version 3.75 (#1702)

* Update version to 3.74 * Add support for Yi Model API (#1635) * 更新以支持零一万物模型 * 删除newbing * 修改config --------- Co-authored-by: binary-husky <[email protected]> * Refactor function signatures in bridge files * fix qwen api change * rename and ref functions * rename and move some cookie functions * 增加haiku模型，新增endpoint配置说明 (#1626) * haiku added * 新增haiku，新增endpoint配置说明 * Haiku added * 将说明同步至最新Endpoint --------- Co-authored-by: binary-husky <[email protected]> * private_upload目录下进行文件鉴权 (#1596) * private_upload目录下进行文件鉴权 * minor fastapi adjustment * Add logging functionality to enable saving conversation records * waiting to fix username retrieve * support 2rd web path * allow accessing default user dir --------- Co-authored-by: binary-husky <[email protected]> * remove yaml deps * fix favicon * fix abs path auth problem * forget to write a return * add `dashscope` to deps * fix GHSA-v9q9-xj86-953p * 用户名重叠越权访问patch (#1681) * add cohere model api access * cohere + can_multi_thread * fix block user access(fail) * fix fastapi bug * change cohere api endpoint * explain version * # fix com_zhipuglm.py illegal temperature problem (#1687) * Update com_zhipuglm.py # fix 用户在使用 zhipuai 界面时遇到了关于温度参数的非法参数错误 * allow store lm model dropdown * add a btn to reverse previous reset * remove extra fns * Add support for glm-4v model (#1700) * 修改chatglm3量化加载方式 (#1688) Co-authored-by: zym9804 <[email protected]> * save chat stage 1 * consider null cookie situation * 在点击复制按钮时激活语音 * miss some parts * move all to js * done first stage * add edge tts * bug fix * bug fix * remove console log * bug fix * bug fix * bug fix * audio switch * update tts readme * remove tempfile when done * disable auto audio follow * avoid play queue update after shut up * feat: minimizing common.js * improve tts functionality * deterine whether the cached model is in choices * Add support for Ollama (#1740) * print err when doc2x not successful * add icon * adjust url for doc2x key version * prepare merge --------- Co-authored-by: Menghuan1918 <[email protected]> Co-authored-by: Skyzayre <[email protected]> Co-authored-by: XIao <[email protected]> Co-authored-by: Yuki <[email protected]> Co-authored-by: zyren123 <[email protected]> Co-authored-by: zym9804 <[email protected]>
binary-husky · Apr 30, 2024 · 5fcd025 · 5fcd025
1 parent bd5280d
commit 5fcd025
Show file tree

Hide file tree

Showing 19 changed files with 1,162 additions and 66 deletions.
diff --git a/.gitignore b/.gitignore
@@ -153,3 +153,4 @@ media
 flagged
 request_llms/ChatGLM-6b-onnx-u8s8
 .pre-commit-config.yaml
+themes/common.js.min.*.js
diff --git a/config.py b/config.py
@@ -34,7 +34,7 @@
 LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
 AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
                     "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
-                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
                     "gemini-pro", "chatglm3"
                     ]
 # --- --- --- ---
@@ -50,17 +50,17 @@
 #   "yi-34b-chat-0205", "yi-34b-chat-200k"
 # ]
 # --- --- --- ---
-# 此外，为了更灵活地接入one-api多模型管理界面，您还可以在接入one-api时，
-# 使用"one-api-*"前缀直接使用非标准方式接入的模型，例如
-# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)"]
+# 此外，您还可以在接入one-api/vllm/ollama时，
+# 使用"one-api-*","vllm-*","ollama-*"前缀直接使用非标准方式接入的模型，例如
+# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)"]
 # --- --- --- ---
 
 
 # --------------- 以下配置可以优化体验 ---------------
 
 # 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
 # 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
-# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
+# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
 API_URL_REDIRECT = {}
 
 
@@ -195,6 +195,12 @@
 ALIYUN_SECRET=""    # （无需填写）
 
 
+# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
+TTS_TYPE = "DISABLE" # LOCAL / LOCAL_SOVITS_API / DISABLE
+GPT_SOVITS_URL = ""
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+
+
 # 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
 XFYUN_APPID = "00000000"
 XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"

diff --git a/crazy_functions/PDF批量翻译.py b/crazy_functions/PDF批量翻译.py
@@ -74,8 +74,10 @@ def pdf2markdown(filepath):
         import requests, json, os
         markdown_dir = get_log_folder(plugin_name="pdf_ocr")
         doc2x_api_key = DOC2X_API_KEY
-        # url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
-        url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
+        if doc2x_api_key.startswith('sk-'):
+            url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
+        else:
+            url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
 
         chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

diff --git a/docs/use_tts.md b/docs/use_tts.md
@@ -0,0 +1,58 @@
+# 使用TTS文字转语音
+
+
+## 1. 使用EDGE-TTS（简单）
+
+将本项目配置项修改如下即可
+
+```
+TTS_TYPE = "EDGE_TTS"
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+```
+
+## 2. 使用SoVITS（需要有显卡）
+
+使用以下docker-compose.yml文件，先启动SoVITS服务API
+
+  1. 创建以下文件夹结构
+      ```shell
+      .
+      ├── docker-compose.yml
+      └── reference
+          ├── clone_target_txt.txt
+          └── clone_target_wave.mp3
+      ```
+  2. 其中`docker-compose.yml`为
+      ```yaml
+      version: '3.8'
+      services:
+        gpt-sovits:
+          image: fuqingxu/sovits_gptac_trim:latest
+          container_name: sovits_gptac_container
+          working_dir: /workspace/gpt_sovits_demo
+          environment:
+            - is_half=False
+            - is_share=False
+          volumes:
+            - ./reference:/reference
+          ports:
+            - "19880:9880"  # 19880 为 sovits api 的暴露端口，记住它
+          shm_size: 16G
+          deploy:
+            resources:
+              reservations:
+                devices:
+                - driver: nvidia
+                  count: "all"
+                  capabilities: [gpu]
+          command: bash -c "python3 api.py"
+      ```
+  3. 其中`clone_target_wave.mp3`为需要克隆的角色音频，`clone_target_txt.txt`为该音频对应的文字文本（ https://wiki.biligame.com/ys/%E8%A7%92%E8%89%B2%E8%AF%AD%E9%9F%B3 ）
+  4. 运行`docker-compose up`
+  5. 将本项目配置项修改如下即可
+      (19880 为 sovits api 的暴露端口，与docker-compose.yml中的端口对应)
+      ```
+      TTS_TYPE = "LOCAL_SOVITS_API"
+      GPT_SOVITS_URL = "http://127.0.0.1:19880"
+      ```
+  6. 启动本项目
diff --git a/main.py b/main.py
@@ -1,4 +1,4 @@
-import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
+import os, json; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
 
 help_menu_description = \
 """Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
@@ -14,7 +14,7 @@
 </br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
 
 def enable_log(PATH_LOGGING):
-    import logging, uuid
+    import logging
     admin_log_path = os.path.join(PATH_LOGGING, "admin")
     os.makedirs(admin_log_path, exist_ok=True)
     log_dir = os.path.join(admin_log_path, "chat_secrets.log")
@@ -29,13 +29,14 @@ def main():
     if gr.__version__ not in ['3.32.9']:
         raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
     from request_llms.bridge_all import predict
-    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
+    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
     proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
     CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
     ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
     NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
-    DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU')
+    DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
+    if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
 
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
@@ -79,15 +80,18 @@ def main():
     cancel_handles = []
     customize_btns = {}
     predefined_btns = {}
+    from shared_utils.cookie_manager import make_cookie_cache, make_history_cache
     with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as app_block:
         gr.HTML(title_html)
-        secret_css, web_cookie_cache = gr.Textbox(visible=False), gr.Textbox(visible=False)
-        cookies = gr.State(load_chat_cookies())
+        secret_css = gr.Textbox(visible=False, elem_id="secret_css")
+
+
+        cookies, web_cookie_cache = make_cookie_cache() # 定义 后端state（cookies）、前端（web_cookie_cache）两兄弟
         with gr_L1():
             with gr_L2(scale=2, elem_id="gpt-chat"):
                 chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
                 if LAYOUT == "TOP-DOWN":  chatbot.style(height=CHATBOT_HEIGHT)
-                history = gr.State([])
+                history, history_cache, history_cache_update = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
             with gr_L2(scale=1, elem_id="gpt-panel"):
                 with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
                     with gr.Row():
@@ -155,7 +159,7 @@ def main():
                     file_upload_2 = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload_float")
 
                 with gr.Tab("更换模型", elem_id="interact-panel"):
-                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
+                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, elem_id="elem_model_sel", label="更换LLM模型/请求源").style(container=False)
                     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", elem_id="elem_temperature")
                     max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
@@ -164,6 +168,8 @@ def main():
                         _js="""(temperature)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_temperature_cookie", temperature)""")
                     system_prompt.change(None, inputs=[system_prompt], outputs=None,
                         _js="""(system_prompt)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_system_prompt_cookie", system_prompt)""")
+                    md_dropdown.change(None, inputs=[md_dropdown], outputs=None,
+                        _js="""(md_dropdown)=>gpt_academic_gradio_saveload("save", "elem_model_sel", "js_md_dropdown_cookie", md_dropdown)""")
 
                 with gr.Tab("界面外观", elem_id="interact-panel"):
                     theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
@@ -247,8 +253,10 @@ def fn_area_visibility_2(a):
         cancel_handles.append(submitBtn2.click(**predict_args))
         resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset)   # 先在前端快速清除chatbot&status
         resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset)  # 先在前端快速清除chatbot&status
-        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])    # 再在后端清除history
-        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])   # 再在后端清除history
+        reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)),
+                                  [history], [chatbot, history, status, history_cache])
+        resetBtn.click(*reset_server_side_args)    # 再在后端清除history，把history转存history_cache备用
+        resetBtn2.click(*reset_server_side_args)   # 再在后端清除history，把history转存history_cache备用
         clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
         clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
         if AUTO_CLEAR_TXT:
@@ -271,7 +279,7 @@ def fn_area_visibility_2(a):
         for k in plugins:
             if not plugins[k].get("AsButton", True): continue
             click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
-            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [plugins[k]["Button"]], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
             cancel_handles.append(click_handle)
         # 函数插件-下拉菜单与随变按钮的互动
         def on_dropdown_changed(k):
@@ -309,7 +317,7 @@ def route(request: gr.Request, k, *args, **kwargs):
             if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
             yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
         click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
-        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
         cancel_handles.append(click_handle)
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
@@ -342,7 +350,7 @@ def deal_audio(audio, cookies):
         app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
             outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
 
-        app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}")""")    # 配置暗色主题或亮色主题
+        app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""")    # 配置暗色主题或亮色主题
 
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def run_delayed_tasks():

diff --git a/request_llms/bridge_all.py b/request_llms/bridge_all.py
@@ -67,7 +67,8 @@ def decode(self, *args, **kwargs):
 gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
 claude_endpoint = "https://api.anthropic.com/v1/messages"
 yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
-cohere_endpoint = 'https://api.cohere.ai/v1/chat'
+cohere_endpoint = "https://api.cohere.ai/v1/chat"
+ollama_endpoint = "http://localhost:11434/api/chat"
 
 if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
@@ -87,6 +88,7 @@ def decode(self, *args, **kwargs):
 if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
 if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
 if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[cohere_endpoint]
+if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
 
 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@@ -266,6 +268,14 @@ def decode(self, *args, **kwargs):
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    "glm-4v": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 1000,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
     "glm-3-turbo": {
         "fn_with_ui": zhipu_ui,
         "fn_without_ui": zhipu_noui,
@@ -827,7 +837,32 @@ def decode(self, *args, **kwargs):
             "token_cnt": get_token_num_gpt35,
         },
     })
-
+# -=-=-=-=-=-=- ollama 对齐支持 -=-=-=-=-=-=-
+for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
+    from .bridge_ollama import predict_no_ui_long_connection as ollama_noui
+    from .bridge_ollama import predict as ollama_ui
+    break
+for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
+    # 为了更灵活地接入ollama多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["ollama-phi3(max_token=6666)"]
+    # 其中
+    #   "ollama-"           是前缀（必要）
+    #   "phi3"            是模型名（必要）
+    #   "(max_token=6666)"  是配置（非必要）
+    try:
+        _, max_token_tmp = read_one_api_model_name(model)
+    except:
+        print(f"ollama模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        continue
+    model_info.update({
+        model: {
+            "fn_with_ui": ollama_ui,
+            "fn_without_ui": ollama_noui,
+            "endpoint": ollama_endpoint,
+            "max_token": max_token_tmp,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
 
 # -=-=-=-=-=-=- azure模型对齐支持 -=-=-=-=-=-=-
 AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY") # <-- 用于定义和切换多个azure模型 -->