Merge branch 'main' of https://github.com/OpenInterpreter/01 into react-native-app

README.md

@@ -8,6 +8,13 @@
     <br><a href="https://openinterpreter.com/01">Preorder the Light</a>‎ ‎ |‎ ‎ <a href="https://changes.openinterpreter.com">Get Updates</a>‎ ‎ |‎ ‎ <a href="https://01.openinterpreter.com/">Documentation</a><br>
 </p>
 
+<div align="center">
+
+ | [日本語](docs/README_JP.md) | [English](README.md) |
+
+</div>
+
+
 <br>
 
 ![OI-O1-BannerDemo-2](https://www.openinterpreter.com/OI-O1-BannerDemo-3.jpg)

docs/video_documentation/collection.md

@@ -0,0 +1,83 @@
+
+## For End Users
+[Announcment video](https://www.youtube.com/watch?v=jWr-WeXAdeI)
+[Wes Roth](https://www.youtube.com/@WesRoth)
+
+<details>
+<summary>Details</summary>
+
+No technical coverage
+
+</details>
+
+---
+
+[Announcment video](https://www.youtube.com/watch?v=JaBFT3fF2fk)
+[TheAIGRID](https://www.youtube.com/@TheAiGrid)
+
+<details>
+<summary>Details</summary>
+
+[here](https://youtu.be/JaBFT3fF2fk?si=8zPGO-U6WdLNnISw&t=656)
+mentions the current lack of windows support
+
+</details>
+
+---
+
+[Announcment video](https://www.youtube.com/watch?v=Q_p82HtBqoc)
+[Matt Berman](https://www.youtube.com/@matthew_berman)
+
+<details>
+<summary>Details</summary>
+
+[here](https://youtu.be/Q_p82HtBqoc?si=aAxjWZnBdwBbaOUr&t=579)
+Berman shows an install of 01 using conda and python 3.9
+in.. looks like linux.. shows how to get openai keys.
+
+</details>
+
+---
+
+[Announcment video](https://www.youtube.com/watch?v=q0dJ7T7au2Y)
+[WorldofAI](https://www.youtube.com/@intheworldofai)
+
+<details>
+<summary>Details</summary>
+
+<!-- Add details here -->
+
+</details>
+
+---
+
+[Breakdown video](https://www.youtube.com/watch?v=W-VwN0n4d9Y)
+[Mervin Praison](https://www.youtube.com/@MervinPraison)
+<details>
+<summary>Details</summary>
+- uses conda to install 01 and uses python 3.11 on linux.. maybe mac
+- 0:00 Introduction to Open Interpreter
+- 0:47 Creating Apps and Summarizing Documents
+- 1:20 Image Modifications and Game Creation
+- 2:55 Exploratory Data Analysis and Charting
+- 4:00 Server Log Analysis
+- 5:01 Image and Video Editing
+- 6:00 Composing Music with AI
+- 7:18 Calendar Management and Email Automation
+- 9:01 Integrating with Fast API and LM Studio
+
+</details>
+
+---
+
+[Breakdown video](https://www.youtube.com/watch?v=uyfoHQVgeY0)
+[Gary Explains](https://www.youtube.com/@GaryExplains)
+<br>for **open interpreter** not **01**
+<details>
+<summary>Details</summary>
+- 3:45 states that it will run on mac/linux and windows and requires python 3.10
+</details>
+
+## For Developers
+<BR>
+Coming soon

hardware/light/README.md

@@ -11,6 +11,7 @@ To set up audio recording + playback on the ESP32 (M5 Atom), do the following:
 - M5Atom by M5Stack [Reference](https://www.arduino.cc/reference/en/libraries/m5atom/)
 - WebSockets by Markus Sattler [Reference](https://www.arduino.cc/reference/en/libraries/websockets/)
 - AsyncTCP by dvarrel [Reference](https://github.com/dvarrel/AsyncTCP)
+- ESPAsyncWebServer by lacamera [Reference](https://github.com/lacamera/ESPAsyncWebServer)
 
 Finally, to flash the .ino to the board, connect the board to the USB port, select the port from the dropdown on the IDE, then select the M5Atom board (or M5Stack-ATOM if you have that). Click on upload to flash the board.
 

software/source/clients/base_device.py

@@ -3,6 +3,7 @@ from dotenv import load_dotenv
 load_dotenv()  # take environment variables from .env.
 
 import os
+import sys
 import asyncio
 import threading
 import pyaudio
@@ -58,7 +59,16 @@ CAMERA_WARMUP_SECONDS = float(os.getenv("CAMERA_WARMUP_SECONDS", 0))
 
 # Specify OS
 current_platform = get_system_info()
-is_win10 = lambda: platform.system() == "Windows" and "10" in platform.version()
+
+def is_win11():
+    return sys.getwindowsversion().build >= 22000
+
+def is_win10():
+    try:
+        return platform.system() == "Windows" and "10" in platform.version() and not is_win11()
+    except:
+        return False
+
 
 # Initialize PyAudio
 p = pyaudio.PyAudio()
@@ -72,6 +82,7 @@ class Device:
         self.captured_images = []
         self.audiosegments = []
         self.server_url = ""
+        self.ctrl_pressed = False
 
     def fetch_image_from_camera(self, camera_index=CAMERA_DEVICE_INDEX):
         """Captures an image from the specified camera device and saves it to a temporary file. Adds the image to the captured_images list."""
@@ -256,23 +267,39 @@ class Device:
     def on_press(self, key):
         """Detect spacebar press and Ctrl+C combination."""
         self.pressed_keys.add(key)  # Add the pressed key to the set
+        
 
         if keyboard.Key.space in self.pressed_keys:
             self.toggle_recording(True)
-        elif {keyboard.Key.ctrl, keyboard.KeyCode.from_char("c")} <= self.pressed_keys:
+        elif {keyboard.Key.ctrl, keyboard.KeyCode.from_char('c')} <= self.pressed_keys:
             logger.info("Ctrl+C pressed. Exiting...")
             kill_process_tree()
             os._exit(0)
+        
+        # Windows alternative to the above
+        if key == keyboard.Key.ctrl_l:
+            self.ctrl_pressed = True
+            
+        try:
+            if key.vk == 67 and self.ctrl_pressed:
+                logger.info("Ctrl+C pressed. Exiting...")
+                kill_process_tree()
+                os._exit(0)
+        # For non-character keys
+        except:
+            pass
+
+
 
     def on_release(self, key):
         """Detect spacebar release and 'c' key press for camera, and handle key release."""
-        self.pressed_keys.discard(
-            key
-        )  # Remove the released key from the key press tracking set
+        self.pressed_keys.discard(key)  # Remove the released key from the key press tracking set
 
+        if key == keyboard.Key.ctrl_l:
+            self.ctrl_pressed = False
         if key == keyboard.Key.space:
             self.toggle_recording(False)
-        elif CAMERA_ENABLED and key == keyboard.KeyCode.from_char("c"):
+        elif CAMERA_ENABLED and key == keyboard.KeyCode.from_char('c'):
             self.fetch_image_from_camera()
 
     async def message_sender(self, websocket):
@@ -342,7 +369,7 @@ class Device:
                         code = message["content"]
                         result = interpreter.computer.run(language, code)
                         send_queue.put(result)
-
+                        
         if is_win10():
             logger.info("Windows 10 detected")
             # Workaround for Windows 10 not latching to the websocket server.

software/source/server/server.py

@@ -355,7 +355,7 @@ async def listener(mobile: bool):
                         json.dump(interpreter.messages, file, indent=4)
 
                     # TODO: is triggering seemingly randomly
-                    # logger.info("New user message recieved. Breaking.")
+                    # logger.info("New user message received. Breaking.")
                     # break
 
                 # Also check if there's any new computer messages
@@ -363,7 +363,7 @@ async def listener(mobile: bool):
                     with open(conversation_history_path, "w") as file:
                         json.dump(interpreter.messages, file, indent=4)
 
-                    logger.info("New computer message recieved. Breaking.")
+                    logger.info("New computer message received. Breaking.")
                     break
         except:
             traceback.print_exc()

software/source/server/services/stt/local-whisper/stt.py

@@ -156,7 +156,7 @@ def stt_wav(service_directory, wav_file_path: str):
         temp_dir, f"output_stt_{datetime.now().strftime('%Y%m%d%H%M%S%f')}.wav"
     )
     ffmpeg.input(wav_file_path).output(
-        output_path, acodec="pcm_s16le", ac=1, ar="16k"
+        output_path, acodec="pcm_s16le", ac=1, ar="16k", loglevel="panic"
     ).run()
     try:
         transcript = get_transcription_file(service_directory, output_path)

software/source/server/utils/kernel.py

@@ -5,12 +5,17 @@ load_dotenv()  # take environment variables from .env.
 import asyncio
 import subprocess
 import platform
+import os
+import shutil
 
 from .logs import setup_logging
 from .logs import logger
 
 setup_logging()
 
+# dmesg process created at boot time
+dmesg_proc = None
+
 
 def get_kernel_messages():
     """
@@ -25,12 +30,37 @@ def get_kernel_messages():
         output, _ = process.communicate()
         return output.decode("utf-8")
     elif current_platform == "Linux":
-        with open("/var/log/dmesg", "r") as file:
+        log_path = get_dmesg_log_path()
+        with open(log_path, 'r') as file:
             return file.read()
     else:
         logger.info("Unsupported platform.")
 
 
+def get_dmesg_log_path():
+    """
+    Check for the existence of a readable dmesg log file and return its path.
+    Create an accessible path if not found.
+    """
+    if os.access('/var/log/dmesg', os.F_OK | os.R_OK):
+        return '/var/log/dmesg'
+
+    global dmesg_proc
+    dmesg_log_path = '/tmp/dmesg'
+    if dmesg_proc:
+        return dmesg_log_path
+
+    logger.info("Created /tmp/dmesg.")
+    subprocess.run(['touch', dmesg_log_path])
+    dmesg_path = shutil.which('dmesg')
+    if dmesg_path:
+        logger.info(f"Writing to {dmesg_log_path} from dmesg.")
+        dmesg_proc = subprocess.Popen([dmesg_path, '--follow'], text=True, stdout=subprocess.PIPE)
+        subprocess.Popen(['tee', dmesg_log_path], text=True, stdin=dmesg_proc.stdout, stdout=subprocess.DEVNULL)
+    
+    return dmesg_log_path
+
+
 def custom_filter(message):
     # Check for {TO_INTERPRETER{ message here }TO_INTERPRETER} pattern
     if "{TO_INTERPRETER{" in message and "}TO_INTERPRETER}" in message:

software/source/server/utils/process_utils.py

@@ -7,7 +7,11 @@ def kill_process_tree():
     pid = os.getpid()  # Get the current process ID
     try:
         # Send SIGTERM to the entire process group to ensure all processes are targeted
-        os.killpg(os.getpgid(pid), signal.SIGKILL)
+        try:
+            os.killpg(os.getpgid(pid), signal.SIGKILL)
+        # Windows implementation
+        except AttributeError:
+            os.kill(pid, signal.SIGTERM)
         parent = psutil.Process(pid)
         children = parent.children(recursive=True)
         for child in children:

software/start.py

@@ -127,6 +127,10 @@ def _run(
         # llm_service = "llamafile"
         stt_service = "local-whisper"
         select_local_model()
+        
+    system_type = platform.system()
+    if system_type == "Windows":
+        server_host = "localhost"
 
     if not server_url:
         server_url = f"{server_host}:{server_port}"
@@ -134,6 +138,8 @@ def _run(
     if not server and not client:
         server = True
         client = True
+        
+    
 
     def handle_exit(signum, frame):
         os._exit(0)