Upload 85 files

ChuanhuChatbot.py

@@ -97,6 +97,7 @@ with gr.Blocks(css=customCSS, theme=small_and_beautiful_theme) as demo:
                     )
                     index_files = gr.Files(label=i18n("上传"), type="file")
                     two_column = gr.Checkbox(label=i18n("双栏pdf"), value=advance_docs["pdf"].get("two_column", False))
+                    summarize_btn = gr.Button(i18n("总结"))
                     # TODO: 公式ocr
                     # formula_ocr = gr.Checkbox(label=i18n("识别公式"), value=advance_docs["pdf"].get("formula_ocr", False))
 
@@ -333,6 +334,7 @@ with gr.Blocks(css=customCSS, theme=small_and_beautiful_theme) as demo:
     submitBtn.click(**get_usage_args)
 
     index_files.change(handle_file_upload, [current_model, index_files, chatbot, language_select_dropdown], [index_files, chatbot, status_display])
+    summarize_btn.click(handle_summarize_index, [current_model, index_files, chatbot, language_select_dropdown], [chatbot, status_display])
 
     emptyBtn.click(
         reset,
@@ -466,7 +468,13 @@ demo.title = i18n("川虎Chat 🚀")
 if __name__ == "__main__":
     reload_javascript()
     demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
+        blocked_paths=["config.json"],
+        server_name=server_name,
+        server_port=server_port,
+        share=share,
+        auth=auth_list if authflag else None,
         favicon_path="./assets/favicon.ico",
+        inbrowser=not dockerflag, # 禁止在docker下开启inbrowser
     )
     # demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", server_port=7860, share=False) # 可自定义端口
     # demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", server_port=7860,auth=("在这里填写用户名", "在这里填写密码")) # 可设置用户名与密码

README.md

@@ -4,7 +4,7 @@ emoji: 🐯
 colorFrom: green
 colorTo: red
 sdk: gradio
-sdk_version: 3.28.0
+sdk_version: 3.30.0
 app_file: ChuanhuChatbot.py
 pinned: false
 license: gpl-3.0

assets/custom.css

@@ -405,7 +405,7 @@ thead th {
     padding: .5em .2em;
 }
 /* 行内代码 */
-code {
+.message :not(pre) code {
     display: inline;
     white-space: break-spaces;
     border-radius: 6px;
@@ -414,13 +414,13 @@ code {
     background-color: rgba(175,184,193,0.2);
 }
 /* 代码块 */
-pre code {
+.message pre code {
     display: block;
     overflow: auto;
     white-space: pre;
     background-color: hsla(0, 0%, 0%, 80%)!important;
     border-radius: 10px;
-    padding: 1.4em 1.2em 0em 1.4em;
+    padding: 1.2em 1em 0em .5em;
     margin: 0.6em 2em 1em 0.2em;
     color: #FFF;
     box-shadow: 6px 6px 16px hsla(0, 0%, 0%, 0.2);
@@ -428,73 +428,81 @@ pre code {
 .message pre {
     padding: 0 !important;
 }
+.message pre code div.highlight {
+    background-color: unset !important;
+}
+
+button.copy-button {
+    display: none;
+}
+
 /* 代码高亮样式 */
-.highlight .hll { background-color: #49483e }
-.highlight .c { color: #75715e } /* Comment */
-.highlight .err { color: #960050; background-color: #1e0010 } /* Error */
-.highlight .k { color: #66d9ef } /* Keyword */
-.highlight .l { color: #ae81ff } /* Literal */
-.highlight .n { color: #f8f8f2 } /* Name */
-.highlight .o { color: #f92672 } /* Operator */
-.highlight .p { color: #f8f8f2 } /* Punctuation */
-.highlight .ch { color: #75715e } /* Comment.Hashbang */
-.highlight .cm { color: #75715e } /* Comment.Multiline */
-.highlight .cp { color: #75715e } /* Comment.Preproc */
-.highlight .cpf { color: #75715e } /* Comment.PreprocFile */
-.highlight .c1 { color: #75715e } /* Comment.Single */
-.highlight .cs { color: #75715e } /* Comment.Special */
-.highlight .gd { color: #f92672 } /* Generic.Deleted */
-.highlight .ge { font-style: italic } /* Generic.Emph */
-.highlight .gi { color: #a6e22e } /* Generic.Inserted */
-.highlight .gs { font-weight: bold } /* Generic.Strong */
-.highlight .gu { color: #75715e } /* Generic.Subheading */
-.highlight .kc { color: #66d9ef } /* Keyword.Constant */
-.highlight .kd { color: #66d9ef } /* Keyword.Declaration */
-.highlight .kn { color: #f92672 } /* Keyword.Namespace */
-.highlight .kp { color: #66d9ef } /* Keyword.Pseudo */
-.highlight .kr { color: #66d9ef } /* Keyword.Reserved */
-.highlight .kt { color: #66d9ef } /* Keyword.Type */
-.highlight .ld { color: #e6db74 } /* Literal.Date */
-.highlight .m { color: #ae81ff } /* Literal.Number */
-.highlight .s { color: #e6db74 } /* Literal.String */
-.highlight .na { color: #a6e22e } /* Name.Attribute */
-.highlight .nb { color: #f8f8f2 } /* Name.Builtin */
-.highlight .nc { color: #a6e22e } /* Name.Class */
-.highlight .no { color: #66d9ef } /* Name.Constant */
-.highlight .nd { color: #a6e22e } /* Name.Decorator */
-.highlight .ni { color: #f8f8f2 } /* Name.Entity */
-.highlight .ne { color: #a6e22e } /* Name.Exception */
-.highlight .nf { color: #a6e22e } /* Name.Function */
-.highlight .nl { color: #f8f8f2 } /* Name.Label */
-.highlight .nn { color: #f8f8f2 } /* Name.Namespace */
-.highlight .nx { color: #a6e22e } /* Name.Other */
-.highlight .py { color: #f8f8f2 } /* Name.Property */
-.highlight .nt { color: #f92672 } /* Name.Tag */
-.highlight .nv { color: #f8f8f2 } /* Name.Variable */
-.highlight .ow { color: #f92672 } /* Operator.Word */
-.highlight .w { color: #f8f8f2 } /* Text.Whitespace */
-.highlight .mb { color: #ae81ff } /* Literal.Number.Bin */
-.highlight .mf { color: #ae81ff } /* Literal.Number.Float */
-.highlight .mh { color: #ae81ff } /* Literal.Number.Hex */
-.highlight .mi { color: #ae81ff } /* Literal.Number.Integer */
-.highlight .mo { color: #ae81ff } /* Literal.Number.Oct */
-.highlight .sa { color: #e6db74 } /* Literal.String.Affix */
-.highlight .sb { color: #e6db74 } /* Literal.String.Backtick */
-.highlight .sc { color: #e6db74 } /* Literal.String.Char */
-.highlight .dl { color: #e6db74 } /* Literal.String.Delimiter */
-.highlight .sd { color: #e6db74 } /* Literal.String.Doc */
-.highlight .s2 { color: #e6db74 } /* Literal.String.Double */
-.highlight .se { color: #ae81ff } /* Literal.String.Escape */
-.highlight .sh { color: #e6db74 } /* Literal.String.Heredoc */
-.highlight .si { color: #e6db74 } /* Literal.String.Interpol */
-.highlight .sx { color: #e6db74 } /* Literal.String.Other */
-.highlight .sr { color: #e6db74 } /* Literal.String.Regex */
-.highlight .s1 { color: #e6db74 } /* Literal.String.Single */
-.highlight .ss { color: #e6db74 } /* Literal.String.Symbol */
-.highlight .bp { color: #f8f8f2 } /* Name.Builtin.Pseudo */
-.highlight .fm { color: #a6e22e } /* Name.Function.Magic */
-.highlight .vc { color: #f8f8f2 } /* Name.Variable.Class */
-.highlight .vg { color: #f8f8f2 } /* Name.Variable.Global */
-.highlight .vi { color: #f8f8f2 } /* Name.Variable.Instance */
-.highlight .vm { color: #f8f8f2 } /* Name.Variable.Magic */
-.highlight .il { color: #ae81ff } /* Literal.Number.Integer.Long */
+.highlight .hll { background-color: #49483e !important }
+.highlight .c { color: #75715e !important } /* Comment */
+.highlight .err { color: #960050 !important; background-color: #1e0010 } /* Error */
+.highlight .k { color: #66d9ef  !important} /* Keyword */
+.highlight .l { color: #ae81ff  !important} /* Literal */
+.highlight .n { color: #f8f8f2  !important} /* Name */
+.highlight .o { color: #f92672  !important} /* Operator */
+.highlight .p { color: #f8f8f2  !important} /* Punctuation */
+.highlight .ch { color: #75715e  !important} /* Comment.Hashbang */
+.highlight .cm { color: #75715e  !important} /* Comment.Multiline */
+.highlight .cp { color: #75715e  !important} /* Comment.Preproc */
+.highlight .cpf { color: #75715e  !important} /* Comment.PreprocFile */
+.highlight .c1 { color: #75715e  !important} /* Comment.Single */
+.highlight .cs { color: #75715e  !important} /* Comment.Special */
+.highlight .gd { color: #f92672  !important} /* Generic.Deleted */
+.highlight .ge { font-style: italic  !important} /* Generic.Emph */
+.highlight .gi { color: #a6e22e  !important} /* Generic.Inserted */
+.highlight .gs { font-weight: bold  !important} /* Generic.Strong */
+.highlight .gu { color: #75715e  !important} /* Generic.Subheading */
+.highlight .kc { color: #66d9ef  !important} /* Keyword.Constant */
+.highlight .kd { color: #66d9ef  !important} /* Keyword.Declaration */
+.highlight .kn { color: #f92672  !important} /* Keyword.Namespace */
+.highlight .kp { color: #66d9ef  !important} /* Keyword.Pseudo */
+.highlight .kr { color: #66d9ef  !important} /* Keyword.Reserved */
+.highlight .kt { color: #66d9ef  !important} /* Keyword.Type */
+.highlight .ld { color: #e6db74  !important} /* Literal.Date */
+.highlight .m { color: #ae81ff  !important} /* Literal.Number */
+.highlight .s { color: #e6db74  !important} /* Literal.String */
+.highlight .na { color: #a6e22e  !important} /* Name.Attribute */
+.highlight .nb { color: #f8f8f2  !important} /* Name.Builtin */
+.highlight .nc { color: #a6e22e  !important} /* Name.Class */
+.highlight .no { color: #66d9ef  !important} /* Name.Constant */
+.highlight .nd { color: #a6e22e  !important} /* Name.Decorator */
+.highlight .ni { color: #f8f8f2  !important} /* Name.Entity */
+.highlight .ne { color: #a6e22e  !important} /* Name.Exception */
+.highlight .nf { color: #a6e22e  !important} /* Name.Function */
+.highlight .nl { color: #f8f8f2  !important} /* Name.Label */
+.highlight .nn { color: #f8f8f2  !important} /* Name.Namespace */
+.highlight .nx { color: #a6e22e  !important} /* Name.Other */
+.highlight .py { color: #f8f8f2  !important} /* Name.Property */
+.highlight .nt { color: #f92672  !important} /* Name.Tag */
+.highlight .nv { color: #f8f8f2  !important} /* Name.Variable */
+.highlight .ow { color: #f92672  !important} /* Operator.Word */
+.highlight .w { color: #f8f8f2  !important} /* Text.Whitespace */
+.highlight .mb { color: #ae81ff  !important} /* Literal.Number.Bin */
+.highlight .mf { color: #ae81ff  !important} /* Literal.Number.Float */
+.highlight .mh { color: #ae81ff  !important} /* Literal.Number.Hex */
+.highlight .mi { color: #ae81ff  !important} /* Literal.Number.Integer */
+.highlight .mo { color: #ae81ff  !important} /* Literal.Number.Oct */
+.highlight .sa { color: #e6db74  !important} /* Literal.String.Affix */
+.highlight .sb { color: #e6db74  !important} /* Literal.String.Backtick */
+.highlight .sc { color: #e6db74  !important} /* Literal.String.Char */
+.highlight .dl { color: #e6db74  !important} /* Literal.String.Delimiter */
+.highlight .sd { color: #e6db74  !important} /* Literal.String.Doc */
+.highlight .s2 { color: #e6db74  !important} /* Literal.String.Double */
+.highlight .se { color: #ae81ff  !important} /* Literal.String.Escape */
+.highlight .sh { color: #e6db74  !important} /* Literal.String.Heredoc */
+.highlight .si { color: #e6db74  !important} /* Literal.String.Interpol */
+.highlight .sx { color: #e6db74  !important} /* Literal.String.Other */
+.highlight .sr { color: #e6db74  !important} /* Literal.String.Regex */
+.highlight .s1 { color: #e6db74  !important} /* Literal.String.Single */
+.highlight .ss { color: #e6db74  !important} /* Literal.String.Symbol */
+.highlight .bp { color: #f8f8f2  !important} /* Name.Builtin.Pseudo */
+.highlight .fm { color: #a6e22e  !important} /* Name.Function.Magic */
+.highlight .vc { color: #f8f8f2  !important} /* Name.Variable.Class */
+.highlight .vg { color: #f8f8f2  !important} /* Name.Variable.Global */
+.highlight .vi { color: #f8f8f2  !important} /* Name.Variable.Instance */
+.highlight .vm { color: #f8f8f2  !important} /* Name.Variable.Magic */
+.highlight .il { color: #ae81ff  !important} /* Literal.Number.Integer.Long */

assets/custom.js

@@ -245,11 +245,11 @@ function showOrHideUserInfo() {
 
 function toggleDarkMode(isEnabled) {
     if (isEnabled) {
-        gradioContainer.classList.add("dark");
-        document.body.style.setProperty("background-color", "var(--neutral-950)", "important");
+        document.body.classList.add("dark");
+        // document.body.style.setProperty("background-color", "var(--neutral-950)", "important");
     } else {
-        gradioContainer.classList.remove("dark");
-        document.body.style.backgroundColor = "";
+        document.body.classList.remove("dark");
+        // document.body.style.backgroundColor = "";
     }
 }
 function adjustDarkMode() {

modules/config.py

@@ -77,8 +77,10 @@ my_api_key = os.environ.get("OPENAI_API_KEY", my_api_key)
 xmchat_api_key = config.get("xmchat_api_key", "")
 os.environ["XMCHAT_API_KEY"] = xmchat_api_key
 
-google_palm_api_key = config.get("google_palm_api_key", "")
-os.environ["GOOGLE_PALM_API_KEY"] = google_palm_api_key
+minimax_api_key = config.get("minimax_api_key", "")
+os.environ["MINIMAX_API_KEY"] = minimax_api_key
+minimax_group_id = config.get("minimax_group_id", "")
+os.environ["MINIMAX_GROUP_ID"] = minimax_group_id
 
 render_latex = config.get("render_latex", True)
 
@@ -102,8 +104,8 @@ auth_list = config.get("users", []) # 实际上是使用者的列表
 authflag = len(auth_list) > 0  # 是否开启认证的状态值，改为判断auth_list长度
 
 # 处理自定义的api_host，优先读环境变量的配置，如果存在则自动装配
-api_host = os.environ.get("api_host", config.get("api_host", ""))
-if api_host:
+api_host = os.environ.get("OPENAI_API_BASE", config.get("openai_api_base", None))
+if api_host is not None:
     shared.state.set_api_host(api_host)
 
 default_chuanhu_assistant_model = config.get("default_chuanhu_assistant_model", "gpt-3.5-turbo")

modules/index_func.py

@@ -83,7 +83,7 @@ def get_documents(file_src):
             logging.error(f"Error loading file: {filename}")
             traceback.print_exc()
 
-        texts = text_splitter.split_documents(texts)
+        texts = text_splitter.split_documents([texts])
         documents.extend(texts)
     logging.debug("Documents loaded.")
     return documents
@@ -118,7 +118,7 @@ def construct_index(
         embeddings = HuggingFaceEmbeddings(model_name = "sentence-transformers/distiluse-base-multilingual-cased-v2")
     else:
         from langchain.embeddings import OpenAIEmbeddings
-        embeddings = OpenAIEmbeddings()
+        embeddings = OpenAIEmbeddings(openai_api_base=os.environ.get("OPENAI_API_BASE", None), openai_api_key=os.environ.get("OPENAI_EMBEDDING_API_KEY", api_key))
     if os.path.exists(index_path):
         logging.info("找到了缓存的索引文件，加载中……")
         return FAISS.load_local(index_path, embeddings)
@@ -136,6 +136,6 @@ def construct_index(
 
         except Exception as e:
             import traceback
-            logging.error("索引构建失败！", e)
+            logging.error("索引构建失败！%s", e)
             traceback.print_exc()
             return None

modules/models/ChuanhuAgent.py

@@ -14,6 +14,7 @@ from langchain.tools import BaseTool, StructuredTool, Tool, tool
 from langchain.callbacks.stdout import StdOutCallbackHandler
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.callbacks.manager import BaseCallbackManager
+from googlesearch import search
 
 from typing import Any, Dict, List, Optional, Union
 
@@ -38,6 +39,9 @@ import os
 import gradio as gr
 import logging
 
+class GoogleSearchInput(BaseModel):
+    keywords: str = Field(description="keywords to search")
+
 class WebBrowsingInput(BaseModel):
     url: str = Field(description="URL of a webpage")
 
@@ -51,8 +55,8 @@ class ChuanhuAgent_Client(BaseLLMModel):
         super().__init__(model_name=model_name, user=user_name)
         self.text_splitter = TokenTextSplitter(chunk_size=500, chunk_overlap=30)
         self.api_key = openai_api_key
-        self.llm = ChatOpenAI(openai_api_key=openai_api_key, temperature=0, model_name=default_chuanhu_assistant_model)
-        self.cheap_llm = ChatOpenAI(openai_api_key=openai_api_key, temperature=0, model_name="gpt-3.5-turbo")
+        self.llm = ChatOpenAI(openai_api_key=openai_api_key, temperature=0, model_name=default_chuanhu_assistant_model, openai_api_base=os.environ.get("OPENAI_API_BASE", None))
+        self.cheap_llm = ChatOpenAI(openai_api_key=openai_api_key, temperature=0, model_name="gpt-3.5-turbo", openai_api_base=os.environ.get("OPENAI_API_BASE", None))
         PROMPT = PromptTemplate(template=SUMMARIZE_PROMPT, input_variables=["text"])
         self.summarize_chain = load_summarize_chain(self.cheap_llm, chain_type="map_reduce", return_intermediate_steps=True, map_prompt=PROMPT, combine_prompt=PROMPT)
         self.index_summary = None
@@ -61,6 +65,14 @@ class ChuanhuAgent_Client(BaseLLMModel):
             self.tools = load_tools(["google-search-results-json", "llm-math", "arxiv", "wikipedia", "wolfram-alpha"], llm=self.llm)
         else:
             self.tools = load_tools(["ddg-search", "llm-math", "arxiv", "wikipedia"], llm=self.llm)
+            self.tools.append(
+                Tool.from_function(
+                    func=self.google_search_simple,
+                    name="Google Search JSON",
+                    description="useful when you need to search the web.",
+                    args_schema=GoogleSearchInput
+                )
+            )
 
         self.tools.append(
             Tool.from_function(
@@ -80,6 +92,10 @@ class ChuanhuAgent_Client(BaseLLMModel):
             )
         )
 
+    def google_search_simple(self, query):
+        results = [{"title": i.title, "link": i.url, "snippet": i.description} for i in search(query, advanced=True)]
+        return str(results)
+
     def handle_file_upload(self, files, chatbot, language):
         """if the model accepts multi modal input, implement this function"""
         status = gr.Markdown.update()
@@ -102,6 +118,7 @@ class ChuanhuAgent_Client(BaseLLMModel):
                 summary = chain({"input_documents": list(index.docstore.__dict__["_dict"].values())}, return_only_outputs=True)["output_text"]
                 logging.info(f"Summary: {summary}")
                 self.index_summary = summary
+                chatbot.append((f"Uploaded {len(files)} files", summary))
             logging.info(cb)
         return gr.Files.update(), chatbot, status
 
@@ -129,6 +146,8 @@ class ChuanhuAgent_Client(BaseLLMModel):
 
     def summary_url(self, url):
         text = self.fetch_url_content(url)
+        if text == "":
+            return "URL unavailable."
         text_summary = self.summary(text)
         url_content = "webpage content summary:\n" + text_summary
 
@@ -136,10 +155,12 @@ class ChuanhuAgent_Client(BaseLLMModel):
 
     def ask_url(self, url, question):
         text = self.fetch_url_content(url)
+        if text == "":
+            return "URL unavailable."
         texts = Document(page_content=text)
         texts = self.text_splitter.split_documents([texts])
         # use embedding
-        embeddings = OpenAIEmbeddings(openai_api_key=self.api_key)
+        embeddings = OpenAIEmbeddings(openai_api_key=self.api_key, openai_api_base=os.environ.get("OPENAI_API_BASE", None))
 
         # create vectorstore
         db = FAISS.from_documents(texts, embeddings)
@@ -170,7 +191,12 @@ class ChuanhuAgent_Client(BaseLLMModel):
                     )
                 )
             agent = initialize_agent(self.tools, self.llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True, callback_manager=manager)
-            reply = agent.run(input=f"{question} Reply in 简体中文")
+            try:
+                reply = agent.run(input=f"{question} Reply in 简体中文")
+            except Exception as e:
+                import traceback
+                traceback.print_exc()
+                reply = str(e)
             it.callback(reply)
             it.finish()
         t = Thread(target=thread_func)

modules/models/base_model.py

@@ -13,7 +13,7 @@ import pathlib
 
 from tqdm import tqdm
 import colorama
-from duckduckgo_search import ddg
+from googlesearch import search
 import asyncio
 import aiohttp
 from enum import Enum
@@ -62,6 +62,19 @@ class CallbackToIterator:
             self.finished = True
             self.cond.notify()  # Wake up the generator if it's waiting.
 
+def get_action_description(text):
+    match = re.search('```(.*?)```', text, re.S)
+    json_text = match.group(1)
+    # 把json转化为python字典
+    json_dict = json.loads(json_text)
+    # 提取'action'和'action_input'的值
+    action_name = json_dict['action']
+    action_input = json_dict['action_input']
+    if action_name != "Final Answer":
+        return f'<p style="font-size: smaller; color: gray;">{action_name}: {action_input}</p>'
+    else:
+        return ""
+
 class ChuanhuCallbackHandler(BaseCallbackHandler):
 
     def __init__(self, callback) -> None:
@@ -71,7 +84,7 @@ class ChuanhuCallbackHandler(BaseCallbackHandler):
     def on_agent_action(
         self, action: AgentAction, color: Optional[str] = None, **kwargs: Any
     ) -> Any:
-        self.callback(action.log)
+        self.callback(get_action_description(action.log))
 
     def on_tool_end(
         self,
@@ -82,16 +95,22 @@ class ChuanhuCallbackHandler(BaseCallbackHandler):
         **kwargs: Any,
     ) -> None:
         """If not the final action, print out observation."""
+        # if observation_prefix is not None:
+        #     self.callback(f"\n\n{observation_prefix}")
+        # self.callback(output)
+        # if llm_prefix is not None:
+        #     self.callback(f"\n\n{llm_prefix}")
         if observation_prefix is not None:
-            self.callback(f"\n\n{observation_prefix}")
+            logging.info(observation_prefix)
         self.callback(output)
         if llm_prefix is not None:
-            self.callback(f"\n\n{llm_prefix}")
+            logging.info(llm_prefix)
 
     def on_agent_finish(
         self, finish: AgentFinish, color: Optional[str] = None, **kwargs: Any
     ) -> None:
-        self.callback(f"{finish.log}\n\n")
+        # self.callback(f"{finish.log}\n\n")
+        logging.info(finish.log)
 
     def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
         """Run on new LLM token. Only available when streaming is enabled."""
@@ -107,8 +126,8 @@ class ModelType(Enum):
     StableLM = 4
     MOSS = 5
     YuanAI = 6
-    ChuanhuAgent = 7
-    PaLM = 8
+    Minimax = 7
+    ChuanhuAgent = 8
 
     @classmethod
     def get_type(cls, model_name: str):
@@ -128,10 +147,10 @@ class ModelType(Enum):
             model_type = ModelType.MOSS
         elif "yuanai" in model_name_lower:
             model_type = ModelType.YuanAI
+        elif "minimax" in model_name_lower:
+            model_type = ModelType.Minimax
         elif "川虎助理" in model_name_lower:
             model_type = ModelType.ChuanhuAgent
-        elif "palm" in model_name_lower:
-            model_type = ModelType.PaLM
         else:
             model_type = ModelType.Unknown
         return model_type
@@ -225,6 +244,8 @@ class BaseLLMModel:
 
         stream_iter = self.get_answer_stream_iter()
 
+        if display_append:
+            display_append = "<hr>" +display_append
         for partial_text in stream_iter:
             chatbot[-1] = (chatbot[-1][0], partial_text + display_append)
             self.all_token_counts[-1] += 1
@@ -265,6 +286,26 @@ class BaseLLMModel:
             status = i18n("索引构建完成")
         return gr.Files.update(), chatbot, status
 
+    def summarize_index(self, files, chatbot, language):
+        status = gr.Markdown.update()
+        if files:
+            index = construct_index(self.api_key, file_src=files)
+            status = i18n("总结完成")
+            logging.info(i18n("生成内容总结中……"))
+            os.environ["OPENAI_API_KEY"] = self.api_key
+            from langchain.chains.summarize import load_summarize_chain
+            from langchain.prompts import PromptTemplate
+            from langchain.chat_models import ChatOpenAI
+            from langchain.callbacks import StdOutCallbackHandler
+            prompt_template = "Write a concise summary of the following:\n\n{text}\n\nCONCISE SUMMARY IN " + language + ":"
+            PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
+            llm = ChatOpenAI()
+            chain = load_summarize_chain(llm, chain_type="map_reduce", return_intermediate_steps=True, map_prompt=PROMPT, combine_prompt=PROMPT)
+            summary = chain({"input_documents": list(index.docstore.__dict__["_dict"].values())}, return_only_outputs=True)["output_text"]
+            print(i18n("总结") + f": {summary}")
+            chatbot.append([i18n("上传了")+str(len(files))+"个文件", summary])
+        return chatbot, status
+
     def prepare_inputs(self, real_inputs, use_websearch, files, reply_language, chatbot):
         fake_inputs = None
         display_append = []
@@ -295,15 +336,15 @@ class BaseLLMModel:
             )
         elif use_websearch:
             limited_context = True
-            search_results = ddg(real_inputs, max_results=5)
+            search_results = [i for i in search(real_inputs, advanced=True)]
             reference_results = []
             for idx, result in enumerate(search_results):
                 logging.debug(f"搜索结果{idx + 1}：{result}")
-                domain_name = urllib3.util.parse_url(result["href"]).host
-                reference_results.append([result["body"], result["href"]])
+                domain_name = urllib3.util.parse_url(result.url).host
+                reference_results.append([result.description, result.url])
                 display_append.append(
                     # f"{idx+1}. [{domain_name}]({result['href']})\n"
-                    f"<li><a href=\"{result['href']}\" target=\"_blank\">{domain_name}</a></li>\n"
+                    f"<li><a href=\"{result.url}\" target=\"_blank\">{domain_name}</a></li>\n"
                 )
             reference_results = add_source_numbers(reference_results)
             display_append = "<ol>\n\n" + "".join(display_append) + "</ol>"

modules/models/minimax.py

@@ -0,0 +1,161 @@
+import json
+import os
+
+import colorama
+import requests
+import logging
+
+from modules.models.base_model import BaseLLMModel
+from modules.presets import STANDARD_ERROR_MSG, GENERAL_ERROR_MSG, TIMEOUT_STREAMING, TIMEOUT_ALL, i18n
+
+group_id = os.environ.get("MINIMAX_GROUP_ID", "")
+
+
+class MiniMax_Client(BaseLLMModel):
+    """
+    MiniMax Client
+    接口文档见 https://api.minimax.chat/document/guides/chat
+    """
+
+    def __init__(self, model_name, api_key, user_name="", system_prompt=None):
+        super().__init__(model_name=model_name, user=user_name)
+        self.url = f'https://api.minimax.chat/v1/text/chatcompletion?GroupId={group_id}'
+        self.history = []
+        self.api_key = api_key
+        self.system_prompt = system_prompt
+        self.headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json"
+        }
+
+    def get_answer_at_once(self):
+        # minimax temperature is (0,1] and base model temperature is [0,2], and yuan 0.9 == base 1 so need to convert
+        temperature = self.temperature * 0.9 if self.temperature <= 1 else 0.9 + (self.temperature - 1) / 10
+
+        request_body = {
+            "model": self.model_name.replace('minimax-', ''),
+            "temperature": temperature,
+            "skip_info_mask": True,
+            'messages': [{"sender_type": "USER", "text": self.history[-1]['content']}]
+        }
+        if self.n_choices:
+            request_body['beam_width'] = self.n_choices
+        if self.system_prompt:
+            request_body['prompt'] = self.system_prompt
+        if self.max_generation_token:
+            request_body['tokens_to_generate'] = self.max_generation_token
+        if self.top_p:
+            request_body['top_p'] = self.top_p
+
+        response = requests.post(self.url, headers=self.headers, json=request_body)
+
+        res = response.json()
+        answer = res['reply']
+        total_token_count = res["usage"]["total_tokens"]
+        return answer, total_token_count
+
+    def get_answer_stream_iter(self):
+        response = self._get_response(stream=True)
+        if response is not None:
+            iter = self._decode_chat_response(response)
+            partial_text = ""
+            for i in iter:
+                partial_text += i
+                yield partial_text
+        else:
+            yield STANDARD_ERROR_MSG + GENERAL_ERROR_MSG
+
+    def _get_response(self, stream=False):
+        minimax_api_key = self.api_key
+        history = self.history
+        logging.debug(colorama.Fore.YELLOW +
+                      f"{history}" + colorama.Fore.RESET)
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {minimax_api_key}",
+        }
+
+        temperature = self.temperature * 0.9 if self.temperature <= 1 else 0.9 + (self.temperature - 1) / 10
+
+        messages = []
+        for msg in self.history:
+            if msg['role'] == 'user':
+                messages.append({"sender_type": "USER", "text": msg['content']})
+            else:
+                messages.append({"sender_type": "BOT", "text": msg['content']})
+
+        request_body = {
+            "model": self.model_name.replace('minimax-', ''),
+            "temperature": temperature,
+            "skip_info_mask": True,
+            'messages': messages
+        }
+        if self.n_choices:
+            request_body['beam_width'] = self.n_choices
+        if self.system_prompt:
+            lines = self.system_prompt.splitlines()
+            if lines[0].find(":") != -1 and len(lines[0]) < 20:
+                request_body["role_meta"] = {
+                    "user_name": lines[0].split(":")[0],
+                    "bot_name": lines[0].split(":")[1]
+                }
+                lines.pop()
+            request_body["prompt"] = "\n".join(lines)
+        if self.max_generation_token:
+            request_body['tokens_to_generate'] = self.max_generation_token
+        else:
+            request_body['tokens_to_generate'] = 512
+        if self.top_p:
+            request_body['top_p'] = self.top_p
+
+        if stream:
+            timeout = TIMEOUT_STREAMING
+            request_body['stream'] = True
+            request_body['use_standard_sse'] = True
+        else:
+            timeout = TIMEOUT_ALL
+        try:
+            response = requests.post(
+                self.url,
+                headers=headers,
+                json=request_body,
+                stream=stream,
+                timeout=timeout,
+            )
+        except:
+            return None
+
+        return response
+
+    def _decode_chat_response(self, response):
+        error_msg = ""
+        for chunk in response.iter_lines():
+            if chunk:
+                chunk = chunk.decode()
+                chunk_length = len(chunk)
+                print(chunk)
+                try:
+                    chunk = json.loads(chunk[6:])
+                except json.JSONDecodeError:
+                    print(i18n("JSON解析错误,��到的内容: ") + f"{chunk}")
+                    error_msg += chunk
+                    continue
+                if chunk_length > 6 and "delta" in chunk["choices"][0]:
+                    if "finish_reason" in chunk["choices"][0] and chunk["choices"][0]["finish_reason"] == "stop":
+                        self.all_token_counts.append(chunk["usage"]["total_tokens"] - sum(self.all_token_counts))
+                        break
+                    try:
+                        yield chunk["choices"][0]["delta"]
+                    except Exception as e:
+                        logging.error(f"Error: {e}")
+                        continue
+        if error_msg:
+            try:
+                error_msg = json.loads(error_msg)
+                if 'base_resp' in error_msg:
+                    status_code = error_msg['base_resp']['status_code']
+                    status_msg = error_msg['base_resp']['status_msg']
+                    raise Exception(f"{status_code} - {status_msg}")
+            except json.JSONDecodeError:
+                pass
+            raise Exception(error_msg)

modules/models/models.py

@@ -15,7 +15,6 @@ from PIL import Image
 
 from tqdm import tqdm
 import colorama
-from duckduckgo_search import ddg
 import asyncio
 import aiohttp
 from enum import Enum
@@ -603,12 +602,14 @@ def get_model(
         elif model_type == ModelType.YuanAI:
             from .inspurai import Yuan_Client
             model = Yuan_Client(model_name, api_key=access_key, user_name=user_name, system_prompt=system_prompt)
+        elif model_type == ModelType.Minimax:
+            from .minimax import MiniMax_Client
+            if os.environ.get("MINIMAX_API_KEY") != "":
+                access_key = os.environ.get("MINIMAX_API_KEY")
+            model = MiniMax_Client(model_name, api_key=access_key, user_name=user_name, system_prompt=system_prompt)
         elif model_type == ModelType.ChuanhuAgent:
             from .ChuanhuAgent import ChuanhuAgent_Client
             model = ChuanhuAgent_Client(model_name, access_key, user_name=user_name)
-        elif model_type == ModelType.PaLM:
-            from .PaLM import PaLM_Client
-            model = PaLM_Client(model_name, user_name=user_name)
         elif model_type == ModelType.Unknown:
             raise ValueError(f"未知模型: {model_name}")
         logging.info(msg)

modules/presets.py

@@ -59,20 +59,21 @@ APPEARANCE_SWITCHER = """
 """
 
 ONLINE_MODELS = [
-    "川虎助理",
-    "川虎助理 Pro",
     "gpt-3.5-turbo",
     "gpt-3.5-turbo-0301",
     "gpt-4",
     "gpt-4-0314",
     "gpt-4-32k",
     "gpt-4-32k-0314",
+    "川虎助理",
+    "川虎助理 Pro",
     "xmchat",
-    "Google PaLM",
     "yuanai-1.0-base_10B",
     "yuanai-1.0-translate",
     "yuanai-1.0-dialog",
     "yuanai-1.0-rhythm_poems",
+    "minimax-abab4-chat",
+    "minimax-abab5-chat",
 ]
 
 LOCAL_MODELS = [

modules/shared.py

@@ -1,6 +1,7 @@
 from modules.presets import COMPLETION_URL, BALANCE_API_URL, USAGE_API_URL, API_HOST
 import os
 import queue
+import openai
 
 class State:
     interrupted = False
@@ -15,23 +16,28 @@ class State:
     def recover(self):
         self.interrupted = False
 
-    def set_api_host(self, api_host):
-        self.completion_url = f"https://{api_host}/v1/chat/completions"
-        self.balance_api_url = f"https://{api_host}/dashboard/billing/credit_grants"
-        self.usage_api_url = f"https://{api_host}/dashboard/billing/usage"
-        os.environ["OPENAI_API_BASE"] = f"https://{api_host}/v1"
+    def set_api_host(self, api_host: str):
+        api_host = api_host.rstrip("/")
+        if not api_host.startswith("http"):
+            api_host = f"https://{api_host}"
+        if api_host.endswith("/v1"):
+            api_host = api_host[:-3]
+        self.completion_url = f"{api_host}/v1/chat/completions"
+        self.balance_api_url = f"{api_host}/dashboard/billing/credit_grants"
+        self.usage_api_url = f"{api_host}/dashboard/billing/usage"
+        os.environ["OPENAI_API_BASE"] = api_host
 
     def reset_api_host(self):
         self.completion_url = COMPLETION_URL
         self.balance_api_url = BALANCE_API_URL
         self.usage_api_url = USAGE_API_URL
-        os.environ["OPENAI_API_BASE"] = f"https://{API_HOST}/v1"
+        os.environ["OPENAI_API_BASE"] = f"https://{API_HOST}"
         return API_HOST
 
     def reset_all(self):
         self.interrupted = False
         self.completion_url = COMPLETION_URL
-    
+
     def set_api_key_queue(self, api_key_list):
         self.multi_api_key = True
         self.api_key_queue = queue.Queue()
@@ -50,6 +56,6 @@ class State:
             return ret
 
         return wrapped
-        
+
 
 state = State()

modules/utils.py

@@ -116,6 +116,9 @@ def set_single_turn(current_model, *args):
 def handle_file_upload(current_model, *args):
     return current_model.handle_file_upload(*args)
 
+def handle_summarize_index(current_model, *args):
+    return current_model.summarize_index(*args)
+
 def like(current_model, *args):
     return current_model.like(*args)
 

requirements.txt

@@ -1,14 +1,14 @@
-gradio==3.28.0
-gradio_client==0.1.4
+gradio==3.30.0
+gradio_client==0.2.4
 mdtex2html
 pypinyin
 tiktoken
 socksio
 tqdm
 colorama
-duckduckgo_search==2.9.5
+googlesearch-python
 Pygments
-langchain==0.0.170
+langchain==0.0.173
 markdown
 PyPDF2
 pdfplumber
@@ -24,4 +24,3 @@ wikipedia
 google.generativeai
 openai
 unstructured
-google-api-python-client