修正一些细节

config.py

@@ -45,7 +45,7 @@ MAX_RETRY = 2
 
 # OpenAI模型选择是（gpt4现在只对申请成功的人开放）
 LLM_MODEL = "gpt-3.5-turbo" # 可选 "chatglm"
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "chatglm", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"

main.py

@@ -95,13 +95,13 @@ def main():
                     with gr.Row():
                         with gr.Accordion("点击展开“文件上传区”。上传本地文件可供红色函数插件调用。", open=False) as area_file_up:
                             file_upload = gr.Files(label="任何文件, 但推荐上传压缩文件(zip, tar)", file_count="multiple")
-                with gr.Accordion("展开SysPrompt & 交互界面布局 & Github地址", open=(LAYOUT == "TOP-DOWN")):
+                with gr.Accordion("更换模型 & SysPrompt & 交互界面布局", open=(LAYOUT == "TOP-DOWN")):
                     system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
                     top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
                     temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
                     max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="MaxLength",)
                     checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
-                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="").style(container=False)
+                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
 
                     gr.Markdown(description)
                 with gr.Accordion("备选输入区", open=True, visible=False) as area_input_secondary:

request_llm/bridge_chatgpt.py

@@ -175,15 +175,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             
             if chunk:
                 try:
-                    if len(json.loads(chunk.decode()[6:])['choices'][0]["delta"]) == 0:
+                    chunk_decoded = chunk.decode()
+                    # 前者API2D的
+                    if ('data: [DONE]' in chunk_decoded) or (len(json.loads(chunk_decoded[6:])['choices'][0]["delta"]) == 0):
                         # 判定为数据流的结束，gpt_replying_buffer也写完了
                         logging.info(f'[response] {gpt_replying_buffer}')
                         break
                     # 处理数据流的主体
-                    chunkjson = json.loads(chunk.decode()[6:])
+                    chunkjson = json.loads(chunk_decoded[6:])
                     status_text = f"finish_reason: {chunkjson['choices'][0]['finish_reason']}"
                     # 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
-                    gpt_replying_buffer = gpt_replying_buffer + json.loads(chunk.decode()[6:])['choices'][0]["delta"]["content"]
+                    gpt_replying_buffer = gpt_replying_buffer + json.loads(chunk_decoded[6:])['choices'][0]["delta"]["content"]
                     history[-1] = gpt_replying_buffer
                     chatbot[-1] = (history[-2], history[-1])
                     yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
@@ -192,7 +194,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     traceback.print_exc()
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
                     chunk = get_full_error(chunk, stream_response)
-                    error_msg = chunk.decode()
+                    error_msg = chunk_decoded
                     if "reduce the length" in error_msg:
                         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长，或历史数据过长. 历史缓存数据现已释放，您可以请再次尝试.")
                         history = []    # 清除历史
@@ -205,7 +207,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     else:
                         from toolbox import regular_txt_to_markdown
                         tb_str = '```\n' + traceback.format_exc() + '```'
-                        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk.decode()[4:])}")
+                        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded[4:])}")
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
                     return
 

version

@@ -1,5 +1,5 @@
 {
   "version": 3.1,
   "show_feature": true,
-  "new_feature": "添加支持清华ChatGLM和GPT-4 <-> 添加支持API2D（国内不需要代理） <-> 改进架构，支持与多个LLM模型同时对话  <-> 支持多API-KEY负载均衡（并列填写，逗号分割） <-> 添加输入区文本清除按键"
+  "new_feature": "添加支持清华ChatGLM和GPT-4 <-> 改进架构，支持与多个LLM模型同时对话 <-> 添加支持API2D（国内，可支持gpt4）<-> 支持多API-KEY负载均衡（并列填写，逗号分割） <-> 添加输入区文本清除按键"
 }