`0.0.10`

01OS/01OS/clients/base_device.py

@@ -28,13 +28,14 @@ from interpreter import interpreter # Just for code execution. Maybe we should l
 # In the future, I guess kernel watching code should be elsewhere? Somewhere server / client agnostic?
 from ..server.utils.kernel import put_kernel_messages_into_queue
 from ..server.utils.get_system_info import get_system_info
-from ..server.stt.stt import stt_wav
 from ..server.utils.process_utils import kill_process_tree
 
 from ..server.utils.logs import setup_logging
 from ..server.utils.logs import logger
 setup_logging()
 
+os.environ["STT_RUNNER"] = "server"
+os.environ["TTS_RUNNER"] = "server"
 
 from ..utils.accumulator import Accumulator
 
@@ -183,6 +184,10 @@ class Device:
             self.queue_all_captured_images()
 
             if os.getenv('STT_RUNNER') == "client":
+
+                # THIS DOES NOT WORK. We moved to this very cool stt_service, llm_service
+                # way of doing things. stt_wav is not a thing anymore. Needs work to work
+
                 # Run stt then send text
                 text = stt_wav(wav_path)
                 logger.debug(f"STT result: {text}")

01OS/01OS/server/server.py

@@ -213,6 +213,13 @@ async def listener():
             # Format will be bytes.wav or bytes.opus
             mime_type = "audio/" + message["format"].split(".")[1]
             audio_file_path = bytes_to_wav(message["content"], mime_type)
+
+            # For microphone debugging:
+            if False:
+                os.system(f"open {audio_file_path}")
+                import time
+                time.sleep(15)
+
             text = stt(audio_file_path)
             print(text)
             message = {"role": "user", "type": "message", "content": text}

01OS/01OS/server/utils/bytes_to_wav.py

@@ -45,7 +45,6 @@ def export_audio_to_wav_ffmpeg(audio: bytearray, mime_type: str) -> str:
         yield output_path
     finally:
         os.remove(input_path)
-        os.remove(output_path)
 
 def run_command(command):
     result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

01OS/pyproject.toml

@@ -4,7 +4,7 @@ packages = [
     {include = "01OS"},
 ]
 include = [".env.example", "start.py", "start.sh"]
-version = "0.0.9"
+version = "0.0.10"
 description = "The open-source language model computer"
 authors = ["Killian <killian@openinterpreter.com>"]
 license = "AGPL"
@@ -36,7 +36,7 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
-01 = "01OS.start:app"
+01 = "start:app"
 
 [tool.poetry.group.dev.dependencies]
 black = "^23.10.1"

01OS/start.py

@@ -5,7 +5,7 @@ import concurrent.futures
 import threading
 import os
 import importlib
-from .server.tunnel import create_tunnel
+create_tunnel = importlib.import_module(".server.tunnel", package="01OS").create_tunnel
 import signal
 app = typer.Typer()
 
@@ -56,7 +56,7 @@ def run(
     signal.signal(signal.SIGINT, handle_exit)
 
     if server:
-        from .server.server import main
+        main = importlib.import_module(".server.server", package="01OS").main
         loop = asyncio.new_event_loop()
         asyncio.set_event_loop(loop)
         server_thread = threading.Thread(target=loop.run_until_complete, args=(main(server_host, server_port, llm_service, model, llm_supports_vision, llm_supports_functions, context_window, max_tokens, temperature, tts_service, stt_service),))