Master 4.0 (#2210)

* stage academic conversation

* stage document conversation

* fix buggy gradio version

* file dynamic load

* merge more academic plugins

* accelerate nltk

* feat: 为predict函数添加文件和URL读取功能
- 添加URL检测和网页内容提取功能，支持自动提取网页文本
- 添加文件路径识别和文件内容读取功能，支持private_upload路径格式
- 集成WebTextExtractor处理网页内容提取
- 集成TextContentLoader处理本地文件读取
- 支持文件路径与问题组合的智能处理

* back

* block unstable

---------

Co-authored-by: XiaoBoAI <liuboyin2019@ia.ac.cn>

check_proxy.py

@@ -230,6 +230,48 @@ def warm_up_modules():
         enc.encode("模块预热", disallowed_special=())
         enc = model_info["gpt-4"]['tokenizer']
         enc.encode("模块预热", disallowed_special=())
+        try_warm_up_vectordb()
+
+
+# def try_warm_up_vectordb():
+#     try:
+#         import os
+#         import nltk
+#         target = os.path.expanduser('~/nltk_data')
+#         logger.info(f'模块预热: nltk punkt (从Github下载部分文件到 {target})')
+#         nltk.data.path.append(target)
+#         nltk.download('punkt', download_dir=target)
+#         logger.info('模块预热完成: nltk punkt')
+#     except:
+#         logger.exception('模块预热: nltk punkt 失败，可能需要手动安装 nltk punkt')
+#         logger.error('模块预热: nltk punkt 失败，可能需要手动安装 nltk punkt')
+
+
+def try_warm_up_vectordb():
+    import os
+    import nltk
+    target = os.path.expanduser('~/nltk_data')
+    nltk.data.path.append(target)
+    try:
+        # 尝试加载 punkt
+        logger.info(f'nltk模块预热')
+        nltk.data.find('tokenizers/punkt')
+        nltk.data.find('tokenizers/punkt_tab')
+        nltk.data.find('taggers/averaged_perceptron_tagger_eng')
+        logger.info('nltk模块预热完成（读取本地缓存）')
+    except:
+        # 如果找不到，则尝试下载
+        try:
+            logger.info(f'模块预热: nltk punkt (从 Github 下载部分文件到 {target})')
+            from shared_utils.nltk_downloader import Downloader
+            _downloader = Downloader()
+            _downloader.download('punkt', download_dir=target)
+            _downloader.download('punkt_tab', download_dir=target)
+            _downloader.download('averaged_perceptron_tagger_eng', download_dir=target)
+            logger.info('nltk模块预热完成')
+        except Exception:
+            logger.exception('模块预热: nltk punkt 失败，可能需要手动安装 nltk punkt')
+
 
 def warm_up_vectordb():
     """