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>

request_llms/embed_models/bridge_all_embed.py

@@ -8,13 +8,10 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
 openai_endpoint = "https://api.openai.com/v1/chat/completions"
 if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
-
-
 if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint]
-
 openai_embed_endpoint = openai_endpoint.replace("chat/completions", "embeddings")
 
-from .openai_embed import OpenAiEmbeddingModel
+from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
 
 embed_model_info = {
     # text-embedding-3-small    Increased performance over 2nd generation ada embedding model  |  1,536