Merge branch 'master' of github.com:Torantulino/Auto-GPT into shellcommands

.env.template

@@ -2,6 +2,8 @@ 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
+ELEVENLABS_VOICE_1_ID=your-voice-id
+ELEVENLABS_VOICE_2_ID=your-voice-id
 SMART_LLM_MODEL=gpt-4
 FAST_LLM_MODEL=gpt-3.5-turbo
 GOOGLE_API_KEY=

.github/PULL_REQUEST_TEMPLATE.md

@@ -23,10 +23,10 @@ By following these guidelines, your PRs are more likely to be merged quickly aft
 
 ### PR Quality Checklist
 - [ ] My pull request is atomic and focuses on a single change.
-- [ ] I have thouroughly tested my changes with multiple different prompts.
+- [ ] I have thoroughly tested my changes with multiple different prompts.
 - [ ] I have considered potential risks and mitigations for my changes.
 - [ ] I have documented my changes clearly and comprehensively.
-- [ ] I have not snuck in any "extra" small tweaks changes <!-- Submit these as seperate Pull Reqests, they are the easiest to merge! -->
+- [ ] I have not snuck in any "extra" small tweaks changes <!-- Submit these as separate Pull Reqests, they are the easiest to merge! -->
 
 <!-- If you haven't added tests, please explain why. If you have, check the appropriate box. If you've ensured your PR is atomic and well-documented, check the corresponding boxes. -->
 

.gitignore

@@ -7,9 +7,10 @@ package-lock.json
 auto_gpt_workspace/*
 *.mpeg
 .env
-venv/*
+*venv/*
 outputs/*
 ai_settings.yaml
 .vscode
+.idea/*
 auto-gpt.json
 log.txt

CONTRIBUTING.md

@@ -6,7 +6,7 @@ To contribute to this GitHub project, you can follow these steps:
 2. Clone the repository to your local machine using the following command:
 
 ```
-git clone https://github.com/Torantulino/Auto-GPT
+git clone https://github.com/<YOUR-GITHUB-USERNAME>/Auto-GPT
 ```
 3. Create a new branch for your changes using the following command:
 

README.md

@@ -3,7 +3,7 @@
 ![Twitter Follow](https://img.shields.io/twitter/follow/siggravitas?style=social)
 [![](https://dcbadge.vercel.app/api/server/PQ7VX6TY4t?style=flat)](https://discord.gg/PQ7VX6TY4t)
 
-Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, autonomously develops and manages businesses to increase net worth. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.
+Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM "thoughts", to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.
 
 ### Demo (30/03/2023):
 https://user-images.githubusercontent.com/22963551/228855501-2f5777cf-755b-4407-a643-c7299e5b6419.mp4
@@ -58,7 +58,7 @@ Your support is greatly appreciated
 
 ## 📋 Requirements
 - [Python 3.8 or later](https://www.tutorialspoint.com/how-to-install-python-in-windows)
-- OpenAI API key
+- [OpenAI API key](https://platform.openai.com/account/api-keys)
 - [PINECONE API key](https://www.pinecone.io/)
 
 Optional:
@@ -267,3 +267,8 @@ Stay up-to-date with the latest news, updates, and insights about Auto-GPT by fo
 
 We look forward to connecting with you and hearing your thoughts, ideas, and experiences with Auto-GPT. Join us on Twitter and let's explore the future of AI together!
 
+<p align="center">
+  <a href="https://star-history.com/#Torantulino/auto-gpt&Date">
+    <img src="https://api.star-history.com/svg?repos=Torantulino/auto-gpt&type=Date" alt="Star History Chart">
+  </a>
+</p>

scripts/agent_manager.py

@@ -13,7 +13,7 @@ def create_agent(task, prompt, model):
 
     messages = [{"role": "user", "content": prompt}, ]
 
-    # Start GTP3 instance
+    # Start GPT instance
     agent_reply = create_chat_completion(
         model=model,
         messages=messages,
@@ -41,7 +41,7 @@ def message_agent(key, message):
     # Add user message to message history before sending to agent
     messages.append({"role": "user", "content": message})
 
-    # Start GTP3 instance
+    # Start GPT instance
     agent_reply = create_chat_completion(
         model=model,
         messages=messages,

scripts/ai_config.py

@@ -42,7 +42,7 @@ class AIConfig:
            config_file (int): The path to the config yaml file. DEFAULT: "../ai_settings.yaml"
 
         Returns:
-            cls (object): A instance of given cls object
+            cls (object): An instance of given cls object
         """
 
         try:
@@ -80,7 +80,7 @@ class AIConfig:
             None
 
         Returns:
-            full_prompt (str): A string containing the intitial prompt for the user including the ai_name, ai_role and ai_goals.
+            full_prompt (str): A string containing the initial prompt for the user including the ai_name, ai_role and ai_goals.
         """
 
         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."""
@@ -92,4 +92,3 @@ class AIConfig:
 
         full_prompt += f"\n\n{data.load_prompt()}"
         return full_prompt
-

scripts/browse.py

@@ -15,7 +15,7 @@ def scrape_text(url):
     # Most 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"

scripts/chat.py

@@ -63,15 +63,15 @@ def chat_with_ai(
             """
             model = cfg.fast_llm_model # TODO: Change model from hardcode to argument
             # Reserve 1000 tokens for the response
-            
-            if cfg.debug:
+
+            if cfg.debug_mode:
                 print(f"Token limit: {token_limit}")
-                
+
             send_token_limit = token_limit - 1000
 
             relevant_memory = permanent_memory.get_relevant(str(full_message_history[-5:]), 10)
 
-            if cfg.debug:
+            if cfg.debug_mode:
                 print('Memory Stats: ', permanent_memory.get_stats())
 
             next_message_to_add_index, current_tokens_used, insertion_index, current_context = generate_context(
@@ -110,7 +110,7 @@ def chat_with_ai(
             # assert tokens_remaining >= 0, "Tokens remaining is negative. This should never happen, please submit a bug report at https://www.github.com/Torantulino/Auto-GPT"
 
             # Debug print the current context
-            if cfg.debug:
+            if cfg.debug_mode:
                 print(f"Token limit: {token_limit}")
                 print(f"Send Token Count: {current_tokens_used}")
                 print(f"Tokens remaining for response: {tokens_remaining}")
@@ -141,6 +141,6 @@ def chat_with_ai(
 
             return assistant_reply
         except openai.error.RateLimitError:
-            # TODO: WHen we switch to langchain, this is built in
+            # TODO: When we switch to langchain, this is built in
             print("Error: ", "API Rate Limit Reached. Waiting 10 seconds...")
             time.sleep(10)

scripts/commands.py

@@ -115,7 +115,7 @@ def execute_command(command_name, arguments):
         elif command_name == "task_complete":
             shutdown()
         else:
-            return f"Unknown command '{command_name}'. Please refer to the 'COMMANDS' list for availabe commands and only respond in the specified JSON format."
+            return f"Unknown command '{command_name}'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format."
     # All errors, return "Error: + error message"
     except Exception as e:
         return "Error: " + str(e)

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
 
@@ -56,6 +56,8 @@ class Config(metaclass=Singleton):
             openai.api_version = self.openai_api_version
 
         self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
+        self.elevenlabs_voice_1_id = os.getenv("ELEVENLABS_VOICE_1_ID")
+        self.elevenlabs_voice_2_id = os.getenv("ELEVENLABS_VOICE_2_ID")
 
         self.use_mac_os_tts = False
         self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
@@ -77,7 +79,7 @@ class Config(metaclass=Singleton):
         self.redis_password = os.getenv("REDIS_PASSWORD", "")
         self.wipe_redis_on_start = os.getenv("WIPE_REDIS_ON_START", "True") == 'True'
         self.memory_index = os.getenv("MEMORY_INDEX", 'auto-gpt')
-        # Note that indexes must be created on db 0 in redis, this is not configureable.
+        # Note that indexes must be created on db 0 in redis, this is not configurable.
 
         self.memory_backend = os.getenv("MEMORY_BACKEND", 'local')
         # Initialize the OpenAI API client
@@ -91,9 +93,6 @@ 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
@@ -118,6 +117,14 @@ class Config(metaclass=Singleton):
         """Set the ElevenLabs API key value."""
         self.elevenlabs_api_key = value
 
+    def set_elevenlabs_voice_1_id(self, value: str):
+        """Set the ElevenLabs Voice 1 ID value."""
+        self.elevenlabs_voice_1_id = value
+
+    def set_elevenlabs_voice_2_id(self, value: str):
+        """Set the ElevenLabs Voice 2 ID value."""
+        self.elevenlabs_voice_2_id = value
+
     def set_google_api_key(self, value: str):
         """Set the Google API key value."""
         self.google_api_key = value
@@ -136,4 +143,4 @@ class Config(metaclass=Singleton):
 
     def set_debug_mode(self, value: bool):
         """Set the debug mode value."""
-        self.debug = value
+        self.debug_mode = value

scripts/json_parser.py

@@ -53,7 +53,7 @@ def fix_and_parse_json(
         last_brace_index = json_str.rindex("}")
         json_str = json_str[:last_brace_index+1]
         return json.loads(json_str)
-    except json.JSONDecodeError as e:  # noqa: F841
+    except (json.JSONDecodeError, ValueError) as e:  # noqa: F841
         if try_to_fix_with_gpt:
             print("Warning: Failed to parse AI output, attempting to fix."
                   "\n If you see this warning frequently, it's likely that"
@@ -67,22 +67,22 @@ def fix_and_parse_json(
             else:
                 # This allows the AI to react to the error message,
                 #   which usually results in it correcting its ways.
-                print("Failed to fix ai output, telling the AI.")
+                print("Failed to fix AI output, telling the AI.")
                 return json_str
         else:
             raise e
-            
-        
+
+
 def fix_json(json_str: str, schema: str) -> str:
-    """Fix the given JSON string to make it parseable and fully complient with the provided schema."""
-    
-    # Try to fix the JSON using gpt:
+    """Fix the given JSON string to make it parseable and fully compliant with the provided schema."""
+
+    # Try to fix the JSON using GPT:
     function_string = "def fix_json(json_str: str, schema:str=None) -> str:"
     args = [f"'''{json_str}'''", f"'''{schema}'''"]
     description_string = "Fixes the provided JSON string to make it parseable"\
-        " and fully complient with the provided schema.\n If an object or"\
+        " and fully compliant with the provided schema.\n If an object or"\
         " field specified in the schema isn't contained within the correct"\
-        " JSON, it is ommited.\n This function is brilliant at guessing"\
+        " JSON, it is omitted.\n This function is brilliant at guessing"\
         " when the format is incorrect."
 
     # If it doesn't already start with a "`", add one:
@@ -91,7 +91,7 @@ def fix_json(json_str: str, schema: str) -> str:
     result_string = call_ai_function(
         function_string, args, description_string, model=cfg.fast_llm_model
     )
-    if cfg.debug:
+    if cfg.debug_mode:
         print("------------ JSON FIX ATTEMPT ---------------")
         print(f"Original JSON: {json_str}")
         print("-----------")

scripts/json_utils.py

@@ -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

@@ -9,8 +9,6 @@ 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
@@ -172,7 +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"
@@ -268,6 +266,7 @@ def prompt_user():
 def parse_arguments():
     """Parses the arguments passed to the script"""
     global cfg
+    cfg.set_debug_mode(False)
     cfg.set_continuous_mode(False)
     cfg.set_speak_mode(False)
 
@@ -276,6 +275,7 @@ def parse_arguments():
     parser.add_argument('--speak', action='store_true', help='Enable Speak Mode')
     parser.add_argument('--debug', action='store_true', help='Enable Debug Mode')
     parser.add_argument('--gpt3only', action='store_true', help='Enable GPT3.5 Only Mode')
+    parser.add_argument('--gpt4only', action='store_true', help='Enable GPT4 Only Mode')
     args = parser.parse_args()
 
     if args.continuous:
@@ -290,13 +290,13 @@ 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.gpt4only:
+        print_to_console("GPT4 Only Mode: ", Fore.GREEN, "ENABLED")
+        cfg.set_fast_llm_model(cfg.smart_llm_model)
 
     if args.debug:
         print_to_console("Debug Mode: ", Fore.GREEN, "ENABLED")
@@ -392,7 +392,7 @@ while True:
             f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}  ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}")
 
     # Execute command
-    if command_name.lower().startswith( "error" ):
+    if command_name is not None and command_name.lower().startswith( "error" ):
         result = f"Command {command_name} threw the following error: " + arguments
     elif command_name == "human_feedback":
         result = f"Human feedback: {user_input}"
@@ -417,4 +417,3 @@ while True:
             chat.create_chat_message(
                 "system", "Unable to execute command"))
         print_to_console("SYSTEM: ", Fore.YELLOW, "Unable to execute command")
-

scripts/memory/local.py

@@ -54,8 +54,8 @@ class LocalCache(MemoryProviderSingleton):
         vector = vector[np.newaxis, :]
         self.data.embeddings = np.concatenate(
             [
-                vector,
                 self.data.embeddings,
+                vector,
             ],
             axis=0,
         )

scripts/speak.py

@@ -4,16 +4,33 @@ import requests
 from config import Config
 cfg = Config()
 import gtts
+import threading
+from threading import Lock, Semaphore
 
+# Default voice IDs
+default_voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
 
-# TODO: Nicer names for these ids
-voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
+# Retrieve custom voice IDs from the Config class
+custom_voice_1 = cfg.elevenlabs_voice_1_id
+custom_voice_2 = cfg.elevenlabs_voice_2_id
+
+# Placeholder values that should be treated as empty
+placeholders = {"your-voice-id"}
+
+# Use custom voice IDs if provided and not placeholders, otherwise use default voice IDs
+voices = [
+    custom_voice_1 if custom_voice_1 and custom_voice_1 not in placeholders else default_voices[0],
+    custom_voice_2 if custom_voice_2 and custom_voice_2 not in placeholders else default_voices[1]
+]
 
 tts_headers = {
     "Content-Type": "application/json",
     "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(
@@ -23,10 +40,11 @@ def eleven_labs_speech(text, voice_index=0):
         tts_url, headers=tts_headers, json=formatted_message)
 
     if response.status_code == 200:
-        with open("speech.mpeg", "wb") as f:
-            f.write(response.content)
-        playsound("speech.mpeg")
-        os.remove("speech.mpeg")
+        with mutex_lock:
+            with open("speech.mpeg", "wb") as f:
+                f.write(response.content)
+            playsound("speech.mpeg", True)
+            os.remove("speech.mpeg")
         return True
     else:
         print("Request failed with status code:", response.status_code)
@@ -35,21 +53,29 @@ def eleven_labs_speech(text, voice_index=0):
 
 def gtts_speech(text):
     tts = gtts.gTTS(text)
-    tts.save("speech.mp3")
-    playsound("speech.mp3")
-    os.remove("speech.mp3")
+    with mutex_lock:
+        tts.save("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):
-    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)
 
+    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/spinner.py

@@ -20,7 +20,7 @@ class Spinner:
             sys.stdout.write(next(self.spinner) + " " + self.message + "\r")
             sys.stdout.flush()
             time.sleep(self.delay)
-            sys.stdout.write('\b' * (len(self.message) + 2))
+            sys.stdout.write('\r' + ' ' * (len(self.message) + 2) + '\r')
 
     def __enter__(self):
         """Start the spinner"""

tests/integration/memory_tests.py

@@ -0,0 +1,49 @@
+import unittest
+import random
+import string
+import sys
+from pathlib import Path
+# Add the parent directory of the 'scripts' folder to the Python path
+sys.path.append(str(Path(__file__).resolve().parent.parent.parent / 'scripts'))
+from config import Config
+from memory.local import LocalCache
+
+class TestLocalCache(unittest.TestCase):
+
+    def random_string(self, length):
+        return ''.join(random.choice(string.ascii_letters) for _ in range(length))
+
+    def setUp(self):
+        cfg = cfg = Config()
+        self.cache = LocalCache(cfg)
+        self.cache.clear()
+
+        # Add example texts to the cache
+        self.example_texts = [
+            'The quick brown fox jumps over the lazy dog',
+            'I love machine learning and natural language processing',
+            'The cake is a lie, but the pie is always true',
+            'ChatGPT is an advanced AI model for conversation'
+        ]
+
+        for text in self.example_texts:
+            self.cache.add(text)
+
+        # Add some random strings to test noise
+        for _ in range(5):
+            self.cache.add(self.random_string(10))
+
+    def test_get_relevant(self):
+        query = "I'm interested in artificial intelligence and NLP"
+        k = 3
+        relevant_texts = self.cache.get_relevant(query, k)
+
+        print(f"Top {k} relevant texts for the query '{query}':")
+        for i, text in enumerate(relevant_texts, start=1):
+            print(f"{i}. {text}")
+
+        self.assertEqual(len(relevant_texts), k)
+        self.assertIn(self.example_texts[1], relevant_texts)
+
+if __name__ == '__main__':
+    unittest.main()