AstrBot 3.5.6__py3-none-any.whl → 4.7.0__py3-none-any.whl

astrbot/core/provider/sources/edge_tts_source.py

@@ -1,12 +1,16 @@
-import uuid
+import asyncio
 import os
-import edge_tts
 import subprocess
-import asyncio
-from ..provider import TTSProvider
+import uuid
+
+import edge_tts
+
+from astrbot.core import logger
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
 from ..entities import ProviderType
+from ..provider import TTSProvider
 from ..register import register_provider_adapter
-from astrbot.core import logger
 
 """
 edge_tts 方式，能够免费、快速生成语音，使用需要先安装edge-tts库
@@ -18,7 +22,9 @@ Windows 如果提示找不到指定文件，以管理员身份运行命令行窗
 
 
 @register_provider_adapter(
-    "edge_tts", "Microsoft Edge TTS", provider_type=ProviderType.TEXT_TO_SPEECH
+    "edge_tts",
+    "Microsoft Edge TTS",
+    provider_type=ProviderType.TEXT_TO_SPEECH,
 )
 class ProviderEdgeTTS(TTSProvider):
     def __init__(
@@ -30,9 +36,9 @@ class ProviderEdgeTTS(TTSProvider):
 
         # 设置默认语音，如果没有指定则使用中文小萱
         self.voice = provider_config.get("edge-tts-voice", "zh-CN-XiaoxiaoNeural")
-        self.rate = provider_config.get("rate", None)
-        self.volume = provider_config.get("volume", None)
-        self.pitch = provider_config.get("pitch", None)
+        self.rate = provider_config.get("rate")
+        self.volume = provider_config.get("volume")
+        self.pitch = provider_config.get("pitch")
         self.timeout = provider_config.get("timeout", 30)
 
         self.proxy = os.getenv("https_proxy", None)
@@ -40,9 +46,9 @@ class ProviderEdgeTTS(TTSProvider):
         self.set_model("edge_tts")
 
     async def get_audio(self, text: str) -> str:
-        os.makedirs("data/temp", exist_ok=True)
-        mp3_path = f"data/temp/edge_tts_temp_{uuid.uuid4()}.mp3"
-        wav_path = f"data/temp/edge_tts_{uuid.uuid4()}.wav"
+        temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+        mp3_path = os.path.join(temp_dir, f"edge_tts_temp_{uuid.uuid4()}.mp3")
+        wav_path = os.path.join(temp_dir, f"edge_tts_{uuid.uuid4()}.wav")
 
         # 构建 Edge TTS 参数
         kwargs = {"text": text, "voice": self.voice}
@@ -96,26 +102,25 @@ class ProviderEdgeTTS(TTSProvider):
             os.remove(mp3_path)
             if os.path.exists(wav_path) and os.path.getsize(wav_path) > 0:
                 return wav_path
-            else:
-                logger.error("生成的WAV文件不存在或为空")
-                raise RuntimeError("生成的WAV文件不存在或为空")
+            logger.error("生成的WAV文件不存在或为空")
+            raise RuntimeError("生成的WAV文件不存在或为空")
 
         except subprocess.CalledProcessError as e:
             logger.error(
-                f"FFmpeg 转换失败: {e.stderr.decode() if e.stderr else str(e)}"
+                f"FFmpeg 转换失败: {e.stderr.decode() if e.stderr else str(e)}",
             )
             try:
                 if os.path.exists(mp3_path):
                     os.remove(mp3_path)
             except Exception:
                 pass
-            raise RuntimeError(f"FFmpeg 转换失败: {str(e)}")
+            raise RuntimeError(f"FFmpeg 转换失败: {e!s}")
 
         except Exception as e:
-            logger.error(f"音频生成失败: {str(e)}")
+            logger.error(f"音频生成失败: {e!s}")
             try:
                 if os.path.exists(mp3_path):
                     os.remove(mp3_path)
             except Exception:
                 pass
-            raise RuntimeError(f"音频生成失败: {str(e)}")
+            raise RuntimeError(f"音频生成失败: {e!s}")

astrbot/core/provider/sources/fishaudio_tts_api_source.py

@@ -1,10 +1,16 @@
+import os
+import re
 import uuid
+from typing import Annotated, Literal
+
 import ormsgpack
-from pydantic import BaseModel, conint
 from httpx import AsyncClient
-from typing import Annotated, Literal
-from ..provider import TTSProvider
+from pydantic import BaseModel, conint
+
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
 from ..entities import ProviderType
+from ..provider import TTSProvider
 from ..register import register_provider_adapter
 
 
@@ -22,8 +28,8 @@ class ServeTTSRequest(BaseModel):
     # 参考音频
     references: list[ServeReferenceAudio] = []
     # 参考模型 ID
-    # 例如 https://fish.audio/m/7f92f8afb8ec43bf81429cc1c9199cb1/
-    # 其中reference_id为 7f92f8afb8ec43bf81429cc1c9199cb1
+    # 例如 https://fish.audio/m/626bb6d3f3364c9cbc3aa6a67300a664/
+    # 其中reference_id为 626bb6d3f3364c9cbc3aa6a67300a664
     reference_id: str | None = None
     # 对中英文文本进行标准化，这可以提高数字的稳定性
     normalize: bool = True
@@ -32,7 +38,9 @@ class ServeTTSRequest(BaseModel):
 
 
 @register_provider_adapter(
-    "fishaudio_tts_api", "FishAudio TTS API", provider_type=ProviderType.TEXT_TO_SPEECH
+    "fishaudio_tts_api",
+    "FishAudio TTS API",
+    provider_type=ProviderType.TEXT_TO_SPEECH,
 )
 class ProviderFishAudioTTSAPI(TTSProvider):
     def __init__(
@@ -42,18 +50,19 @@ class ProviderFishAudioTTSAPI(TTSProvider):
     ) -> None:
         super().__init__(provider_config, provider_settings)
         self.chosen_api_key: str = provider_config.get("api_key", "")
+        self.reference_id: str = provider_config.get("fishaudio-tts-reference-id", "")
         self.character: str = provider_config.get("fishaudio-tts-character", "可莉")
         self.api_base: str = provider_config.get(
-            "api_base", "https://api.fish-audio.cn/v1"
+            "api_base",
+            "https://api.fish-audio.cn/v1",
         )
         self.headers = {
             "Authorization": f"Bearer {self.chosen_api_key}",
         }
-        self.set_model(provider_config.get("model", None))
+        self.set_model(provider_config.get("model"))
 
     async def _get_reference_id_by_character(self, character: str) -> str:
-        """
-        获取角色的reference_id
+        """获取角色的reference_id
 
         Args:
             character: 角色名称
@@ -63,13 +72,16 @@ class ProviderFishAudioTTSAPI(TTSProvider):
 
         exception:
             APIException: 获取语音角色列表为空
+
         """
         sort_options = ["score", "task_count", "created_at"]
         async with AsyncClient(base_url=self.api_base.replace("/v1", "")) as client:
             for sort_by in sort_options:
                 params = {"title": character, "sort_by": sort_by}
                 response = await client.get(
-                    "/model", params=params, headers=self.headers
+                    "/model",
+                    params=params,
+                    headers=self.headers,
                 )
                 resp_data = response.json()
                 if resp_data["total"] == 0:
@@ -79,15 +91,48 @@ class ProviderFishAudioTTSAPI(TTSProvider):
                         return item["_id"]
             return None
 
+    def _validate_reference_id(self, reference_id: str) -> bool:
+        """验证reference_id格式是否有效
+
+        Args:
+            reference_id: 参考模型ID
+
+        Returns:
+            bool: ID是否有效
+
+        """
+        if not reference_id or not reference_id.strip():
+            return False
+
+        # FishAudio的reference_id通常是32位十六进制字符串
+        # 例如: 626bb6d3f3364c9cbc3aa6a67300a664
+        pattern = r"^[a-fA-F0-9]{32}$"
+        return bool(re.match(pattern, reference_id.strip()))
+
     async def _generate_request(self, text: str) -> dict:
+        # 向前兼容逻辑：优先使用reference_id，如果没有则使用角色名称查询
+        if self.reference_id and self.reference_id.strip():
+            # 验证reference_id格式
+            if not self._validate_reference_id(self.reference_id):
+                raise ValueError(
+                    f"无效的FishAudio参考模型ID: '{self.reference_id}'. "
+                    f"请确保ID是32位十六进制字符串（例如: 626bb6d3f3364c9cbc3aa6a67300a664）。"
+                    f"您可以从 https://fish.audio/zh-CN/discovery 获取有效的模型ID。",
+                )
+            reference_id = self.reference_id.strip()
+        else:
+            # 回退到原来的角色名称查询逻辑
+            reference_id = await self._get_reference_id_by_character(self.character)
+
         return ServeTTSRequest(
             text=text,
             format="wav",
-            reference_id=await self._get_reference_id_by_character(self.character),
+            reference_id=reference_id,
         )
 
     async def get_audio(self, text: str) -> str:
-        path = f"data/temp/fishaudio_tts_api_{uuid.uuid4()}.wav"
+        temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+        path = os.path.join(temp_dir, f"fishaudio_tts_api_{uuid.uuid4()}.wav")
         self.headers["content-type"] = "application/msgpack"
         request = await self._generate_request(text)
         async with AsyncClient(base_url=self.api_base).stream(

astrbot/core/provider/sources/gemini_embedding_source.py

@@ -0,0 +1,61 @@
+from google import genai
+from google.genai import types
+from google.genai.errors import APIError
+
+from ..entities import ProviderType
+from ..provider import EmbeddingProvider
+from ..register import register_provider_adapter
+
+
+@register_provider_adapter(
+    "gemini_embedding",
+    "Google Gemini Embedding 提供商适配器",
+    provider_type=ProviderType.EMBEDDING,
+)
+class GeminiEmbeddingProvider(EmbeddingProvider):
+    def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.provider_config = provider_config
+        self.provider_settings = provider_settings
+
+        api_key: str = provider_config.get("embedding_api_key")
+        api_base: str = provider_config.get("embedding_api_base")
+        timeout: int = int(provider_config.get("timeout", 20))
+
+        http_options = types.HttpOptions(timeout=timeout * 1000)
+        if api_base:
+            api_base = api_base.removesuffix("/")
+            http_options.base_url = api_base
+
+        self.client = genai.Client(api_key=api_key, http_options=http_options).aio
+
+        self.model = provider_config.get(
+            "embedding_model",
+            "gemini-embedding-exp-03-07",
+        )
+
+    async def get_embedding(self, text: str) -> list[float]:
+        """获取文本的嵌入"""
+        try:
+            result = await self.client.models.embed_content(
+                model=self.model,
+                contents=text,
+            )
+            return result.embeddings[0].values
+        except APIError as e:
+            raise Exception(f"Gemini Embedding API请求失败: {e.message}")
+
+    async def get_embeddings(self, texts: list[str]) -> list[list[float]]:
+        """批量获取文本的嵌入"""
+        try:
+            result = await self.client.models.embed_content(
+                model=self.model,
+                contents=texts,
+            )
+            return [embedding.values for embedding in result.embeddings]
+        except APIError as e:
+            raise Exception(f"Gemini Embedding API批量请求失败: {e.message}")
+
+    def get_dim(self) -> int:
+        """获取向量的维度"""
+        return self.provider_config.get("embedding_dimensions", 768)