update

request_llms/bridge_all.py

@@ -11,7 +11,7 @@
 import tiktoken, copy
 from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
-from toolbox import get_conf, trimmed_format_exc
+from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
 
 from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
 from .bridge_chatgpt import predict as chatgpt_ui
@@ -31,6 +31,9 @@ from .bridge_qianfan import predict as qianfan_ui
 from .bridge_google_gemini import predict as genai_ui
 from .bridge_google_gemini import predict_no_ui_long_connection  as genai_noui
 
+from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
+from .bridge_zhipu import predict as zhipu_ui
+
 colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
 
 class LazyloadTiktoken(object):
@@ -44,13 +47,13 @@ class LazyloadTiktoken(object):
         tmp = tiktoken.encoding_for_model(model)
         print('加载tokenizer完毕')
         return tmp
-    
+
     def encode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.encode(*args, **kwargs)
-    
+
     def decode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.decode(*args, **kwargs)
 
 # Endpoint 重定向
@@ -63,7 +66,7 @@ azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/compl
 # 兼容旧版的配置
 try:
     API_URL = get_conf("API_URL")
-    if API_URL != "https://api.openai.com/v1/chat/completions": 
+    if API_URL != "https://api.openai.com/v1/chat/completions":
         openai_endpoint = API_URL
         print("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置")
 except:
@@ -95,7 +98,7 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-    
+
     "gpt-3.5-turbo-16k": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -150,6 +153,15 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4-turbo-preview": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
     "gpt-4-1106-preview": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -159,6 +171,15 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4-0125-preview": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
     "gpt-3.5-random": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -167,7 +188,7 @@ model_info = {
         "tokenizer": tokenizer_gpt4,
         "token_cnt": get_token_num_gpt4,
     },
-    
+
     "gpt-4-vision-preview": {
         "fn_with_ui": chatgpt_vision_ui,
         "fn_without_ui": chatgpt_vision_noui,
@@ -197,16 +218,25 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
-    "api2d-gpt-3.5-turbo": {
-        "fn_with_ui": chatgpt_ui,
-        "fn_without_ui": chatgpt_noui,
-        "endpoint": api2d_endpoint,
-        "max_token": 4096,
+    # 智谱AI
+    "glm-4": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "glm-3-turbo": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 4,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
 
+    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
     "api2d-gpt-4": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -530,7 +560,7 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
         })
     except:
         print(trimmed_format_exc())
-if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
         from .bridge_spark import predict as spark_ui
@@ -542,6 +572,14 @@ if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
+            },
+            "sparkv3.5": {
+                "fn_with_ui": spark_ui,
+                "fn_without_ui": spark_noui,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
             }
         })
     except:
@@ -562,19 +600,17 @@ if "llama2" in AVAIL_LLM_MODELS:   # llama2
         })
     except:
         print(trimmed_format_exc())
-if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai
+if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容配置
     try:
-        from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
-        from .bridge_zhipu import predict as zhipu_ui
         model_info.update({
             "zhipuai": {
                 "fn_with_ui": zhipu_ui,
                 "fn_without_ui": zhipu_noui,
                 "endpoint": None,
-                "max_token": 4096,
+                "max_token": 10124 * 8,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
-            }
+            },
         })
     except:
         print(trimmed_format_exc())
@@ -617,7 +653,7 @@ AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
 if len(AZURE_CFG_ARRAY) > 0:
     for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
         # 可能会覆盖之前的配置，但这是意料之中的
-        if not azure_model_name.startswith('azure'): 
+        if not azure_model_name.startswith('azure'):
             raise ValueError("AZURE_CFG_ARRAY中配置的模型必须以azure开头")
         endpoint_ = azure_cfg_dict["AZURE_ENDPOINT"] + \
             f'openai/deployments/{azure_cfg_dict["AZURE_ENGINE"]}/chat/completions?api-version=2023-05-15'
@@ -668,6 +704,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
     """
     import threading, time, copy
 
+    inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
     model = llm_kwargs['llm_model']
     n_model = 1
     if '&' not in model:
@@ -682,7 +719,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
         executor = ThreadPoolExecutor(max_workers=4)
         models = model.split('&')
         n_model = len(models)
-        
+
         window_len = len(observe_window)
         assert window_len==3
         window_mutex = [["", time.time(), ""] for _ in range(n_model)] + [True]
@@ -701,7 +738,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
                 time.sleep(0.25)
                 if not window_mutex[-1]: break
                 # 看门狗（watchdog）
-                for i in range(n_model): 
+                for i in range(n_model):
                     window_mutex[i][1] = observe_window[1]
                 # 观察窗（window）
                 chat_string = []
@@ -741,6 +778,7 @@ def predict(inputs, llm_kwargs, *args, **kwargs):
     additional_fn代表点击的哪个按钮，按钮见functional.py
     """
 
+    inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
     method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]  # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
     yield from method(inputs, llm_kwargs, *args, **kwargs)
 

request_llms/bridge_chatgpt.py

@@ -113,6 +113,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
             error_msg = get_full_error(chunk, stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
+            elif """type":"upstream_error","param":"307""" in error_msg:
+                raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
             else:
                 raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
         if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成

request_llms/bridge_google_gemini.py

@@ -57,6 +57,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     if "vision" in llm_kwargs["llm_model"]:
         have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
+        if not have_recent_file:
+            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
+            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
+            return
         def make_media_input(inputs, image_paths): 
             for image_path in image_paths:
                 inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'

request_llms/bridge_qianfan.py

@@ -146,21 +146,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     yield from update_ui(chatbot=chatbot, history=history)
     # 开始接收回复
     try:
+        response = f"[Local Message] 等待{model_name}响应中 ..."
         for response in generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
             chatbot[-1] = (inputs, response)
             yield from update_ui(chatbot=chatbot, history=history)
+        history.extend([inputs, response])
+        yield from update_ui(chatbot=chatbot, history=history)
     except ConnectionAbortedError as e:
         from .bridge_all import model_info
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
                     max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
         yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
         return
-    
-    # 总结输出
-    response = f"[Local Message] {model_name}响应异常 ..."
-    if response == f"[Local Message] 等待{model_name}响应中 ...":
-        response = f"[Local Message] {model_name}响应异常 ..."
-    history.extend([inputs, response])
-    yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_qwen.py

@@ -51,6 +51,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     # 开始接收回复
     from .com_qwenapi import QwenRequestInstance
     sri = QwenRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_skylark2.py

@@ -56,6 +56,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     # 开始接收回复
     from .com_skylark2api import YUNQUERequestInstance
     sri = YUNQUERequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_spark.py

@@ -9,7 +9,7 @@ model_name = '星火认知大模型'
 
 def validate_key():
     XFYUN_APPID = get_conf('XFYUN_APPID')
-    if XFYUN_APPID == '00000000' or XFYUN_APPID == '': 
+    if XFYUN_APPID == '00000000' or XFYUN_APPID == '':
         return False
     return True
 
@@ -49,9 +49,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
-    # 开始接收回复    
+    # 开始接收回复
     from .com_sparkapi import SparkRequestInstance
     sri = SparkRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt, use_image_api=True):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_zhipu.py

@@ -1,15 +1,21 @@
-
 import time
+import os
 from toolbox import update_ui, get_conf, update_ui_lastest_msg
-from toolbox import check_packages, report_exception
+from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
 
 model_name = '智谱AI大模型'
+zhipuai_default_model = 'glm-4'
 
 def validate_key():
     ZHIPUAI_API_KEY = get_conf("ZHIPUAI_API_KEY")
     if ZHIPUAI_API_KEY == '': return False
     return True
 
+def make_media_input(inputs, image_paths):
+    for image_path in image_paths:
+        inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
+    return inputs
+
 def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
     """
         ⭐多线程方法
@@ -18,34 +24,40 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     watch_dog_patience = 5
     response = ""
 
+    if llm_kwargs["llm_model"] == "zhipuai":
+        llm_kwargs["llm_model"] = zhipuai_default_model
+
     if validate_key() is False:
         raise RuntimeError('请配置ZHIPUAI_API_KEY')
 
-    from .com_zhipuapi import ZhipuRequestInstance
-    sri = ZhipuRequestInstance()
-    for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
+    # 开始接收回复
+    from .com_zhipuglm import ZhipuChatInit
+    zhipu_bro_init = ZhipuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
         if len(observe_window) >= 1:
             observe_window[0] = response
         if len(observe_window) >= 2:
-            if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
+            if (time.time() - observe_window[1]) > watch_dog_patience:
+                raise RuntimeError("程序终止。")
     return response
 
-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
     """
         ⭐单线程方法
         函数的说明请见 request_llms/bridge_all.py
     """
-    chatbot.append((inputs, ""))
+    chatbot.append([inputs, ""])
     yield from update_ui(chatbot=chatbot, history=history)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         check_packages(["zhipuai"])
     except:
-        yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install zhipuai==1.0.7```。",
-                                         chatbot=chatbot, history=history, delay=0)
+        yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
+            chatbot=chatbot, history=history, delay=0)
         return
-    
+
     if validate_key() is False:
         yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
         return
@@ -53,16 +65,29 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     if additional_fn is not None:
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
-
-    # 开始接收回复    
-    from .com_zhipuapi import ZhipuRequestInstance
-    sri = ZhipuRequestInstance()
-    for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
-        chatbot[-1] = (inputs, response)
+        chatbot[-1] = [inputs, ""]
         yield from update_ui(chatbot=chatbot, history=history)
 
-    # 总结输出
-    if response == f"[Local Message] 等待{model_name}响应中 ...":
-        response = f"[Local Message] {model_name}响应异常 ..."
+    if llm_kwargs["llm_model"] == "zhipuai":
+        llm_kwargs["llm_model"] = zhipuai_default_model
+
+    if llm_kwargs["llm_model"] in ["glm-4v"]:
+        have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
+        if not have_recent_file:
+            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
+            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
+            return
+        if have_recent_file:
+            inputs = make_media_input(inputs, image_paths)
+            chatbot[-1] = [inputs, ""]
+            yield from update_ui(chatbot=chatbot, history=history)
+
+
+    # 开始接收回复
+    from .com_zhipuglm import ZhipuChatInit
+    zhipu_bro_init = ZhipuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
+        chatbot[-1] = [inputs, response]
+        yield from update_ui(chatbot=chatbot, history=history)
     history.extend([inputs, response])
     yield from update_ui(chatbot=chatbot, history=history)

request_llms/com_google.py

@@ -7,7 +7,7 @@ import os
 import re
 import requests
 from typing import List, Dict, Tuple
-from toolbox import get_conf, encode_image, get_pictures_list
+from toolbox import get_conf, encode_image, get_pictures_list, to_markdown_tabs
 
 proxies, TIMEOUT_SECONDS = get_conf("proxies", "TIMEOUT_SECONDS")
 
@@ -112,34 +112,6 @@ def html_local_img(__file, layout="left", max_width=None, max_height=None, md=Tr
     return a
 
 
-def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
-    """
-    Args:
-        head: 表头：[]
-        tabs: 表值：[[列1], [列2], [列3], [列4]]
-        alignment: :--- 左对齐， :---: 居中对齐， ---: 右对齐
-        column: True to keep data in columns, False to keep data in rows (default).
-    Returns:
-        A string representation of the markdown table.
-    """
-    if column:
-        transposed_tabs = list(map(list, zip(*tabs)))
-    else:
-        transposed_tabs = tabs
-    # Find the maximum length among the columns
-    max_len = max(len(column) for column in transposed_tabs)
-
-    tab_format = "| %s "
-    tabs_list = "".join([tab_format % i for i in head]) + "|\n"
-    tabs_list += "".join([tab_format % alignment for i in head]) + "|\n"
-
-    for i in range(max_len):
-        row_data = [tab[i] if i < len(tab) else "" for tab in transposed_tabs]
-        row_data = file_manifest_filter_html(row_data, filter_=None)
-        tabs_list += "".join([tab_format % i for i in row_data]) + "|\n"
-
-    return tabs_list
-
 
 class GoogleChatInit:
     def __init__(self):

request_llms/com_sparkapi.py

@@ -65,6 +65,7 @@ class SparkRequestInstance():
         self.gpt_url = "ws://spark-api.xf-yun.com/v1.1/chat"
         self.gpt_url_v2 = "ws://spark-api.xf-yun.com/v2.1/chat"
         self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
+        self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
         self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
 
         self.time_to_yield_event = threading.Event()
@@ -91,6 +92,8 @@ class SparkRequestInstance():
             gpt_url = self.gpt_url_v2
         elif llm_kwargs['llm_model'] == 'sparkv3':
             gpt_url = self.gpt_url_v3
+        elif llm_kwargs['llm_model'] == 'sparkv3.5':
+            gpt_url = self.gpt_url_v35
         else:
             gpt_url = self.gpt_url
         file_manifest = []
@@ -190,6 +193,7 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
         "spark": "general",
         "sparkv2": "generalv2",
         "sparkv3": "generalv3",
+        "sparkv3.5": "generalv3.5",
     }
     domains_select = domains[llm_kwargs['llm_model']]
     if file_manifest: domains_select = 'image'

request_llms/com_zhipuglm.py

@@ -0,0 +1,84 @@
+# encoding: utf-8
+# @Time   : 2024/1/22
+# @Author : Kilig947 & binary husky
+# @Descr   : 兼容最新的智谱Ai
+from toolbox import get_conf
+from zhipuai import ZhipuAI
+from toolbox import get_conf, encode_image, get_pictures_list
+import logging, os
+
+
+def input_encode_handler(inputs, llm_kwargs):        
+    if llm_kwargs["most_recent_uploaded"].get("path"):
+        image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
+    md_encode = []
+    for md_path in image_paths:
+        type_ = os.path.splitext(md_path)[1].replace(".", "")
+        type_ = "jpeg" if type_ == "jpg" else type_
+        md_encode.append({"data": encode_image(md_path), "type": type_})
+    return inputs, md_encode
+
+
+class ZhipuChatInit:
+
+    def __init__(self):
+        ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
+        if len(ZHIPUAI_MODEL) > 0:
+            logging.error('ZHIPUAI_MODEL 配置项选项已经弃用，请在LLM_MODEL中配置')
+        self.zhipu_bro = ZhipuAI(api_key=ZHIPUAI_API_KEY)
+        self.model = ''
+
+    def __conversation_user(self, user_input: str, llm_kwargs):
+        if self.model not in ["glm-4v"]:
+            return {"role": "user", "content": user_input}
+        else:
+            input_, encode_img = input_encode_handler(user_input, llm_kwargs=llm_kwargs)
+            what_i_have_asked = {"role": "user", "content": []}
+            what_i_have_asked['content'].append({"type": 'text', "text": user_input})
+            if encode_img:
+                img_d = {"type": "image_url",
+                         "image_url": {'url': encode_img}}
+                what_i_have_asked['content'].append(img_d)
+            return what_i_have_asked
+
+    def __conversation_history(self, history, llm_kwargs):
+        messages = []
+        conversation_cnt = len(history) // 2
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
+                what_gpt_answer = {
+                    "role": "assistant",
+                    "content": history[index + 1]
+                }
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+        return messages
+
+    def __conversation_message_payload(self, inputs, llm_kwargs, history, system_prompt):
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        self.model = llm_kwargs['llm_model']
+        messages.extend(self.__conversation_history(history, llm_kwargs))  # 处理 history
+        messages.append(self.__conversation_user(inputs, llm_kwargs))  # 处理用户对话
+        response = self.zhipu_bro.chat.completions.create(
+            model=self.model, messages=messages, stream=True,
+            temperature=llm_kwargs.get('temperature', 0.95) * 0.95,  # 只能传默认的 temperature 和 top_p
+            top_p=llm_kwargs.get('top_p', 0.7) * 0.7,
+            max_tokens=llm_kwargs.get('max_tokens', 1024 * 4),  # 最大输出模型的一半
+        )
+        return response
+
+    def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
+        self.model = llm_kwargs['llm_model']
+        response = self.__conversation_message_payload(inputs, llm_kwargs, history, system_prompt)
+        bro_results = ''
+        for chunk in response:
+            bro_results += chunk.choices[0].delta.content
+            yield chunk.choices[0].delta.content, bro_results
+
+
+if __name__ == '__main__':
+    zhipu = ZhipuChatInit()
+    zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')