Merge branch 'master' into security-and-robustness-improvements

.env.template

@@ -2,13 +2,14 @@ PINECONE_API_KEY=your-pinecone-api-key
 PINECONE_ENV=your-pinecone-region
 OPENAI_API_KEY=your-openai-api-key
 ELEVENLABS_API_KEY=your-elevenlabs-api-key
-SMART_LLM_MODEL="gpt-4"
+SMART_LLM_MODEL=gpt-4
-FAST_LLM_MODEL="gpt-3.5-turbo"
+FAST_LLM_MODEL=gpt-3.5-turbo
 GOOGLE_API_KEY=
 CUSTOM_SEARCH_ENGINE_ID=
 USE_AZURE=False
-OPENAI_API_BASE=your-base-url-for-azure
+OPENAI_AZURE_API_BASE=your-base-url-for-azure
-OPENAI_API_VERSION=api-version-for-azure
+OPENAI_AZURE_API_VERSION=api-version-for-azure
-OPENAI_DEPLOYMENT_ID=deployment-id-for-azure
+OPENAI_AZURE_DEPLOYMENT_ID=deployment-id-for-azure
 IMAGE_PROVIDER=dalle
 HUGGINGFACE_API_TOKEN=
+USE_MAC_OS_TTS=False

.gitignore

@@ -12,3 +12,4 @@ outputs/*
 ai_settings.yaml
 .vscode
 auto-gpt.json
+log.txt

README.md

@@ -59,7 +59,7 @@ Your support is greatly appreciated
 ## 📋 Requirements
 - [Python 3.8 or later](https://www.tutorialspoint.com/how-to-install-python-in-windows)
 - OpenAI API key
-- PINECONE API key
+- [PINECONE API key](https://www.pinecone.io/)
 
 Optional:
 - ElevenLabs Key (If you want the AI to speak)
@@ -92,8 +92,8 @@ pip install -r requirements.txt
 
 4. Rename `.env.template` to `.env` and fill in your `OPENAI_API_KEY`. If you plan to use Speech Mode, fill in your `ELEVEN_LABS_API_KEY` as well.
   - Obtain your OpenAI API key from: https://platform.openai.com/account/api-keys.
-  - Obtain your ElevenLabs API key from: https://beta.elevenlabs.io. You can view your xi-api-key using the "Profile" tab on the website.
+  - Obtain your ElevenLabs API key from: https://elevenlabs.io. You can view your xi-api-key using the "Profile" tab on the website.
-  - If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and provide the `OPENAI_API_BASE`, `OPENAI_API_VERSION` and `OPENAI_DEPLOYMENT_ID` values as explained here: https://pypi.org/project/openai/ in the `Microsoft Azure Endpoints` section
+  - If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and provide the `OPENAI_AZURE_API_BASE`, `OPENAI_AZURE_API_VERSION` and `OPENAI_AZURE_DEPLOYMENT_ID` values as explained here: https://pypi.org/project/openai/ in the `Microsoft Azure Endpoints` section
 
 ## 🔧 Usage
 
@@ -179,8 +179,7 @@ MEMORY_INDEX=whatever
 
 ## 🌲 Pinecone API Key Setup
 
-Pinecone enable a vector based memory so a vast memory can be stored and only relevant memories
+Pinecone enables the storage of vast amounts of vector-based memory, allowing for only relevant memories to be loaded for the agent at any given time.
-are loaded for the agent at any given time.
 
 1. Go to app.pinecone.io and make an account if you don't already have one.
 2. Choose the `Starter` plan to avoid being charged.

scripts/ai_config.py

@@ -92,4 +92,3 @@ class AIConfig:
 
         full_prompt += f"\n\n{data.load_prompt()}"
         return full_prompt
-

scripts/browse.py

@@ -27,12 +27,21 @@ def make_request(url, timeout=10):
     except requests.exceptions.RequestException as e:
         return "Error: " + str(e)
 
+# Define and check for local file address prefixes
+def check_local_file_access(url):
+    local_prefixes = ['file:///', 'file://localhost', 'http://localhost', 'https://localhost']
+    return any(url.startswith(prefix) for prefix in local_prefixes)
+
 def scrape_text(url):
     """Scrape text from a webpage"""
     # Basic check if the URL is valid
     if not url.startswith('http'):
         return "Error: Invalid URL"
 
+    # Restrict access to local files
+    if check_local_file_access(url):
+        return "Error: Access to local files is restricted"
+    
     # Validate the input URL
     if not is_valid_url(url):
         # Sanitize the input URL

scripts/commands.py

@@ -42,9 +42,6 @@ def get_command(response):
         # Use an empty dictionary if 'args' field is not present in 'command' object
         arguments = command.get("args", {})
 
-        if not arguments:
-            arguments = {}
-
         return command_name, arguments
     except json.decoder.JSONDecodeError:
         return "Error:", "Invalid JSON"

scripts/config.py

@@ -33,7 +33,7 @@ class Config(metaclass=Singleton):
 
     def __init__(self):
         """Initialize the Config class"""
-        self.debug = False
+        self.debug_mode = False
         self.continuous_mode = False
         self.speak_mode = False
 
@@ -46,15 +46,18 @@ class Config(metaclass=Singleton):
         self.use_azure = False
         self.use_azure = os.getenv("USE_AZURE") == 'True'
         if self.use_azure:
-            self.openai_api_base = os.getenv("OPENAI_API_BASE")
+            self.openai_api_base = os.getenv("OPENAI_AZURE_API_BASE")
-            self.openai_api_version = os.getenv("OPENAI_API_VERSION")
+            self.openai_api_version = os.getenv("OPENAI_AZURE_API_VERSION")
-            self.openai_deployment_id = os.getenv("OPENAI_DEPLOYMENT_ID")
+            self.openai_deployment_id = os.getenv("OPENAI_AZURE_DEPLOYMENT_ID")
             openai.api_type = "azure"
             openai.api_base = self.openai_api_base
             openai.api_version = self.openai_api_version
 
         self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
 
+        self.use_mac_os_tts = False
+        self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
+        
         self.google_api_key = os.getenv("GOOGLE_API_KEY")
         self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
 
@@ -86,9 +89,6 @@ class Config(metaclass=Singleton):
         """Set the speak mode value."""
         self.speak_mode = value
 
-    def set_debug_mode(self, value: bool):
-        self.debug_mode = value
-
     def set_fast_llm_model(self, value: str):
         """Set the fast LLM model value."""
         self.fast_llm_model = value
@@ -131,4 +131,4 @@ class Config(metaclass=Singleton):
 
     def set_debug_mode(self, value: bool):
         """Set the debug mode value."""
-        self.debug = value
+        self.debug_mode = value

scripts/file_operations.py

@@ -24,7 +24,7 @@ def read_file(filename):
     """Read a file and return the contents"""
     try:
         filepath = safe_join(working_directory, filename)
-        with open(filepath, "r") as f:
+        with open(filepath, "r", encoding='utf-8') as f:
             content = f.read()
         return content
     except Exception as e:

scripts/json_utils.py

@@ -76,7 +76,7 @@ def balance_braces(json_string: str) -> str:
         json.loads(json_string)
         return json_string
     except json.JSONDecodeError as e:
-        raise e
+        pass
 
 
 def fix_invalid_escape(json_str: str, error_message: str) -> str:
@@ -88,7 +88,7 @@ def fix_invalid_escape(json_str: str, error_message: str) -> str:
             json.loads(json_str)
             return json_str
         except json.JSONDecodeError as e:
-            if cfg.debug:
+            if cfg.debug_mode:
                 print('json loads error - fix invalid escape', e)
             error_message = str(e)
     return json_str
@@ -103,12 +103,12 @@ def correct_json(json_str: str) -> str:
     """
 
     try:
-        if cfg.debug:
+        if cfg.debug_mode:
             print("json", json_str)
         json.loads(json_str)
         return json_str
     except json.JSONDecodeError as e:
-        if cfg.debug:
+        if cfg.debug_mode:
             print('json loads error', e)
         error_message = str(e)
         if error_message.startswith('Invalid \\escape'):
@@ -119,7 +119,7 @@ def correct_json(json_str: str) -> str:
                 json.loads(json_str)
                 return json_str
             except json.JSONDecodeError as e:
-                if cfg.debug:
+                if cfg.debug_mode:
                     print('json loads error - add quotes', e)
                 error_message = str(e)
         if balanced_str := balance_braces(json_str):

scripts/main.py

@@ -1,6 +1,7 @@
 import json
 import random
 import commands as cmd
+import utils
 from memory import get_memory
 import data
 import chat
@@ -8,17 +9,24 @@ from colorama import Fore, Style
 from spinner import Spinner
 import time
 import speak
-from enum import Enum, auto
-import sys
 from config import Config
 from json_parser import fix_and_parse_json
 from ai_config import AIConfig
 import traceback
 import yaml
 import argparse
+import logging
 
 cfg = Config()
 
+def configure_logging():
+    logging.basicConfig(filename='log.txt',
+                    filemode='a',
+                    format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
+                    datefmt='%H:%M:%S',
+                    level=logging.DEBUG)
+    return logging.getLogger('AutoGPT')
+
 def check_openai_api_key():
     """Check if the OpenAI API key is set in config.py or as an environment variable."""
     if not cfg.openai_api_key:
@@ -29,7 +37,6 @@ def check_openai_api_key():
         print("You can get your key from https://beta.openai.com/account/api-keys")
         exit(1)
 
-
 def print_to_console(
         title,
         title_color,
@@ -39,10 +46,12 @@ def print_to_console(
         max_typing_speed=0.01):
     """Prints text to the console with a typing effect"""
     global cfg
+    global logger
     if speak_text and cfg.speak_mode:
         speak.say_text(f"{title}. {content}")
     print(title_color + title + " " + Style.RESET_ALL, end="")
     if content:
+        logger.info(title + ': ' + content)
         if isinstance(content, list):
             content = " ".join(content)
         words = content.split()
@@ -133,12 +142,12 @@ def load_variables(config_file="config.yaml"):
 
     # Prompt the user for input if config file is missing or empty values
     if not ai_name:
-        ai_name = input("Name your AI: ")
+        ai_name = utils.clean_input("Name your AI: ")
         if ai_name == "":
             ai_name = "Entrepreneur-GPT"
 
     if not ai_role:
-        ai_role = input(f"{ai_name} is: ")
+        ai_role = utils.clean_input(f"{ai_name} is: ")
         if ai_role == "":
             ai_role = "an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth."
 
@@ -148,7 +157,7 @@ def load_variables(config_file="config.yaml"):
         print("Enter nothing to load defaults, enter nothing when finished.")
         ai_goals = []
         for i in range(5):
-            ai_goal = input(f"Goal {i+1}: ")
+            ai_goal = utils.clean_input(f"Goal {i+1}: ")
             if ai_goal == "":
                 break
             ai_goals.append(ai_goal)
@@ -161,7 +170,7 @@ def load_variables(config_file="config.yaml"):
         documents = yaml.dump(config, file)
 
     prompt = data.load_prompt()
-    prompt_start = """Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications."""
+    prompt_start = """Your decisions must always be made independently without seeking user assistance. Play to your strengths as a LLM and pursue simple strategies with no legal complications."""
 
     # Construct full prompt
     full_prompt = f"You are {ai_name}, {ai_role}\n{prompt_start}\n\nGOALS:\n\n"
@@ -181,7 +190,7 @@ def construct_prompt():
             Fore.GREEN,
             f"Would you like me to return to being {config.ai_name}?",
             speak_text=True)
-        should_continue = input(f"""Continue with the last settings?
+        should_continue = utils.clean_input(f"""Continue with the last settings?
 Name:  {config.ai_name}
 Role:  {config.ai_role}
 Goals: {config.ai_goals}
@@ -216,7 +225,7 @@ def prompt_user():
         "Name your AI: ",
         Fore.GREEN,
         "For example, 'Entrepreneur-GPT'")
-    ai_name = input("AI Name: ")
+    ai_name = utils.clean_input("AI Name: ")
     if ai_name == "":
         ai_name = "Entrepreneur-GPT"
 
@@ -231,7 +240,7 @@ def prompt_user():
         "Describe your AI's role: ",
         Fore.GREEN,
         "For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'")
-    ai_role = input(f"{ai_name} is: ")
+    ai_role = utils.clean_input(f"{ai_name} is: ")
     if ai_role == "":
         ai_role = "an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth."
 
@@ -243,7 +252,7 @@ def prompt_user():
     print("Enter nothing to load defaults, enter nothing when finished.", flush=True)
     ai_goals = []
     for i in range(5):
-        ai_goal = input(f"{Fore.LIGHTBLUE_EX}Goal{Style.RESET_ALL} {i+1}: ")
+        ai_goal = utils.clean_input(f"{Fore.LIGHTBLUE_EX}Goal{Style.RESET_ALL} {i+1}: ")
         if ai_goal == "":
             break
         ai_goals.append(ai_goal)
@@ -279,22 +288,16 @@ def parse_arguments():
         print_to_console("Speak Mode: ", Fore.GREEN, "ENABLED")
         cfg.set_speak_mode(True)
 
-    if args.debug:
-        print_to_console("Debug Mode: ", Fore.GREEN, "ENABLED")
-        cfg.set_debug_mode(True)        
-
     if args.gpt3only:
         print_to_console("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED")
         cfg.set_smart_llm_model(cfg.fast_llm_model)
 
-    if args.debug:
-        print_to_console("Debug Mode: ", Fore.GREEN, "ENABLED")
-        cfg.set_debug_mode(True)
 
 
 # TODO: fill in llm values here
 check_openai_api_key()
 cfg = Config()
+logger = configure_logging()
 parse_arguments()
 ai_name = ""
 prompt = construct_prompt()
@@ -344,7 +347,7 @@ while True:
             f"Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for {ai_name}...",
             flush=True)
         while True:
-            console_input = input(Fore.MAGENTA + "Input:" + Style.RESET_ALL)
+            console_input = utils.clean_input(Fore.MAGENTA + "Input:" + Style.RESET_ALL)
             if console_input.lower() == "y":
                 user_input = "GENERATE NEXT COMMAND JSON"
                 break
@@ -405,4 +408,3 @@ while True:
             chat.create_chat_message(
                 "system", "Unable to execute command"))
         print_to_console("SYSTEM: ", Fore.YELLOW, "Unable to execute command")
-

scripts/speak.py

@@ -4,6 +4,8 @@ import requests
 from config import Config
 cfg = Config()
 import gtts
+import threading
+from threading import Lock, Semaphore
 
 
 # TODO: Nicer names for these ids
@@ -14,6 +16,9 @@ tts_headers = {
     "xi-api-key": cfg.elevenlabs_api_key
 }
 
+mutex_lock = Lock() # Ensure only one sound is played at a time
+queue_semaphore = Semaphore(1) # The amount of sounds to queue before blocking the main thread
+
 def eleven_labs_speech(text, voice_index=0):
     """Speak text using elevenlabs.io's API"""
     tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
@@ -23,9 +28,10 @@ def eleven_labs_speech(text, voice_index=0):
         tts_url, headers=tts_headers, json=formatted_message)
 
     if response.status_code == 200:
+        with mutex_lock:
             with open("speech.mpeg", "wb") as f:
                 f.write(response.content)
-        playsound("speech.mpeg")
+            playsound("speech.mpeg", True)
             os.remove("speech.mpeg")
         return True
     else:
@@ -35,15 +41,29 @@ def eleven_labs_speech(text, voice_index=0):
 
 def gtts_speech(text):
     tts = gtts.gTTS(text)
+    with mutex_lock:
         tts.save("speech.mp3")
-    playsound("speech.mp3")
+        playsound("speech.mp3", True)
         os.remove("speech.mp3")
 
+def macos_tts_speech(text):
+    os.system(f'say "{text}"')
+
 def say_text(text, voice_index=0):
+
+    def speak():
         if not cfg.elevenlabs_api_key:
+            if cfg.use_mac_os_tts == 'True':
+                macos_tts_speech(text)
+            else:
                 gtts_speech(text)
         else:
             success = eleven_labs_speech(text, voice_index)
             if not success:
                 gtts_speech(text)
         
+        queue_semaphore.release()
+
+    queue_semaphore.acquire(True)
+    thread = threading.Thread(target=speak)
+    thread.start()

scripts/utils.py

@@ -0,0 +1,8 @@
+def clean_input(prompt: str=''):
+    try:
+        return input(prompt)
+    except KeyboardInterrupt:
+        print("You interrupted Auto-GPT")
+        print("Quitting...")
+        exit(0)
+