chore: the bot directory was changed to models

models/baidu/baidu_unit_bot.py

@@ -0,0 +1,36 @@
+# encoding:utf-8
+
+import requests
+
+from models.bot import Bot
+from bridge.reply import Reply, ReplyType
+
+
+# Baidu Unit对话接口 (可用, 但能力较弱)
+class BaiduUnitBot(Bot):
+    def reply(self, query, context=None):
+        token = self.get_token()
+        url = "https://aip.baidubce.com/rpc/2.0/unit/service/v3/chat?access_token=" + token
+        post_data = (
+            '{"version":"3.0","service_id":"S73177","session_id":"","log_id":"7758521","skill_ids":["1221886"],"request":{"terminal_id":"88888","query":"'
+            + query
+            + '", "hyper_params": {"chat_custom_bot_profile": 1}}}'
+        )
+        print(post_data)
+        headers = {"content-type": "application/x-www-form-urlencoded"}
+        response = requests.post(url, data=post_data.encode(), headers=headers)
+        if response:
+            reply = Reply(
+                ReplyType.TEXT,
+                response.json()["result"]["context"]["SYS_PRESUMED_HIST"][1],
+            )
+            return reply
+
+    def get_token(self):
+        access_key = "YOUR_ACCESS_KEY"
+        secret_key = "YOUR_SECRET_KEY"
+        host = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=" + access_key + "&client_secret=" + secret_key
+        response = requests.get(host)
+        if response:
+            print(response.json())
+            return response.json()["access_token"]

models/baidu/baidu_wenxin.py

@@ -0,0 +1,120 @@
+# encoding:utf-8
+
+import requests
+import json
+from common import const
+from models.bot import Bot
+from models.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from models.baidu.baidu_wenxin_session import BaiduWenxinSession
+
+BAIDU_API_KEY = conf().get("baidu_wenxin_api_key")
+BAIDU_SECRET_KEY = conf().get("baidu_wenxin_secret_key")
+
+class BaiduWenxinBot(Bot):
+
+    def __init__(self):
+        super().__init__()
+        wenxin_model = conf().get("baidu_wenxin_model")
+        self.prompt_enabled = conf().get("baidu_wenxin_prompt_enabled")
+        if self.prompt_enabled:
+            self.prompt = conf().get("character_desc", "")
+            if self.prompt == "":
+                logger.warn("[BAIDU] Although you enabled model prompt, character_desc is not specified.")
+        if wenxin_model is not None:
+            wenxin_model = conf().get("baidu_wenxin_model") or "eb-instant"
+        else:
+            if conf().get("model") and conf().get("model") == const.WEN_XIN:
+                wenxin_model = "completions"
+            elif conf().get("model") and conf().get("model") == const.WEN_XIN_4:
+                wenxin_model = "completions_pro"
+
+        self.sessions = SessionManager(BaiduWenxinSession, model=wenxin_model)
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context and context.type:
+            if context.type == ContextType.TEXT:
+                logger.info("[BAIDU] query={}".format(query))
+                session_id = context["session_id"]
+                reply = None
+                if query == "#清除记忆":
+                    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")
+                else:
+                    session = self.sessions.session_query(query, session_id)
+                    result = self.reply_text(session)
+                    total_tokens, completion_tokens, reply_content = (
+                        result["total_tokens"],
+                        result["completion_tokens"],
+                        result["content"],
+                    )
+                    logger.debug(
+                        "[BAIDU] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(session.messages, session_id, reply_content, completion_tokens)
+                    )
+
+                    if total_tokens == 0:
+                        reply = Reply(ReplyType.ERROR, reply_content)
+                    else:
+                        self.sessions.session_reply(reply_content, session_id, total_tokens)
+                        reply = Reply(ReplyType.TEXT, reply_content)
+                return reply
+            elif context.type == ContextType.IMAGE_CREATE:
+                ok, retstring = self.create_img(query, 0)
+                reply = None
+                if ok:
+                    reply = Reply(ReplyType.IMAGE_URL, retstring)
+                else:
+                    reply = Reply(ReplyType.ERROR, retstring)
+                return reply
+
+    def reply_text(self, session: BaiduWenxinSession, retry_count=0):
+        try:
+            logger.info("[BAIDU] model={}".format(session.model))
+            access_token = self.get_access_token()
+            if access_token == 'None':
+                logger.warn("[BAIDU] access token 获取失败")
+                return {
+                    "total_tokens": 0,
+                    "completion_tokens": 0,
+                    "content": 0,
+                    }
+            url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/" + session.model + "?access_token=" + access_token
+            headers = {
+                'Content-Type': 'application/json'
+            }
+            payload = {'messages': session.messages, 'system': self.prompt} if self.prompt_enabled else {'messages': session.messages}
+            response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
+            response_text = json.loads(response.text)
+            logger.info(f"[BAIDU] response text={response_text}")
+            res_content = response_text["result"]
+            total_tokens = response_text["usage"]["total_tokens"]
+            completion_tokens = response_text["usage"]["completion_tokens"]
+            logger.info("[BAIDU] reply={}".format(res_content))
+            return {
+                "total_tokens": total_tokens,
+                "completion_tokens": completion_tokens,
+                "content": res_content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            logger.warn("[BAIDU] Exception: {}".format(e))
+            need_retry = False
+            self.sessions.clear_session(session.session_id)
+            result = {"total_tokens": 0, "completion_tokens": 0, "content": "出错了: {}".format(e)}
+            return result
+
+    def get_access_token(self):
+        """
+        使用 AK，SK 生成鉴权签名（Access Token）
+        :return: access_token，或是None(如果错误)
+        """
+        url = "https://aip.baidubce.com/oauth/2.0/token"
+        params = {"grant_type": "client_credentials", "client_id": BAIDU_API_KEY, "client_secret": BAIDU_SECRET_KEY}
+        return str(requests.post(url, params=params).json().get("access_token"))

models/baidu/baidu_wenxin_session.py

@@ -0,0 +1,53 @@
+from models.session_manager import Session
+from common.log import logger
+
+"""
+    e.g.  [
+        {"role": "user", "content": "Who won the world series in 2020?"},
+        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
+        {"role": "user", "content": "Where was it played?"}
+    ]
+"""
+
+
+class BaiduWenxinSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="gpt-3.5-turbo"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        # 百度文心不支持system prompt
+        # 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(0)
+                self.messages.pop(0)
+            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):
+    """Returns the number of tokens used by a list of messages."""
+    tokens = 0
+    for msg in messages:
+        # 官方token计算规则暂不明确： "大约为 token数为 "中文字 + 其他语种单词数 x 1.3"
+        # 这里先直接根据字数粗略估算吧，暂不影响正常使用，仅在判断是否丢弃历史会话的时候会有偏差
+        tokens += len(msg["content"])
+    return tokens