支持gpt-4-gizmo-XXX，动态配置GPTS

.idea/encodings.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding">
+    <file url="file://$PROJECT_DIR$/log/access.log" charset="GBK" />
+  </component>
+</project>

Readme.md

@@ -99,9 +99,9 @@
 
 - `need_log_to_file`: 用于设置是否需要将日志输出到文件，可选值为：`true`、`false`，默认为 `true`，日志文件路径为：`./log/access.log`，默认每天会自动分割日志文件。
 
-- `process_workers`: 用于设置进程数，如果不需要设置，可以保持不变，如果需要设置，可以设置为需要设置的值，如果设置为 `1`，则会强制设置为单进程模式。
+- `process_workers`: 用于设置进程数，如果不需要设置，可以保持不变，如果需要设置，可以设置为需要设置的值，默认为 `2`。
 
-- `process_threads`: 用于设置线程数，如果不需要设置，可以保持不变，如果需要设置，可以设置为需要设置的值，如果设置为 `1`，则会强制设置为单线程模式。
+- `process_threads`: 用于设置线程数，如果不需要设置，可以保持不变，如果需要设置，可以设置为需要设置的值，默认为 `2`。
 
 - `upstream_base_url`: xyhelper 的免费接口地址，如：`https://demo.xyhelper.cn`，注意：不要以 `/` 结尾。
 

data/config.json

@@ -26,7 +26,7 @@
     },
     "refresh_ToAccess": {
         "stream_sleep_time": 0,
-        "enableOai":"true",
+        "enableOai":"false",
         "xyhelper_refreshToAccess_Url": "https://demo.xyhelper.cn/applelogin"
     },
     "redis": {

main.py

@@ -255,7 +255,7 @@ def fetch_gizmo_info(base_url, proxy_api_prefix, model_id):
 # 将配置添加到全局列表
 def add_config_to_global_list(base_url, proxy_api_prefix, gpts_data):
     global gpts_configurations
-    updateGptsKey()
+    updateGptsKey()  # cSpell:ignore Gpts
     # print(f"gpts_data: {gpts_data}")
     for model_name, model_info in gpts_data.items():
         # print(f"model_name: {model_name}")
@@ -276,17 +276,15 @@ def add_config_to_global_list(base_url, proxy_api_prefix, gpts_data):
             if gizmo_info:
                 redis_client.set(model_id, str(gizmo_info))
                 logger.info(f"Cached gizmo info for {model_name}, {model_id}")
-
-        if gizmo_info:
-            # 检查模型名称是否已经在列表中
-            if not any(d['name'] == model_name for d in gpts_configurations):
-                gpts_configurations.append({
-                    'name': model_name,
-                    'id': model_id,
-                    'config': gizmo_info
-                })
-            else:
-                logger.info(f"Model already exists in the list, skipping...")
+                # 检查模型名称是否已经在列表中
+                if not any(d['name'] == model_name for d in gpts_configurations):
+                    gpts_configurations.append({
+                        'name': model_name,
+                        'id': model_id,
+                        'config': gizmo_info
+                    })
+                else:
+                    logger.info(f"Model already exists in the list, skipping...")
 
 
 def generate_gpts_payload(model, messages):
@@ -324,9 +322,9 @@ scheduler.start()
 # PANDORA_UPLOAD_URL = 'files.pandoranext.com'
 
 
-VERSION = '0.7.8'
+VERSION = '0.7.8.1'
 # VERSION = 'test'
-UPDATE_INFO = '项目将脱离ninja，使用xyhelper，xyhelper_refreshToAccess_Url等配置需修改'
+UPDATE_INFO = '支持gpt-4-gizmo-XXX，动态配置GPTS'
 # UPDATE_INFO = '【仅供临时测试使用】 '
 
 # 解析响应中的信息
@@ -864,10 +862,14 @@ def send_text_prompt_and_get_response(messages, api_key, stream, model):
 
     # 查找模型配置
     model_config = find_model_config(model)
-    if model_config:
+    if model_config or 'gpt-4-gizmo-' in model:
         # 检查是否有 ori_name
-        ori_model_name = model_config.get('ori_name', model)
-        logger.info(f"原模型名: {ori_model_name}")
+        if model_config:
+            ori_model_name = model_config.get('ori_name', model)
+            logger.info(f"原模型名: {ori_model_name}")
+        else:
+            ori_model_name = model
+            logger.info(f"请求模型名: {model}")
         if ori_model_name == 'gpt-4-s':
             payload = {
                 # 构建 payload
@@ -918,6 +920,33 @@ def send_text_prompt_and_get_response(messages, api_key, stream, model):
                 "force_paragen": False,
                 "force_rate_limit": False
             }
+        elif 'gpt-4-gizmo-' in model:
+            payload = generate_gpts_payload(model, formatted_messages)
+            if not payload:
+                global gpts_configurations
+                # 假设 model是 'gpt-4-gizmo-123'
+                split_name = model.split('gpt-4-gizmo-')
+                model_id = split_name[1] if len(split_name) > 1 else None
+                gizmo_info = fetch_gizmo_info(BASE_URL, PROXY_API_PREFIX, model_id)
+                logging.info(gizmo_info)
+
+                # 如果成功获取到数据，则将其存入 Redis
+                if gizmo_info:
+                    redis_client.set(model_id, str(gizmo_info))
+                    logger.info(f"Cached gizmo info for {model}, {model_id}")
+                    # 检查模型名称是否已经在列表中
+                    if not any(d['name'] == model for d in gpts_configurations):
+                        gpts_configurations.append({
+                            'name': model,
+                            'id': model_id,
+                            'config': gizmo_info
+                        })
+                    else:
+                        logger.info(f"Model already exists in the list, skipping...")
+                    payload = generate_gpts_payload(model, formatted_messages)
+                else:
+                    raise Exception('KEY_FOR_GPTS_INFO is not accessible')
+
         else:
             payload = generate_gpts_payload(model, formatted_messages)
             if not payload:
@@ -2248,7 +2277,7 @@ def chat_completions():
     messages = data.get('messages')
     model = data.get('model')
     accessible_model_list = get_accessible_model_list()
-    if model not in accessible_model_list:
+    if model not in accessible_model_list and not 'gpt-4-gizmo-' in model:
         return jsonify({"error": "model is not accessible"}), 401
 
     stream = data.get('stream', False)
@@ -2368,32 +2397,36 @@ def chat_completions():
             ori_model_name = model_config.get('ori_name', model)
         input_tokens = count_total_input_words(messages, ori_model_name)
         comp_tokens = count_tokens(all_new_text, ori_model_name)
-        response_json = {
-            "id": generate_unique_id("chatcmpl"),
-            "object": "chat.completion",
-            "created": int(time.time()),  # 使用当前时间戳
-            "model": model,  # 使用请求中指定的模型
-            "choices": [
-                {
-                    "index": 0,
-                    "message": {
-                        "role": "assistant",
-                        "content": all_new_text  # 使用累积的文本
-                    },
-                    "finish_reason": "stop"
-                }
-            ],
-            "usage": {
-                # 这里的 token 计数需要根据实际情况计算
-                "prompt_tokens": input_tokens,
-                "completion_tokens": comp_tokens,
-                "total_tokens": input_tokens + comp_tokens
-            },
-            "system_fingerprint": None
-        }
-
-        # 返回 JSON 响应
-        return jsonify(response_json)
+        if input_tokens >= 100 and comp_tokens <= 0:
+            # 返回错误消息和状态码429
+            error_response = {"error": "空回复"}
+            return jsonify(error_response), 429
+        else:
+            response_json = {
+                "id": generate_unique_id("chatcmpl"),
+                "object": "chat.completion",
+                "created": int(time.time()),  # 使用当前时间戳
+                "model": model,  # 使用请求中指定的模型
+                "choices": [
+                    {
+                        "index": 0,
+                        "message": {
+                            "role": "assistant",
+                            "content": all_new_text  # 使用累积的文本
+                        },
+                        "finish_reason": "stop"
+                    }
+                ],
+                "usage": {
+                    # 这里的 token 计数需要根据实际情况计算    
+                    "prompt_tokens": input_tokens,
+                    "completion_tokens": comp_tokens,
+                    "total_tokens": input_tokens + comp_tokens
+                },
+                "system_fingerprint": None
+            }
+            # 返回 JSON 响应
+            return jsonify(response_json)
     else:
         return Response(generate(), mimetype='text/event-stream')
 
@@ -2406,7 +2439,7 @@ def images_generations():
     # messages = data.get('messages')
     model = data.get('model')
     accessible_model_list = get_accessible_model_list()
-    if model not in accessible_model_list:
+    if model not in accessible_model_list and not 'gpt-4-gizmo-' in model:
         return jsonify({"error": "model is not accessible"}), 401
 
     prompt = data.get('prompt', '')

start.sh

@@ -11,7 +11,7 @@ if [ -z "$PROCESS_WORKERS" ]; then
     export PROCESS_WORKERS
 
     if [ -z "$PROCESS_WORKERS" ]; then
-        PROCESS_WORKERS=1
+        PROCESS_WORKERS=2
     fi
 fi