diff --git a/bridge/agent_bridge.py b/bridge/agent_bridge.py index 44d59b7f..81caad3c 100644 --- a/bridge/agent_bridge.py +++ b/bridge/agent_bridge.py @@ -74,7 +74,7 @@ class AgentLLMModel(LLMModel): ("qwen", const.QWEN_DASHSCOPE), ("qwq", const.QWEN_DASHSCOPE), ("qvq", const.QWEN_DASHSCOPE), ("gemini", const.GEMINI), ("glm", const.ZHIPU_AI), ("claude", const.CLAUDEAPI), ("moonshot", const.MOONSHOT), ("kimi", const.MOONSHOT), - ("doubao", const.DOUBAO), + ("doubao", const.DOUBAO), ("deepseek", const.DEEPSEEK), ] def __init__(self, bridge: Bridge, bot_type: str = "chat"): @@ -115,8 +115,6 @@ class AgentLLMModel(LLMModel): return const.QWEN_DASHSCOPE if model_name in [const.MOONSHOT, "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]: return const.MOONSHOT - if model_name in [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER]: - return const.OPENAI for prefix, btype in self._MODEL_PREFIX_MAP: if model_name.startswith(prefix): return btype diff --git a/bridge/bridge.py b/bridge/bridge.py index 6c2dcb2d..388c2999 100644 --- a/bridge/bridge.py +++ b/bridge/bridge.py @@ -61,6 +61,9 @@ class Bridge(object): if model_type and model_type.startswith("doubao"): self.btype["chat"] = const.DOUBAO + if model_type and model_type.startswith("deepseek"): + self.btype["chat"] = const.DEEPSEEK + if model_type in [const.MODELSCOPE]: self.btype["chat"] = const.MODELSCOPE diff --git a/channel/web/web_channel.py b/channel/web/web_channel.py index 0be5b75a..2979cd9e 100644 --- a/channel/web/web_channel.py +++ b/channel/web/web_channel.py @@ -563,9 +563,9 @@ class ConfigHandler: }), ("deepseek", { "label": "DeepSeek", - "api_key_field": "open_ai_api_key", - "api_base_key": None, - "api_base_default": None, + "api_key_field": "deepseek_api_key", + "api_base_key": "deepseek_api_base", + "api_base_default": "https://api.deepseek.com/v1", "models": [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER], }), ("linkai", { @@ -579,9 +579,9 @@ class ConfigHandler: EDITABLE_KEYS = { "model", "bot_type", "use_linkai", - "open_ai_api_base", "claude_api_base", "gemini_api_base", + "open_ai_api_base", "deepseek_api_base", "claude_api_base", "gemini_api_base", "zhipu_ai_api_base", "moonshot_base_url", "ark_base_url", - "open_ai_api_key", "claude_api_key", "gemini_api_key", + "open_ai_api_key", "deepseek_api_key", "claude_api_key", "gemini_api_key", "zhipu_ai_api_key", "dashscope_api_key", "moonshot_api_key", "ark_api_key", "minimax_api_key", "linkai_api_key", "agent_max_context_tokens", "agent_max_context_turns", "agent_max_steps", diff --git a/models/bot_factory.py b/models/bot_factory.py index 26111b6d..5c91c7c6 100644 --- a/models/bot_factory.py +++ b/models/bot_factory.py @@ -17,7 +17,11 @@ def create_bot(bot_type): from models.baidu.baidu_wenxin import BaiduWenxinBot return BaiduWenxinBot() - elif bot_type in (const.OPENAI, const.CHATGPT, const.DEEPSEEK): # OpenAI-compatible API + elif bot_type == const.DEEPSEEK: + from models.deepseek.deepseek_bot import DeepSeekBot + return DeepSeekBot() + + elif bot_type in (const.OPENAI, const.CHATGPT): # OpenAI-compatible API from models.chatgpt.chat_gpt_bot import ChatGPTBot return ChatGPTBot() diff --git a/models/deepseek/__init__.py b/models/deepseek/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/models/deepseek/deepseek_bot.py b/models/deepseek/deepseek_bot.py new file mode 100644 index 00000000..033e0216 --- /dev/null +++ b/models/deepseek/deepseek_bot.py @@ -0,0 +1,160 @@ +# encoding:utf-8 + +""" +DeepSeek Bot — fully OpenAI-compatible, uses its own API key / base config. +""" + +import time + +import requests +from models.bot import Bot +from models.openai_compatible_bot import OpenAICompatibleBot +from models.session_manager import SessionManager +from bridge.context import ContextType +from bridge.reply import Reply, ReplyType +from common import const +from common.log import logger +from config import conf, load_config +from .deepseek_session import DeepSeekSession + +DEFAULT_API_BASE = "https://api.deepseek.com/v1" + + +class DeepSeekBot(Bot, OpenAICompatibleBot): + def __init__(self): + super().__init__() + self.sessions = SessionManager( + DeepSeekSession, + model=conf().get("model") or const.DEEPSEEK_CHAT, + ) + conf_model = conf().get("model") or const.DEEPSEEK_CHAT + self.args = { + "model": conf_model, + "temperature": conf().get("temperature", 0.7), + "top_p": conf().get("top_p", 1.0), + "frequency_penalty": conf().get("frequency_penalty", 0.0), + "presence_penalty": conf().get("presence_penalty", 0.0), + } + + # ---------- config helpers ---------- + + @property + def api_key(self): + return conf().get("deepseek_api_key") or conf().get("open_ai_api_key") + + @property + def api_base(self): + url = ( + conf().get("deepseek_api_base") + or conf().get("open_ai_api_base") + or DEFAULT_API_BASE + ) + return url.rstrip("/") + + def get_api_config(self): + """OpenAICompatibleBot interface — used by call_with_tools().""" + return { + "api_key": self.api_key, + "api_base": self.api_base, + "model": conf().get("model", const.DEEPSEEK_CHAT), + "default_temperature": conf().get("temperature", 0.7), + "default_top_p": conf().get("top_p", 1.0), + "default_frequency_penalty": conf().get("frequency_penalty", 0.0), + "default_presence_penalty": conf().get("presence_penalty", 0.0), + } + + # ---------- simple chat (non-agent mode) ---------- + + def reply(self, query, context=None): + if context.type == ContextType.TEXT: + logger.info("[DEEPSEEK] 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("[DEEPSEEK] session query={}".format(session.messages)) + + new_args = self.args.copy() + reply_content = self.reply_text(session, args=new_args) + logger.debug( + "[DEEPSEEK] 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("[DEEPSEEK] 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, args=None, retry_count: int = 0) -> dict: + try: + headers = { + "Content-Type": "application/json", + "Authorization": "Bearer " + self.api_key, + } + body = args.copy() + body["messages"] = session.messages + + res = requests.post( + f"{self.api_base}/chat/completions", + headers=headers, + json=body, + timeout=180, + ) + 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"[DEEPSEEK] 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: + 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 + + if need_retry: + time.sleep(3) + return self.reply_text(session, args, retry_count + 1) + return result + except Exception as e: + logger.exception(e) + if retry_count < 2: + return self.reply_text(session, args, retry_count + 1) + return {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"} diff --git a/models/deepseek/deepseek_session.py b/models/deepseek/deepseek_session.py new file mode 100644 index 00000000..9500c8f4 --- /dev/null +++ b/models/deepseek/deepseek_session.py @@ -0,0 +1,57 @@ +from models.session_manager import Session +from common.log import logger + + +class DeepSeekSession(Session): + def __init__(self, session_id, system_prompt=None, model="deepseek-chat"): + 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: + content = msg.get("content", "") + if isinstance(content, str): + tokens += len(content) + elif isinstance(content, list): + for block in content: + if isinstance(block, dict): + tokens += len(block.get("text", "")) + return tokens