diff --git a/.gitignore b/.gitignore index 6c6fb46..9b3bcdf 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,8 @@ .DS_Store .idea .vscode +.venv +.vs .wechaty/ __pycache__/ venv* @@ -22,6 +24,8 @@ plugins/**/ !plugins/tool !plugins/banwords !plugins/banwords/**/ +plugins/banwords/__pycache__ +plugins/banwords/lib/__pycache__ !plugins/hello !plugins/role !plugins/keyword diff --git a/README.md b/README.md index b685c67..8bbd9c0 100644 --- a/README.md +++ b/README.md @@ -5,11 +5,12 @@ 最新版本支持的功能如下: - [x] **多端部署:** 有多种部署方式可选择且功能完备,目前已支持个人微信,微信公众号和企业微信应用等部署方式 -- [x] **基础对话:** 私聊及群聊的消息智能回复,支持多轮会话上下文记忆,支持 GPT-3,GPT-3.5,GPT-4模型 +- [x] **基础对话:** 私聊及群聊的消息智能回复,支持多轮会话上下文记忆,支持 GPT-3, GPT-3.5, GPT-4, 文心一言模型 - [x] **语音识别:** 可识别语音消息,通过文字或语音回复,支持 azure, baidu, google, openai等多种语音模型 -- [x] **图片生成:** 支持图片生成 和 图生图(如照片修复),可选择 Dell-E, stable diffusion, replicate模型 +- [x] **图片生成:** 支持图片生成 和 图生图(如照片修复),可选择 Dell-E, stable diffusion, replicate, midjourney模型 - [x] **丰富插件:** 支持个性化插件扩展,已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结等插件 - [X] **Tool工具:** 与操作系统和互联网交互,支持最新信息搜索、数学计算、天气和资讯查询、网页总结,基于 [chatgpt-tool-hub](https://github.com/goldfishh/chatgpt-tool-hub) 实现 +- [x] **知识库:** 通过上传知识库文件自定义专属机器人,可作为数字分身、领域知识库、智能客服使用,基于 [LinkAI](https://chat.link-ai.tech/console) 实现 > 欢迎接入更多应用,参考 [Terminal代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/terminal/terminal_channel.py)实现接收和发送消息逻辑即可接入。 同时欢迎增加新的插件,参考 [插件说明文档](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)。 @@ -27,7 +28,9 @@ Demo made by [Visionn](https://www.wangpc.cc/) # 更新日志 ->**2023.06.12:** 接入 [LinkAI](https://chat.link-ai.tech/console) 平台,可在线创建 个人知识库,并接入微信、公众号及企业微信中。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。 +>**2023.08.08:** 接入百度文心一言模型,通过 [插件](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/linkai) 支持 Midjourney 绘图 + +>**2023.06.12:** 接入 [LinkAI](https://chat.link-ai.tech/console) 平台,可在线创建个人知识库,并接入微信、公众号及企业微信中,打造专属客服机器人。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。 >**2023.04.26:** 支持企业微信应用号部署,兼容插件,并支持语音图片交互,私人助理理想选择,[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatcom/README.md)。(contributed by [@lanvent](https://github.com/lanvent) in [#944](https://github.com/zhayujie/chatgpt-on-wechat/pull/944)) @@ -151,7 +154,7 @@ pip3 install azure-cognitiveservices-speech **4.其他配置** -+ `model`: 模型名称,目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k` (其中gpt-4 api暂未完全开放,申请通过后可使用) ++ `model`: 模型名称,目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k`, `wenxin` (其中gpt-4 api暂未完全开放,申请通过后可使用) + `temperature`,`frequency_penalty`,`presence_penalty`: Chat API接口参数,详情参考[OpenAI官方文档。](https://platform.openai.com/docs/api-reference/chat) + `proxy`:由于目前 `openai` 接口国内无法访问,需配置代理客户端的地址,详情参考 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351) + 对于图像生成,在满足个人或群组触发条件外,还需要额外的关键词前缀来触发,对应配置 `image_create_prefix ` diff --git a/bot/baidu/baidu_wenxin.py b/bot/baidu/baidu_wenxin.py new file mode 100644 index 0000000..589e249 --- /dev/null +++ b/bot/baidu/baidu_wenxin.py @@ -0,0 +1,104 @@ +# encoding:utf-8 + +import requests, json +from bot.bot import Bot +from bridge.reply import Reply, ReplyType +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 +from bot.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__() + self.sessions = SessionManager(BaiduWenxinSession, model=conf().get("baidu_wenxin_model") or "eb-instant") + + 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} + response = requests.request("POST", url, headers=headers, data=json.dumps(payload)) + response_text = json.loads(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 = {"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")) diff --git a/bot/baidu/baidu_wenxin_session.py b/bot/baidu/baidu_wenxin_session.py new file mode 100644 index 0000000..aad8f71 --- /dev/null +++ b/bot/baidu/baidu_wenxin_session.py @@ -0,0 +1,87 @@ +from bot.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): + # pdb.set_trace() + 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) + + +# refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb +def num_tokens_from_messages(messages, model): + """Returns the number of tokens used by a list of messages.""" + import tiktoken + + if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo"]: + 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"]: + return num_tokens_from_messages(messages, model="gpt-4") + + try: + encoding = tiktoken.encoding_for_model(model) + except KeyError: + logger.debug("Warning: model not found. Using cl100k_base encoding.") + encoding = tiktoken.get_encoding("cl100k_base") + if model == "gpt-3.5-turbo": + tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n + tokens_per_name = -1 # if there's a name, the role is omitted + elif model == "gpt-4": + tokens_per_message = 3 + tokens_per_name = 1 + else: + logger.warn(f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo.") + return num_tokens_from_messages(messages, model="gpt-3.5-turbo") + num_tokens = 0 + for message in messages: + num_tokens += tokens_per_message + for key, value in message.items(): + num_tokens += len(encoding.encode(value)) + if key == "name": + num_tokens += tokens_per_name + num_tokens += 3 # every reply is primed with <|start|>assistant<|message|> + return num_tokens diff --git a/bot/bot_factory.py b/bot/bot_factory.py index 2e9cb2d..e0e07e4 100644 --- a/bot/bot_factory.py +++ b/bot/bot_factory.py @@ -11,10 +11,13 @@ def create_bot(bot_type): :return: bot instance """ if bot_type == const.BAIDU: - # Baidu Unit对话接口 - from bot.baidu.baidu_unit_bot import BaiduUnitBot + # 替换Baidu Unit为Baidu文心千帆对话接口 + # from bot.baidu.baidu_unit_bot import BaiduUnitBot + # return BaiduUnitBot() - return BaiduUnitBot() + from bot.baidu.baidu_wenxin import BaiduWenxinBot + + return BaiduWenxinBot() elif bot_type == const.CHATGPT: # ChatGPT 网页端web接口 diff --git a/bot/linkai/link_ai_bot.py b/bot/linkai/link_ai_bot.py index c95113a..d90bcb0 100644 --- a/bot/linkai/link_ai_bot.py +++ b/bot/linkai/link_ai_bot.py @@ -64,15 +64,16 @@ class LinkAIBot(Bot, OpenAIImage): session_id = context["session_id"] session = self.sessions.session_query(query, session_id) - + model = conf().get("model") or "gpt-3.5-turbo" # remove system message - if app_code and session.messages[0].get("role") == "system": - session.messages.pop(0) + if session.messages[0].get("role") == "system": + if app_code or model == "wenxin": + session.messages.pop(0) body = { "app_code": app_code, "messages": session.messages, - "model": conf().get("model") or "gpt-3.5-turbo", # 对话模型的名称 + "model": model, # 对话模型的名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin "temperature": conf().get("temperature"), "top_p": conf().get("top_p", 1), "frequency_penalty": conf().get("frequency_penalty", 0.0), # [-2,2]之间,该值越大则更倾向于产生不同的内容 diff --git a/bridge/bridge.py b/bridge/bridge.py index 524cb8c..c58b975 100644 --- a/bridge/bridge.py +++ b/bridge/bridge.py @@ -23,6 +23,8 @@ class Bridge(object): self.btype["chat"] = const.OPEN_AI if conf().get("use_azure_chatgpt", False): self.btype["chat"] = const.CHATGPTONAZURE + if model_type in ["wenxin"]: + self.btype["chat"] = const.BAIDU if conf().get("use_linkai") and conf().get("linkai_api_key"): self.btype["chat"] = const.LINKAI self.bots = {} diff --git a/config-template.json b/config-template.json index 0c14ff4..f01633d 100644 --- a/config-template.json +++ b/config-template.json @@ -1,6 +1,7 @@ { "open_ai_api_key": "YOUR API KEY", "model": "gpt-3.5-turbo", + "channel_type": "wx", "proxy": "", "hot_reload": false, "single_chat_prefix": [ diff --git a/config.py b/config.py index 8359b0d..fb5b407 100644 --- a/config.py +++ b/config.py @@ -16,7 +16,7 @@ available_setting = { "open_ai_api_base": "https://api.openai.com/v1", "proxy": "", # openai使用的代理 # chatgpt模型, 当use_azure_chatgpt为true时,其名称为Azure上model deployment名称 - "model": "gpt-3.5-turbo", + "model": "gpt-3.5-turbo", # 还支持 gpt-3.5-turbo-16k, gpt-4, wenxin "use_azure_chatgpt": False, # 是否使用azure的chatgpt "azure_deployment_id": "", # azure 模型部署名称 "azure_api_version": "", # azure api版本 @@ -51,6 +51,10 @@ available_setting = { "presence_penalty": 0, "request_timeout": 60, # chatgpt请求超时时间,openai接口默认设置为600,对于难问题一般需要较长时间 "timeout": 120, # chatgpt重试超时时间,在这个时间内,将会自动重试 + # Baidu 文心一言参数 + "baidu_wenxin_model": "eb-instant", # 默认使用ERNIE-Bot-turbo模型 + "baidu_wenxin_api_key": "", # Baidu api key + "baidu_wenxin_secret_key": "", # Baidu secret key # 语音设置 "speech_recognition": False, # 是否开启语音识别 "group_speech_recognition": False, # 是否开启群组语音识别 diff --git a/plugins/linkai/README.md b/plugins/linkai/README.md index 3397e0f..5380c43 100644 --- a/plugins/linkai/README.md +++ b/plugins/linkai/README.md @@ -47,6 +47,8 @@ 例如输入 `$linkai app Kv2fXJcH`,即将当前群聊与 app_code为 Kv2fXJcH 的应用绑定。 +另外,还可以通过 `$linkai close` 来一键关闭linkai对话,此时就会使用默认的openai接口;同理,发送 `$linkai open` 可以再次开启。 + ### 2.Midjourney绘画功能 指令格式: @@ -54,6 +56,8 @@ ``` - 图片生成: $mj 描述词1, 描述词2.. - 图片放大: $mju 图片ID 图片序号 + - 图片变换: $mjv 图片ID 图片序号 + - 重置: $mjr 图片ID ``` 例如: @@ -61,6 +65,11 @@ ``` "$mj a little cat, white --ar 9:16" "$mju 1105592717188272288 2" +"$mjv 11055927171882 2" +"$mjr 11055927171882" ``` -注:开启 `use_image_create_prefix` 配置后可直接复用全局画图触发词,以"画"开头便可以生成图片。 \ No newline at end of file +注: +1. 开启 `use_image_create_prefix` 配置后可直接复用全局画图触发词,以"画"开头便可以生成图片。 +2. 提示词内容中包含敏感词或者参数格式错误可能导致绘画失败,生成失败不消耗积分 +3. 使用 `$mj open` 和 `$mj close` 指令可以快速打开和关闭绘图功能 diff --git a/plugins/linkai/linkai.py b/plugins/linkai/linkai.py index a71b3b1..727f02c 100644 --- a/plugins/linkai/linkai.py +++ b/plugins/linkai/linkai.py @@ -130,8 +130,11 @@ class LinkAI(Plugin): help_text = "用于集成 LinkAI 提供的知识库、Midjourney绘画等能力。\n\n" if not verbose: return help_text - help_text += f'📖 知识库\n - 群聊中指定应用: {trigger_prefix}linkai app 应用编码\n\n例如: \n"$linkai app Kv2fXJcH"\n\n' - help_text += f"🎨 绘画\n - 生成: {trigger_prefix}mj 描述词1, 描述词2.. \n - 放大: {trigger_prefix}mju 图片ID 图片序号\n - 变换: mjv 图片ID 图片序号\n - 重置: mjr 图片ID" + help_text += f'📖 知识库\n - 群聊中指定应用: {trigger_prefix}linkai app 应用编码\n' + help_text += f' - {trigger_prefix}linkai open: 开启对话\n' + help_text += f' - {trigger_prefix}linkai close: 关闭对话\n' + help_text += f'\n例如: \n"{trigger_prefix}linkai app Kv2fXJcH"\n\n' + help_text += f"🎨 绘画\n - 生成: {trigger_prefix}mj 描述词1, 描述词2.. \n - 放大: {trigger_prefix}mju 图片ID 图片序号\n - 变换: {trigger_prefix}mjv 图片ID 图片序号\n - 重置: {trigger_prefix}mjr 图片ID" help_text += f"\n\n例如:\n\"{trigger_prefix}mj a little cat, white --ar 9:16\"\n\"{trigger_prefix}mju 11055927171882 2\"" help_text += f"\n\"{trigger_prefix}mjv 11055927171882 2\"\n\"{trigger_prefix}mjr 11055927171882\"" return help_text