xiaogpt 3.2__tar.gz → 3.4__tar.gz

{xiaogpt-3.2 → xiaogpt-3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xiaogpt
-Version: 3.2
+Version: 3.4
 Summary: Play ChatGPT or other LLM with xiaomi AI speaker
 Author-Email: yihong0618 <zouzou0208@gmail.com>
 License: MIT
@@ -28,7 +28,7 @@ Requires-Dist: langchain-community>=0.0.38
 Requires-Dist: lingua-language-detector>=2.0.2; python_version < "3.13"
 Provides-Extra: locked
 Requires-Dist: aiohappyeyeballs==2.4.0; extra == "locked"
-Requires-Dist: aiohttp==3.10.5; extra == "locked"
+Requires-Dist: aiohttp==3.10.10; extra == "locked"
 Requires-Dist: aiosignal==1.3.1; extra == "locked"
 Requires-Dist: annotated-types==0.6.0; extra == "locked"
 Requires-Dist: anyio==4.3.0; extra == "locked"
@@ -47,14 +47,14 @@ Requires-Dist: distro==1.9.0; extra == "locked"
 Requires-Dist: edge-tts==6.1.10; extra == "locked"
 Requires-Dist: exceptiongroup==1.2.0; python_version < "3.11" and extra == "locked"
 Requires-Dist: frozenlist==1.4.1; extra == "locked"
-Requires-Dist: google-ai-generativelanguage==0.6.9; extra == "locked"
+Requires-Dist: google-ai-generativelanguage==0.6.10; extra == "locked"
 Requires-Dist: google-api-core==2.15.0; extra == "locked"
 Requires-Dist: google-api-core[grpc]==2.15.0; extra == "locked"
 Requires-Dist: google-api-python-client==2.125.0; extra == "locked"
 Requires-Dist: google-auth==2.26.1; extra == "locked"
 Requires-Dist: google-auth-httplib2==0.2.0; extra == "locked"
 Requires-Dist: google-cloud-texttospeech==2.16.3; extra == "locked"
-Requires-Dist: google-generativeai==0.8.1; extra == "locked"
+Requires-Dist: google-generativeai==0.8.3; extra == "locked"
 Requires-Dist: google-search-results==2.4.2; extra == "locked"
 Requires-Dist: googleapis-common-protos==1.62.0; extra == "locked"
 Requires-Dist: greenlet==3.0.3; (platform_machine == "win32" or platform_machine == "WIN32" or platform_machine == "AMD64" or platform_machine == "amd64" or platform_machine == "x86_64" or platform_machine == "ppc64le" or platform_machine == "aarch64") and extra == "locked"
@@ -65,16 +65,17 @@ Requires-Dist: h11==0.14.0; extra == "locked"
 Requires-Dist: httpcore==1.0.5; extra == "locked"
 Requires-Dist: httplib2==0.22.0; extra == "locked"
 Requires-Dist: httpx==0.27.2; extra == "locked"
+Requires-Dist: httpx-ws==0.6.2; extra == "locked"
 Requires-Dist: httpx[socks]==0.27.2; extra == "locked"
 Requires-Dist: idna==3.7; extra == "locked"
 Requires-Dist: jiter==0.5.0; extra == "locked"
 Requires-Dist: jsonpatch==1.33; extra == "locked"
 Requires-Dist: jsonpointer==2.4; extra == "locked"
-Requires-Dist: langchain==0.3.0; extra == "locked"
-Requires-Dist: langchain-community==0.3.0; extra == "locked"
-Requires-Dist: langchain-core==0.3.0; extra == "locked"
+Requires-Dist: langchain==0.3.3; extra == "locked"
+Requires-Dist: langchain-community==0.3.2; extra == "locked"
+Requires-Dist: langchain-core==0.3.10; extra == "locked"
 Requires-Dist: langchain-text-splitters==0.3.0; extra == "locked"
-Requires-Dist: langsmith==0.1.120; extra == "locked"
+Requires-Dist: langsmith==0.1.133; extra == "locked"
 Requires-Dist: lingua-language-detector==2.0.2; python_version < "3.13" and extra == "locked"
 Requires-Dist: markdown-it-py==3.0.0; extra == "locked"
 Requires-Dist: marshmallow==3.20.1; extra == "locked"
@@ -85,10 +86,11 @@ Requires-Dist: mutagen==1.47.0; extra == "locked"
 Requires-Dist: mypy-extensions==1.0.0; extra == "locked"
 Requires-Dist: numexpr==2.10.1; extra == "locked"
 Requires-Dist: numpy==1.26.3; extra == "locked"
-Requires-Dist: openai==1.45.0; extra == "locked"
+Requires-Dist: openai==1.51.2; extra == "locked"
 Requires-Dist: orjson==3.10.0; extra == "locked"
 Requires-Dist: ormsgpack==1.5.0; extra == "locked"
 Requires-Dist: packaging==23.2; extra == "locked"
+Requires-Dist: propcache==0.2.0; extra == "locked"
 Requires-Dist: proto-plus==1.23.0; extra == "locked"
 Requires-Dist: protobuf==4.25.1; extra == "locked"
 Requires-Dist: pyasn1==0.5.1; extra == "locked"
@@ -102,22 +104,23 @@ Requires-Dist: pyparsing==3.1.2; python_version > "3.0" and extra == "locked"
 Requires-Dist: python-dotenv==1.0.1; extra == "locked"
 Requires-Dist: pyyaml==6.0.2; extra == "locked"
 Requires-Dist: requests==2.31.0; extra == "locked"
-Requires-Dist: rich==13.8.1; extra == "locked"
+Requires-Dist: requests-toolbelt==1.0.0; extra == "locked"
+Requires-Dist: rich==13.9.2; extra == "locked"
 Requires-Dist: rsa==4.9; extra == "locked"
 Requires-Dist: sniffio==1.3.0; extra == "locked"
 Requires-Dist: socksio==1.0.0; extra == "locked"
 Requires-Dist: soupsieve==2.5; extra == "locked"
 Requires-Dist: sqlalchemy==2.0.25; extra == "locked"
 Requires-Dist: tenacity==8.2.3; extra == "locked"
-Requires-Dist: tetos==0.3.1; extra == "locked"
+Requires-Dist: tetos==0.4.1; extra == "locked"
 Requires-Dist: tqdm==4.66.1; extra == "locked"
 Requires-Dist: typing-extensions==4.12.2; extra == "locked"
 Requires-Dist: typing-inspect==0.9.0; extra == "locked"
 Requires-Dist: uritemplate==4.1.1; extra == "locked"
 Requires-Dist: urllib3==2.1.0; extra == "locked"
 Requires-Dist: websocket-client==1.8.0; extra == "locked"
-Requires-Dist: websockets==12.0; extra == "locked"
-Requires-Dist: yarl==1.9.4; extra == "locked"
+Requires-Dist: wsproto==1.2.0; extra == "locked"
+Requires-Dist: yarl==1.14.0; extra == "locked"
 Requires-Dist: zhipuai==2.1.5.20230904; extra == "locked"
 Description-Content-Type: text/markdown
 

{xiaogpt-3.2 → xiaogpt-3.4}/pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
     "lingua-language-detector>=2.0.2; python_version < \"3.13\"",
 ]
 dynamic = []
-version = "3.2"
+version = "3.4"
 
 [project.license]
 text = "MIT"
@@ -45,7 +45,7 @@ xiaogpt = "xiaogpt.cli:main"
 [project.optional-dependencies]
 locked = [
     "aiohappyeyeballs==2.4.0",
-    "aiohttp==3.10.5",
+    "aiohttp==3.10.10",
     "aiosignal==1.3.1",
     "annotated-types==0.6.0",
     "anyio==4.3.0",
@@ -64,14 +64,14 @@ locked = [
     "edge-tts==6.1.10",
     "exceptiongroup==1.2.0 ; python_version < \"3.11\"",
     "frozenlist==1.4.1",
-    "google-ai-generativelanguage==0.6.9",
+    "google-ai-generativelanguage==0.6.10",
     "google-api-core==2.15.0",
     "google-api-core[grpc]==2.15.0",
     "google-api-python-client==2.125.0",
     "google-auth==2.26.1",
     "google-auth-httplib2==0.2.0",
     "google-cloud-texttospeech==2.16.3",
-    "google-generativeai==0.8.1",
+    "google-generativeai==0.8.3",
     "google-search-results==2.4.2",
     "googleapis-common-protos==1.62.0",
     "greenlet==3.0.3 ; platform_machine == \"win32\" or platform_machine == \"WIN32\" or platform_machine == \"AMD64\" or platform_machine == \"amd64\" or platform_machine == \"x86_64\" or platform_machine == \"ppc64le\" or platform_machine == \"aarch64\"",
@@ -82,16 +82,17 @@ locked = [
     "httpcore==1.0.5",
     "httplib2==0.22.0",
     "httpx==0.27.2",
+    "httpx-ws==0.6.2",
     "httpx[socks]==0.27.2",
     "idna==3.7",
     "jiter==0.5.0",
     "jsonpatch==1.33",
     "jsonpointer==2.4",
-    "langchain==0.3.0",
-    "langchain-community==0.3.0",
-    "langchain-core==0.3.0",
+    "langchain==0.3.3",
+    "langchain-community==0.3.2",
+    "langchain-core==0.3.10",
     "langchain-text-splitters==0.3.0",
-    "langsmith==0.1.120",
+    "langsmith==0.1.133",
     "lingua-language-detector==2.0.2 ; python_version < \"3.13\"",
     "markdown-it-py==3.0.0",
     "marshmallow==3.20.1",
@@ -102,10 +103,11 @@ locked = [
     "mypy-extensions==1.0.0",
     "numexpr==2.10.1",
     "numpy==1.26.3",
-    "openai==1.45.0",
+    "openai==1.51.2",
     "orjson==3.10.0",
     "ormsgpack==1.5.0",
     "packaging==23.2",
+    "propcache==0.2.0",
     "proto-plus==1.23.0",
     "protobuf==4.25.1",
     "pyasn1==0.5.1",
@@ -119,22 +121,23 @@ locked = [
     "python-dotenv==1.0.1",
     "pyyaml==6.0.2",
     "requests==2.31.0",
-    "rich==13.8.1",
+    "requests-toolbelt==1.0.0",
+    "rich==13.9.2",
     "rsa==4.9",
     "sniffio==1.3.0",
     "socksio==1.0.0",
     "soupsieve==2.5",
     "sqlalchemy==2.0.25",
     "tenacity==8.2.3",
-    "tetos==0.3.1",
+    "tetos==0.4.1",
     "tqdm==4.66.1",
     "typing-extensions==4.12.2",
     "typing-inspect==0.9.0",
     "uritemplate==4.1.1",
     "urllib3==2.1.0",
     "websocket-client==1.8.0",
-    "websockets==12.0",
-    "yarl==1.9.4",
+    "wsproto==1.2.0",
+    "yarl==1.14.0",
     "zhipuai==2.1.5.20230904",
 ]
 

xiaogpt-3.4/xiaogpt/tts/__init__.py

@@ -0,0 +1,6 @@
+from xiaogpt.tts.base import TTS
+from xiaogpt.tts.file import TetosFileTTS
+from xiaogpt.tts.live import TetosLiveTTS
+from xiaogpt.tts.mi import MiTTS
+
+__all__ = ["TTS", "TetosFileTTS", "MiTTS", "TetosLiveTTS"]

xiaogpt-3.4/xiaogpt/tts/base.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+import abc
+import asyncio
+import json
+import logging
+from typing import TYPE_CHECKING, AsyncIterator
+
+if TYPE_CHECKING:
+    from typing import TypeVar
+
+    from miservice import MiNAService
+
+    from xiaogpt.config import Config
+
+    T = TypeVar("T", bound="TTS")
+
+logger = logging.getLogger(__name__)
+
+
+class TTS(abc.ABC):
+    """An abstract base class for Text-to-Speech models."""
+
+    def __init__(
+        self, mina_service: MiNAService, device_id: str, config: Config
+    ) -> None:
+        self.mina_service = mina_service
+        self.device_id = device_id
+        self.config = config
+
+    async def wait_for_duration(self, duration: float) -> None:
+        """Wait for the specified duration."""
+        await asyncio.sleep(duration)
+        while True:
+            if not await self.get_if_xiaoai_is_playing():
+                break
+            await asyncio.sleep(1)
+
+    async def get_if_xiaoai_is_playing(self) -> bool:
+        playing_info = await self.mina_service.player_get_status(self.device_id)
+        # WTF xiaomi api
+        is_playing = (
+            json.loads(playing_info.get("data", {}).get("info", "{}")).get("status", -1)
+            == 1
+        )
+        return is_playing
+
+    @abc.abstractmethod
+    async def synthesize(self, lang: str, text_stream: AsyncIterator[str]) -> None:
+        """Synthesize speech from a stream of text."""
+        raise NotImplementedError

xiaogpt-3.2/xiaogpt/tts/base.py → xiaogpt-3.4/xiaogpt/tts/file.py

@@ -1,10 +1,5 @@
-from __future__ import annotations
-
-import abc
 import asyncio
 import functools
-import json
-import logging
 import os
 import random
 import socket
@@ -12,53 +7,13 @@ import tempfile
 import threading
 from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
-from typing import TYPE_CHECKING, AsyncIterator
-
-from xiaogpt.utils import get_hostname
-
-if TYPE_CHECKING:
-    from typing import TypeVar
-
-    from miservice import MiNAService
-
-    from xiaogpt.config import Config
-
-    T = TypeVar("T", bound="TTS")
-
-logger = logging.getLogger(__name__)
-
-
-class TTS(abc.ABC):
-    """An abstract base class for Text-to-Speech models."""
-
-    def __init__(
-        self, mina_service: MiNAService, device_id: str, config: Config
-    ) -> None:
-        self.mina_service = mina_service
-        self.device_id = device_id
-        self.config = config
+from typing import AsyncIterator
 
-    async def wait_for_duration(self, duration: float) -> None:
-        """Wait for the specified duration."""
-        await asyncio.sleep(duration)
-        while True:
-            if not await self.get_if_xiaoai_is_playing():
-                break
-            await asyncio.sleep(1)
-
-    async def get_if_xiaoai_is_playing(self):
-        playing_info = await self.mina_service.player_get_status(self.device_id)
-        # WTF xiaomi api
-        is_playing = (
-            json.loads(playing_info.get("data", {}).get("info", "{}")).get("status", -1)
-            == 1
-        )
-        return is_playing
+from miservice import MiNAService
 
-    @abc.abstractmethod
-    async def synthesize(self, lang: str, text_stream: AsyncIterator[str]) -> None:
-        """Synthesize speech from a stream of text."""
-        raise NotImplementedError
+from xiaogpt.config import Config
+from xiaogpt.tts.base import TTS, logger
+from xiaogpt.utils import get_hostname
 
 
 class HTTPRequestHandler(SimpleHTTPRequestHandler):
@@ -76,23 +31,31 @@ class HTTPRequestHandler(SimpleHTTPRequestHandler):
             pass
 
 
-class AudioFileTTS(TTS):
+class TetosFileTTS(TTS):
     """A TTS model that generates audio files locally and plays them via URL."""
 
     def __init__(
         self, mina_service: MiNAService, device_id: str, config: Config
     ) -> None:
+        from tetos import get_speaker
+
         super().__init__(mina_service, device_id, config)
         self.dirname = tempfile.TemporaryDirectory(prefix="xiaogpt-tts-")
         self._start_http_server()
 
-    @abc.abstractmethod
+        assert config.tts and config.tts != "mi"
+        speaker_cls = get_speaker(config.tts)
+        try:
+            self.speaker = speaker_cls(**config.tts_options)
+        except TypeError as e:
+            raise ValueError(f"{e}. Please add them via `tts_options` config") from e
+
     async def make_audio_file(self, lang: str, text: str) -> tuple[Path, float]:
-        """Synthesize speech from text and save it to a file.
-        Return the file path and the duration of the audio in seconds.
-        The file path must be relative to the self.dirname.
-        """
-        raise NotImplementedError
+        output_file = tempfile.NamedTemporaryFile(
+            suffix=".mp3", mode="wb", delete=False, dir=self.dirname.name
+        )
+        duration = await self.speaker.synthesize(text, output_file.name, lang=lang)
+        return Path(output_file.name), duration
 
     async def synthesize(self, lang: str, text_stream: AsyncIterator[str]) -> None:
         queue: asyncio.Queue[tuple[str, float]] = asyncio.Queue()

xiaogpt-3.4/xiaogpt/tts/live.py

@@ -0,0 +1,98 @@
+import asyncio
+import os
+import queue
+import random
+import threading
+import uuid
+from functools import lru_cache
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from typing import AsyncIterator
+
+from miservice import MiNAService
+
+from xiaogpt.config import Config
+from xiaogpt.tts.base import TTS, logger
+from xiaogpt.utils import get_hostname
+
+
+@lru_cache(maxsize=64)
+def get_queue(key: str) -> queue.Queue[bytes]:
+    return queue.Queue()
+
+
+class HTTPRequestHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        self.send_response(200)
+        self.send_header("Content-type", "audio/mpeg")
+        self.end_headers()
+        key = self.path.split("/")[-1]
+        queue = get_queue(key)
+        while True:
+            chunk = queue.get()
+            if chunk == b"":
+                break
+            self.wfile.write(chunk)
+
+    def log_message(self, format, *args):
+        logger.debug(f"{self.address_string()} - {format}", *args)
+
+    def log_error(self, format, *args):
+        logger.error(f"{self.address_string()} - {format}", *args)
+
+
+class TetosLiveTTS(TTS):
+    """A TTS model that generates audio in real-time."""
+
+    def __init__(
+        self, mina_service: MiNAService, device_id: str, config: Config
+    ) -> None:
+        from tetos import get_speaker
+
+        super().__init__(mina_service, device_id, config)
+        self._start_http_server()
+
+        assert config.tts and config.tts != "mi"
+        speaker_cls = get_speaker(config.tts)
+        try:
+            self.speaker = speaker_cls(**config.tts_options)
+        except TypeError as e:
+            raise ValueError(f"{e}. Please add them via `tts_options` config") from e
+        if not hasattr(self.speaker, "live"):
+            raise ValueError(f"{config.tts} Speaker does not support live synthesis")
+
+    async def synthesize(self, lang: str, text_stream: AsyncIterator[str]) -> None:
+        key = str(uuid.uuid4())
+        queue = get_queue(key)
+
+        async def worker():
+            async for chunk in self.speaker.live(text_stream, lang):
+                queue.put(chunk)
+            queue.put(b"")
+
+        task = asyncio.create_task(worker())
+        await self.mina_service.play_by_url(
+            self.device_id, f"http://{self.hostname}:{self.port}/{key}", _type=1
+        )
+
+        while True:
+            if await self.get_if_xiaoai_is_playing():
+                await asyncio.sleep(1)
+            else:
+                break
+        await task
+
+    def _start_http_server(self):
+        # set the port range
+        port_range = range(8050, 8090)
+        # get a random port from the range
+        self.port = int(os.getenv("XIAOGPT_PORT", random.choice(port_range)))
+        # create the server
+        handler = HTTPRequestHandler
+        httpd = ThreadingHTTPServer(("", self.port), handler)
+        # start the server in a new thread
+        server_thread = threading.Thread(target=httpd.serve_forever)
+        server_thread.daemon = True
+        server_thread.start()
+
+        self.hostname = get_hostname()
+        logger.info(f"Serving on {self.hostname}:{self.port}")

{xiaogpt-3.2 → xiaogpt-3.4}/xiaogpt/xiaogpt.py

@@ -23,7 +23,8 @@ from xiaogpt.config import (
     WAKEUP_KEYWORD,
     Config,
 )
-from xiaogpt.tts import TTS, MiTTS, TetosTTS
+from xiaogpt.tts import TTS, MiTTS, TetosFileTTS
+from xiaogpt.tts.live import TetosLiveTTS
 from xiaogpt.utils import detect_language, parse_cookie_string
 
 EOF = object()
@@ -260,8 +261,10 @@ class MiGPT:
     def tts(self) -> TTS:
         if self.config.tts == "mi":
             return MiTTS(self.mina_service, self.device_id, self.config)
+        elif self.config.tts == "fish":
+            return TetosLiveTTS(self.mina_service, self.device_id, self.config)
         else:
-            return TetosTTS(self.mina_service, self.device_id, self.config)
+            return TetosFileTTS(self.mina_service, self.device_id, self.config)
 
     async def wait_for_tts_finish(self):
         while True:
@@ -274,7 +277,7 @@ class MiGPT:
         message = message.strip().replace(" ", "--")
         message = message.replace("\n", "，")
         message = message.replace('"', "，")
-        message = message.replace('*', "")
+        message = message.replace("*", "")
         return message
 
     async def ask_gpt(self, query: str) -> AsyncIterator[str]:

xiaogpt-3.2/xiaogpt/tts/__init__.py

@@ -1,5 +0,0 @@
-from xiaogpt.tts.base import TTS
-from xiaogpt.tts.mi import MiTTS
-from xiaogpt.tts.tetos import TetosTTS
-
-__all__ = ["TTS", "TetosTTS", "MiTTS"]

xiaogpt-3.2/xiaogpt/tts/tetos.py

@@ -1,31 +0,0 @@
-from __future__ import annotations
-
-import tempfile
-from pathlib import Path
-
-from miservice import MiNAService
-
-from xiaogpt.config import Config
-from xiaogpt.tts.base import AudioFileTTS
-
-
-class TetosTTS(AudioFileTTS):
-    def __init__(
-        self, mina_service: MiNAService, device_id: str, config: Config
-    ) -> None:
-        from tetos import get_speaker
-
-        super().__init__(mina_service, device_id, config)
-        assert config.tts and config.tts != "mi"
-        speaker_cls = get_speaker(config.tts)
-        try:
-            self.speaker = speaker_cls(**config.tts_options)
-        except TypeError as e:
-            raise ValueError(f"{e}. Please add them via `tts_options` config") from e
-
-    async def make_audio_file(self, lang: str, text: str) -> tuple[Path, float]:
-        output_file = tempfile.NamedTemporaryFile(
-            suffix=".mp3", mode="wb", delete=False, dir=self.dirname.name
-        )
-        duration = await self.speaker.synthesize(text, output_file.name, lang=lang)
-        return Path(output_file.name), duration