Merge branch 'zhayujie:master' into master

bot/bot_factory.py

@@ -50,7 +50,9 @@ def create_bot(bot_type):
     elif bot_type == const.QWEN:
         from bot.ali.ali_qwen_bot import AliQwenBot
         return AliQwenBot()
-
+    elif bot_type == const.QWEN_DASHSCOPE:
+        from bot.dashscope.dashscope_bot import DashscopeBot
+        return DashscopeBot()
     elif bot_type == const.GEMINI:
         from bot.gemini.google_gemini_bot import GoogleGeminiBot
         return GoogleGeminiBot()
@@ -59,5 +61,9 @@ def create_bot(bot_type):
         from bot.zhipuai.zhipuai_bot import ZHIPUAIBot
         return ZHIPUAIBot()
 
+    elif bot_type == const.MOONSHOT:
+        from bot.moonshot.moonshot_bot import MoonshotBot
+        return MoonshotBot()
+
 
     raise RuntimeError

bot/chatgpt/chat_gpt_session.py

@@ -62,11 +62,12 @@ def num_tokens_from_messages(messages, model):
 
     import tiktoken
 
-    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106", "moonshot"]:
+    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106", "moonshot", const.LINKAI_35]:
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
     elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
                    "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
-                   "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW]:
+                   "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25,
+                   const.GPT_4o, const.LINKAI_4o, const.LINKAI_4_TURBO]:
         return num_tokens_from_messages(messages, model="gpt-4")
     elif model.startswith("claude-3"):
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")

bot/dashscope/dashscope_bot.py

@@ -0,0 +1,117 @@
+# encoding:utf-8
+
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from .dashscope_session import DashscopeSession
+import os
+import dashscope
+from http import HTTPStatus
+
+
+
+dashscope_models = {
+    "qwen-turbo": dashscope.Generation.Models.qwen_turbo,
+    "qwen-plus": dashscope.Generation.Models.qwen_plus,
+    "qwen-max": dashscope.Generation.Models.qwen_max,
+    "qwen-bailian-v1": dashscope.Generation.Models.bailian_v1
+}
+# ZhipuAI对话模型API
+class DashscopeBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(DashscopeSession, model=conf().get("model") or "qwen-plus")
+        self.model_name = conf().get("model") or "qwen-plus"
+        self.api_key = conf().get("dashscope_api_key")
+        os.environ["DASHSCOPE_API_KEY"] = self.api_key
+        self.client = dashscope.Generation
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[DASHSCOPE] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[DASHSCOPE] session query={}".format(session.messages))
+
+            reply_content = self.reply_text(session)
+            logger.debug(
+                "[DASHSCOPE] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[DASHSCOPE] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: DashscopeSession, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            dashscope.api_key = self.api_key
+            response = self.client.call(
+                dashscope_models[self.model_name],
+                messages=session.messages,
+                result_format="message"
+            )
+            if response.status_code == HTTPStatus.OK:
+                content = response.output.choices[0]["message"]["content"]
+                return {
+                    "total_tokens": response.usage["total_tokens"],
+                    "completion_tokens": response.usage["output_tokens"],
+                    "content": content,
+                }
+            else:
+                logger.error('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+                    response.request_id, response.status_code,
+                    response.code, response.message
+                ))
+                result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+                need_retry = retry_count < 2
+                result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+                if need_retry:
+                    return self.reply_text(session, retry_count + 1)
+                else:
+                    return result
+        except Exception as e:
+            logger.exception(e)
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if need_retry:
+                return self.reply_text(session, retry_count + 1)
+            else:
+                return result

bot/dashscope/dashscope_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class DashscopeSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="qwen-turbo"):
+        super().__init__(session_id)
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
+                                                                                       len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages)
+
+
+def num_tokens_from_messages(messages):
+    # 只是大概，具体计算规则：https://help.aliyun.com/zh/dashscope/developer-reference/token-api?spm=a2c4g.11186623.0.0.4d8b12b0BkP3K9
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/linkai/link_ai_bot.py

@@ -122,7 +122,7 @@ class LinkAIBot(Bot):
             headers = {"Authorization": "Bearer " + linkai_api_key}
 
             # do http request
-            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
             res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
                                 timeout=conf().get("request_timeout", 180))
             if res.status_code == 200:
@@ -261,7 +261,7 @@ class LinkAIBot(Bot):
             headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
 
             # do http request
-            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
             res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
                                 timeout=conf().get("request_timeout", 180))
             if res.status_code == 200:
@@ -304,7 +304,7 @@ class LinkAIBot(Bot):
     def _fetch_app_info(self, app_code: str):
         headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
         # do http request
-        base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+        base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
         params = {"app_code": app_code}
         res = requests.get(url=base_url + "/v1/app/info", params=params, headers=headers, timeout=(5, 10))
         if res.status_code == 200:
@@ -326,7 +326,7 @@ class LinkAIBot(Bot):
                 "response_format": "url",
                 "img_proxy": conf().get("image_proxy")
             }
-            url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/images/generations"
+            url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/images/generations"
             res = requests.post(url, headers=headers, json=data, timeout=(5, 90))
             t2 = time.time()
             image_url = res.json()["data"][0]["url"]

bot/moonshot/moonshot_bot.py

@@ -0,0 +1,143 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from .moonshot_session import MoonshotSession
+import requests
+
+
+# ZhipuAI对话模型API
+class MoonshotBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(MoonshotSession, model=conf().get("model") or "moonshot-v1-128k")
+        self.args = {
+            "model": conf().get("model") or "moonshot-v1-128k",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.3),  # 如果设置，值域须为 [0, 1] 我们推荐 0.3，以达到较合适的效果。
+            "top_p": conf().get("top_p", 1.0),  # 使用默认值
+        }
+        self.api_key = conf().get("moonshot_api_key")
+        self.base_url = conf().get("moonshot_base_url", "https://api.moonshot.cn/v1/chat/completions")
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[MOONSHOT_AI] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[MOONSHOT_AI] session query={}".format(session.messages))
+
+            model = context.get("moonshot_model")
+            new_args = self.args.copy()
+            if model:
+                new_args["model"] = model
+            # if context.get('stream'):
+            #     # reply in stream
+            #     return self.reply_text_stream(query, new_query, session_id)
+
+            reply_content = self.reply_text(session, args=new_args)
+            logger.debug(
+                "[MOONSHOT_AI] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[MOONSHOT_AI] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: MoonshotSession, args=None, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": "Bearer " + self.api_key
+            }
+            body = args
+            body["messages"] = session.messages
+            # logger.debug("[MOONSHOT_AI] response={}".format(response))
+            # logger.info("[MOONSHOT_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+            res = requests.post(
+                self.base_url,
+                headers=headers,
+                json=body
+            )
+            if res.status_code == 200:
+                response = res.json()
+                return {
+                    "total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": response["choices"][0]["message"]["content"]
+                }
+            else:
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[MOONSHOT_AI] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}")
+
+                result = {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
+                need_retry = False
+                if res.status_code >= 500:
+                    # server error, need retry
+                    logger.warn(f"[MOONSHOT_AI] do retry, times={retry_count}")
+                    need_retry = retry_count < 2
+                elif res.status_code == 401:
+                    result["content"] = "授权失败，请检查API Key是否正确"
+                elif res.status_code == 429:
+                    result["content"] = "请求过于频繁，请稍后再试"
+                    need_retry = retry_count < 2
+                else:
+                    need_retry = False
+
+                if need_retry:
+                    time.sleep(3)
+                    return self.reply_text(session, args, retry_count + 1)
+                else:
+                    return result
+        except Exception as e:
+            logger.exception(e)
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if need_retry:
+                return self.reply_text(session, args, retry_count + 1)
+            else:
+                return result

bot/moonshot/moonshot_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class MoonshotSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="moonshot-v1-128k"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
+                                                                                       len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/zhipuai/zhipu_ai_session.py

@@ -7,6 +7,8 @@ class ZhipuAISession(Session):
         super().__init__(session_id, system_prompt)
         self.model = model
         self.reset()
+        if not system_prompt:
+            logger.warn("[ZhiPu] `character_desc` can not be empty")
 
     def discard_exceeding(self, max_tokens, cur_tokens=None):
         precise = True