@@ -23,7 +23,6 @@ Demo made by [Visionn](https://www.wangpc.cc/) | |||
SaaS服务、私有化部署、稳定托管接入 等多种模式。 | |||
> | |||
> 目前已在私域运营、智能客服、企业效率助手等场景积累了丰富的 AI 解决方案, 在电商、文教、健康、新消费等各行业沉淀了 AI 落地的最佳实践,致力于打造助力中小企业拥抱 AI 的一站式平台。 | |||
企业服务和商用咨询可联系产品顾问: | |||
<img width="240" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/product-manager-qrcode.jpg"> | |||
@@ -44,6 +44,7 @@ class GoogleGeminiBot(Bot): | |||
except Exception as e: | |||
logger.error("[Gemini] fetch reply error, may contain unsafe content") | |||
logger.error(e) | |||
return Reply(ReplyType.ERROR, "invoke [Gemini] api failed!") | |||
def _convert_to_gemini_messages(self, messages: list): | |||
res = [] | |||
@@ -63,6 +64,8 @@ class GoogleGeminiBot(Bot): | |||
def _filter_messages(self, messages: list): | |||
res = [] | |||
turn = "user" | |||
if not messages: | |||
return res | |||
for i in range(len(messages) - 1, -1, -1): | |||
message = messages[i] | |||
if message.get("role") != turn: | |||
@@ -92,6 +92,7 @@ class LinkAIBot(Bot): | |||
"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 | |||
"presence_penalty": conf().get("presence_penalty", 0.0), # [-2,2]之间,该值越大则更倾向于产生不同的内容 | |||
"session_id": session_id, | |||
"sender_id": session_id, | |||
"channel_type": conf().get("channel_type", "wx") | |||
} | |||
try: | |||
@@ -47,7 +47,7 @@ class XunFeiBot(Bot): | |||
# 默认使用v2.0版本: "ws://spark-api.xf-yun.com/v2.1/chat" | |||
# v1.5版本为: "ws://spark-api.xf-yun.com/v1.1/chat" | |||
# v3.0版本为: "ws://spark-api.xf-yun.com/v3.1/chat" | |||
# 升级到v3.5版本,同时升级到wss协议,避免请求时出现11200错误码 | |||
# v3.5版本为: "wss://spark-api.xf-yun.com/v3.5/chat" | |||
self.spark_url = "wss://spark-api.xf-yun.com/v3.5/chat" | |||
self.host = urlparse(self.spark_url).netloc | |||
self.path = urlparse(self.spark_url).path | |||
@@ -11,7 +11,7 @@ class ReplyType(Enum): | |||
VIDEO_URL = 5 # 视频URL | |||
FILE = 6 # 文件 | |||
CARD = 7 # 微信名片,仅支持ntchat | |||
InviteRoom = 8 # 邀请好友进群 | |||
INVITE_ROOM = 8 # 邀请好友进群 | |||
INFO = 9 | |||
ERROR = 10 | |||
TEXT_ = 11 # 强制文本 | |||
@@ -170,11 +170,13 @@ class ChatChannel(Channel): | |||
reply = self._generate_reply(context) | |||
logger.debug("[WX] ready to decorate reply: {}".format(reply)) | |||
# reply的包装步骤 | |||
reply = self._decorate_reply(context, reply) | |||
if reply and reply.content: | |||
reply = self._decorate_reply(context, reply) | |||
# reply的发送步骤 | |||
self._send_reply(context, reply) | |||
# reply的发送步骤 | |||
self._send_reply(context, reply) | |||
def _generate_reply(self, context: Context, reply: Reply = Reply()) -> Reply: | |||
e_context = PluginManager().emit_event( | |||
@@ -233,7 +233,6 @@ class WechatChannel(ChatChannel): | |||
logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver)) | |||
elif reply.type == ReplyType.IMAGE: # 从文件读取图片 | |||
image_storage = reply.content | |||
image_storage.seek(0) | |||
itchat.send_image(image_storage, toUserName=receiver) | |||
logger.info("[WX] sendImage, receiver={}".format(receiver)) | |||
elif reply.type == ReplyType.FILE: # 新增文件回复类型 | |||
@@ -83,7 +83,7 @@ available_setting = { | |||
"voice_reply_voice": False, # 是否使用语音回复语音,需要设置对应语音合成引擎的api key | |||
"always_reply_voice": False, # 是否一直使用语音回复 | |||
"voice_to_text": "openai", # 语音识别引擎,支持openai,baidu,google,azure | |||
"text_to_voice": "openai", # 语音合成引擎,支持openai,baidu,google,pytts(offline),azure,elevenlabs | |||
"text_to_voice": "openai", # 语音合成引擎,支持openai,baidu,google,pytts(offline),azure,elevenlabs,edge(online) | |||
"text_to_voice_model": "tts-1", | |||
"tts_voice_id": "alloy", | |||
# baidu 语音api配置, 使用百度语音识别和语音合成时需要 | |||
@@ -99,7 +99,7 @@ class PluginManager: | |||
try: | |||
self.current_plugin_path = plugin_path | |||
if plugin_path in self.loaded: | |||
if self.loaded[plugin_path] == None: | |||
if plugin_name.upper() != 'GODCMD': | |||
logger.info("reload module %s" % plugin_name) | |||
self.loaded[plugin_path] = importlib.reload(sys.modules[import_path]) | |||
dependent_module_names = [name for name in sys.modules.keys() if name.startswith(import_path + ".")] | |||
@@ -141,19 +141,21 @@ class PluginManager: | |||
failed_plugins = [] | |||
for name, plugincls in self.plugins.items(): | |||
if plugincls.enabled: | |||
if name not in self.instances: | |||
try: | |||
instance = plugincls() | |||
except Exception as e: | |||
logger.warn("Failed to init %s, diabled. %s" % (name, e)) | |||
self.disable_plugin(name) | |||
failed_plugins.append(name) | |||
continue | |||
self.instances[name] = instance | |||
for event in instance.handlers: | |||
if event not in self.listening_plugins: | |||
self.listening_plugins[event] = [] | |||
self.listening_plugins[event].append(name) | |||
if 'GODCMD' in self.instances and name == 'GODCMD': | |||
continue | |||
# if name not in self.instances: | |||
try: | |||
instance = plugincls() | |||
except Exception as e: | |||
logger.warn("Failed to init %s, diabled. %s" % (name, e)) | |||
self.disable_plugin(name) | |||
failed_plugins.append(name) | |||
continue | |||
self.instances[name] = instance | |||
for event in instance.handlers: | |||
if event not in self.listening_plugins: | |||
self.listening_plugins[event] = [] | |||
self.listening_plugins[event].append(name) | |||
self.refresh_order() | |||
return failed_plugins | |||
@@ -20,5 +20,9 @@ | |||
"url": "https://github.com/6vision/Apilot.git", | |||
"desc": "通过api直接查询早报、热榜、快递、天气等实用信息的插件" | |||
} | |||
"pictureChange": { | |||
"url": "https://github.com/Yanyutin753/pictureChange.git", | |||
"desc": "利用stable-diffusion和百度Ai进行图生图或者画图的插件" | |||
} | |||
} | |||
} |
@@ -137,7 +137,7 @@ class Tool(Plugin): | |||
return { | |||
# 全局配置相关 | |||
"log": True, # tool 日志开关 | |||
"log": False, # tool 日志开关 | |||
"debug": kwargs.get("debug", False), # 输出更多日志 | |||
"no_default": kwargs.get("no_default", False), # 不要默认的工具,只加载自己导入的工具 | |||
"think_depth": kwargs.get("think_depth", 2), # 一个问题最多使用多少次工具 | |||
@@ -7,6 +7,7 @@ gTTS>=2.3.1 # google text to speech | |||
pyttsx3>=2.90 # pytsx text to speech | |||
baidu_aip>=4.16.10 # baidu voice | |||
azure-cognitiveservices-speech # azure voice | |||
edge-tts # edge-tts | |||
numpy<=1.24.2 | |||
langid # language detect | |||
@@ -64,7 +64,9 @@ def any_to_wav(any_path, wav_path): | |||
if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"): | |||
return sil_to_wav(any_path, wav_path) | |||
audio = AudioSegment.from_file(any_path) | |||
audio.export(wav_path, format="wav") | |||
audio.set_frame_rate(8000) # 百度语音转写支持8000采样率, pcm_s16le, 单通道语音识别 | |||
audio.set_channels(1) | |||
audio.export(wav_path, format="wav", codec='pcm_s16le') | |||
def any_to_sil(any_path, sil_path): | |||
@@ -62,7 +62,7 @@ class BaiduVoice(Voice): | |||
# 识别本地文件 | |||
logger.debug("[Baidu] voice file name={}".format(voice_file)) | |||
pcm = get_pcm_from_wav(voice_file) | |||
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.dev_id}) | |||
res = self.client.asr(pcm, "pcm", 8000, {"dev_pid": self.dev_id}) | |||
if res["err_no"] == 0: | |||
logger.info("百度语音识别到了:{}".format(res["result"])) | |||
text = "".join(res["result"]) | |||
@@ -0,0 +1,50 @@ | |||
import time | |||
import edge_tts | |||
import asyncio | |||
from bridge.reply import Reply, ReplyType | |||
from common.log import logger | |||
from common.tmp_dir import TmpDir | |||
from voice.voice import Voice | |||
class EdgeVoice(Voice): | |||
def __init__(self): | |||
''' | |||
# 普通话 | |||
zh-CN-XiaoxiaoNeural | |||
zh-CN-XiaoyiNeural | |||
zh-CN-YunjianNeural | |||
zh-CN-YunxiNeural | |||
zh-CN-YunxiaNeural | |||
zh-CN-YunyangNeural | |||
# 地方口音 | |||
zh-CN-liaoning-XiaobeiNeural | |||
zh-CN-shaanxi-XiaoniNeural | |||
# 粤语 | |||
zh-HK-HiuGaaiNeural | |||
zh-HK-HiuMaanNeural | |||
zh-HK-WanLungNeural | |||
# 湾湾腔 | |||
zh-TW-HsiaoChenNeural | |||
zh-TW-HsiaoYuNeural | |||
zh-TW-YunJheNeural | |||
''' | |||
self.voice = "zh-CN-YunjianNeural" | |||
def voiceToText(self, voice_file): | |||
pass | |||
async def gen_voice(self, text, fileName): | |||
communicate = edge_tts.Communicate(text, self.voice) | |||
await communicate.save(fileName) | |||
def textToVoice(self, text): | |||
fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3" | |||
asyncio.run(self.gen_voice(text, fileName)) | |||
logger.info("[EdgeTTS] textToVoice text={} voice file name={}".format(text, fileName)) | |||
return Reply(ReplyType.VOICE, fileName) |
@@ -42,4 +42,8 @@ def create_voice(voice_type): | |||
from voice.ali.ali_voice import AliVoice | |||
return AliVoice() | |||
elif voice_type == "edge": | |||
from voice.edge.edge_voice import EdgeVoice | |||
return EdgeVoice() | |||
raise RuntimeError |