Merge branch 'master' into prompt-generator

scripts/ai_functions.py

@@ -45,6 +45,7 @@ def improve_code(suggestions: List[str], code: str) -> str:
     result_string = call_ai_function(function_string, args, description_string)
     return result_string
 
+
 def write_tests(code: str, focus: List[str]) -> str:
     """
     A function that takes in code and focus topics and returns a response from create chat completion api call.

scripts/browse.py

@@ -6,6 +6,7 @@ from urllib.parse import urlparse, urljoin
 
 cfg = Config()
 
+
 # Function to check if the URL is valid
 def is_valid_url(url):
     try:
@@ -14,49 +15,51 @@ def is_valid_url(url):
     except ValueError:
         return False
 
+
 # Function to sanitize the URL
 def sanitize_url(url):
     return urljoin(url, urlparse(url).path)
 
-# Function to make a request with a specified timeout and handle exceptions
-def make_request(url, timeout=10):
-    try:
-        response = requests.get(url, headers=cfg.user_agent_header, timeout=timeout)
-        response.raise_for_status()
-        return response
-    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 get_response(url, headers=cfg.user_agent_header, timeout=10):
+    try:
+        # Restrict access to local files
+        if check_local_file_access(url):
+            raise ValueError('Access to local files is restricted')
+
+        # Most basic check if the URL is valid:
+        if not url.startswith('http://') and not url.startswith('https://'):
+            raise ValueError('Invalid URL format')
+
+        sanitized_url = sanitize_url(url)
+
+        response = requests.get(sanitized_url, headers=headers, timeout=timeout)
+
+        # Check if the response contains an HTTP error
+        if response.status_code >= 400:
+            return None, "Error: HTTP " + str(response.status_code) + " error"
+
+        return response, None
+    except ValueError as ve:
+        # Handle invalid URL format
+        return None, "Error: " + str(ve)
+
+    except requests.exceptions.RequestException as re:
+        # Handle exceptions related to the HTTP request (e.g., connection errors, timeouts, etc.)
+        return None, "Error: " + str(re)
+
+
 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
-        sanitized_url = sanitize_url(url)
-
-        # Make the request with a timeout and handle exceptions
-        response = make_request(sanitized_url)
-
-        if isinstance(response, str):
-            return response
-    else:
-        # Sanitize the input URL
-        sanitized_url = sanitize_url(url)
-
-        response = requests.get(sanitized_url, headers=cfg.user_agent_header)
+    response, error_message = get_response(url)
+    if error_message:
+        return error_message
 
     soup = BeautifulSoup(response.text, "html.parser")
 
@@ -89,11 +92,9 @@ def format_hyperlinks(hyperlinks):
 
 def scrape_links(url):
     """Scrape links from a webpage"""
-    response = requests.get(url, headers=cfg.user_agent_header)
-
-    # Check if the response contains an HTTP error
-    if response.status_code >= 400:
-        return "error"
+    response, error_message = get_response(url)
+    if error_message:
+        return error_message
 
     soup = BeautifulSoup(response.text, "html.parser")
 
@@ -131,6 +132,7 @@ def create_message(chunk, question):
         "content": f"\"\"\"{chunk}\"\"\" Using the above text, please answer the following question: \"{question}\" -- if the question cannot be answered using the text, please summarize the text."
     }
 
+
 def summarize_text(text, question):
     """Summarize text using the LLM model"""
     if not text:

scripts/commands.py

@@ -7,7 +7,7 @@ import speak
 from config import Config
 import ai_functions as ai
 from file_operations import read_file, write_to_file, append_to_file, delete_file, search_files
-from execute_code import execute_python_file
+from execute_code import execute_python_file, execute_shell
 from json_parser import fix_and_parse_json
 from image_gen import generate_image
 from duckduckgo_search import ddg
@@ -103,6 +103,11 @@ def execute_command(command_name, arguments):
             return ai.write_tests(arguments["code"], arguments.get("focus"))
         elif command_name == "execute_python_file":  # Add this command
             return execute_python_file(arguments["file"])
+        elif command_name == "execute_shell":
+            if cfg.execute_local_commands:
+                return execute_shell(arguments["command_line"])
+            else:
+                return "You are not allowed to run local shell commands. To execute shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' in your config. Do not attempt to bypass the restriction."
         elif command_name == "generate_image":
             return generate_image(arguments["prompt"])
         elif command_name == "do_nothing":

scripts/config.py

@@ -1,6 +1,7 @@
 import abc
 import os
 import openai
+import yaml
 from dotenv import load_dotenv
 # Load environment variables from .env file
 load_dotenv()
@@ -43,14 +44,13 @@ class Config(metaclass=Singleton):
         self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000))
 
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        self.temperature = int(os.getenv("TEMPERATURE", "1"))
         self.use_azure = False
         self.use_azure = os.getenv("USE_AZURE") == 'True'
+        self.execute_local_commands = os.getenv('EXECUTE_LOCAL_COMMANDS', 'False') == 'True'
+
         if self.use_azure:
-            self.openai_api_base = os.getenv("OPENAI_AZURE_API_BASE")
-            self.openai_api_version = os.getenv("OPENAI_AZURE_API_VERSION")
-            self.openai_deployment_id = os.getenv("OPENAI_AZURE_DEPLOYMENT_ID")
-            self.azure_chat_deployment_id = os.getenv("OPENAI_AZURE_CHAT_DEPLOYMENT_ID")
-            self.azure_embeddigs_deployment_id = os.getenv("OPENAI_AZURE_EMBEDDINGS_DEPLOYMENT_ID")
+            self.load_azure_config()
             openai.api_type = "azure"
             openai.api_base = self.openai_api_base
             openai.api_version = self.openai_api_version
@@ -85,6 +85,46 @@ class Config(metaclass=Singleton):
         # Initialize the OpenAI API client
         openai.api_key = self.openai_api_key
 
+    def get_azure_deployment_id_for_model(self, model: str) -> str:
+        """
+        Returns the relevant deployment id for the model specified.
+
+        Parameters:
+            model(str): The model to map to the deployment id.
+
+        Returns:
+            The matching deployment id if found, otherwise an empty string.
+        """
+        if model == self.fast_llm_model:
+            return self.azure_model_to_deployment_id_map["fast_llm_model_deployment_id"]
+        elif model == self.smart_llm_model:
+            return self.azure_model_to_deployment_id_map["smart_llm_model_deployment_id"]
+        elif model == "text-embedding-ada-002":
+            return self.azure_model_to_deployment_id_map["embedding_model_deployment_id"]
+        else:
+            return ""
+
+    AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), '..', 'azure.yaml')
+
+    def load_azure_config(self, config_file: str=AZURE_CONFIG_FILE) -> None:
+        """
+        Loads the configuration parameters for Azure hosting from the specified file path as a yaml file.
+
+        Parameters:
+            config_file(str): The path to the config yaml file. DEFAULT: "../azure.yaml"
+
+        Returns:
+            None
+        """
+        try:
+            with open(config_file) as file:
+                config_params = yaml.load(file, Loader=yaml.FullLoader)
+        except FileNotFoundError:
+            config_params = {}
+        self.openai_api_base = config_params.get("azure_api_base", "")
+        self.openai_api_version = config_params.get("azure_api_version", "")
+        self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", [])
+
     def set_continuous_mode(self, value: bool):
         """Set the continuous mode value."""
         self.continuous_mode = value

scripts/execute_code.py

@@ -1,17 +1,20 @@
 import docker
 import os
+import subprocess
+
+
+WORKSPACE_FOLDER = "auto_gpt_workspace"
 
 
 def execute_python_file(file):
     """Execute a Python file in a Docker container and return the output"""
-    workspace_folder = "auto_gpt_workspace"
 
-    print (f"Executing file '{file}' in workspace '{workspace_folder}'")
+    print (f"Executing file '{file}' in workspace '{WORKSPACE_FOLDER}'")
 
     if not file.endswith(".py"):
         return "Error: Invalid file type. Only .py files are allowed."
 
-    file_path = os.path.join(workspace_folder, file)
+    file_path = os.path.join(WORKSPACE_FOLDER, file)
 
     if not os.path.isfile(file_path):
         return f"Error: File '{file}' does not exist."
@@ -19,14 +22,31 @@ def execute_python_file(file):
     try:
         client = docker.from_env()
 
+        image_name = 'python:3.10'
+        try:
+            client.images.get(image_name)
+            print(f"Image '{image_name}' found locally")
+        except docker.errors.ImageNotFound:
+            print(f"Image '{image_name}' not found locally, pulling from Docker Hub")
+            # Use the low-level API to stream the pull response
+            low_level_client = docker.APIClient()
+            for line in low_level_client.pull(image_name, stream=True, decode=True):
+                # Print the status and progress, if available
+                status = line.get('status')
+                progress = line.get('progress')
+                if status and progress:
+                    print(f"{status}: {progress}")
+                elif status:
+                    print(status)
+
         # You can replace 'python:3.8' with the desired Python image/version
         # You can find available Python images on Docker Hub:
         # https://hub.docker.com/_/python
         container = client.containers.run(
-            'python:3.10',
+            image_name,
             f'python {file}',
             volumes={
-                os.path.abspath(workspace_folder): {
+                os.path.abspath(WORKSPACE_FOLDER): {
                     'bind': '/workspace',
                     'mode': 'ro'}},
             working_dir='/workspace',
@@ -46,3 +66,22 @@ def execute_python_file(file):
 
     except Exception as e:
         return f"Error: {str(e)}"
+
+def execute_shell(command_line):
+
+    current_dir = os.getcwd()
+
+    if not WORKSPACE_FOLDER in current_dir: # Change dir into workspace if necessary
+        work_dir = os.path.join(os.getcwd(), WORKSPACE_FOLDER)
+        os.chdir(work_dir)
+
+    print (f"Executing command '{command_line}' in working directory '{os.getcwd()}'")
+
+    result = subprocess.run(command_line, capture_output=True, shell=True)
+    output = f"STDOUT:\n{result.stdout}\nSTDERR:\n{result.stderr}"
+
+    # Change back to whatever the prior working dir was
+
+    os.chdir(current_dir)
+
+    return output

scripts/llm_utils.py

@@ -5,11 +5,11 @@ cfg = Config()
 openai.api_key = cfg.openai_api_key
 
 # Overly simple abstraction until we create something better
-def create_chat_completion(messages, model=None, temperature=None, max_tokens=None)->str:
+def create_chat_completion(messages, model=None, temperature=cfg.temperature, max_tokens=None)->str:
     """Create a chat completion using the OpenAI API"""
     if cfg.use_azure:
         response = openai.ChatCompletion.create(
-            deployment_id=cfg.azure_chat_deployment_id,
+            deployment_id=cfg.get_azure_deployment_id_for_model(model),
             model=model,
             messages=messages,
             temperature=temperature,

scripts/logger.py

@@ -124,6 +124,12 @@ class Logger(metaclass=Singleton):
         self.logger.setLevel(level)
         self.typing_logger.setLevel(level)
 
+    def double_check(self, additionalText=None):
+        if not additionalText:
+            additionalText = "Please ensure you've setup and configured everything correctly. Read https://github.com/Torantulino/Auto-GPT#readme to double check. You can also create a github issue or join the discord and ask there!"
+
+        self.typewriter_log("DOUBLE CHECK CONFIGURATION", Fore.YELLOW, additionalText)
+
 
 '''
 Output stream to console using simulated typing
@@ -164,8 +170,6 @@ class ConsoleHandler(logging.StreamHandler):
 Allows to handle custom placeholders 'title_color' and 'message_no_color'.
 To use this formatter, make sure to pass 'color', 'title' as log extras.
 '''
-
-
 class AutoGptFormatter(logging.Formatter):
     def format(self, record: LogRecord) -> str:
         if (hasattr(record, 'color')):

scripts/main.py

@@ -310,15 +310,14 @@ def parse_arguments():
         supported_memory = get_supported_memory_backends()
         chosen = args.memory_type
         if not chosen in supported_memory:
-            print_to_console("ONLY THE FOLLOWING MEMORY BACKENDS ARE SUPPORTED: ", Fore.RED, f'{supported_memory}')
-            print_to_console(f"Defaulting to: ", Fore.YELLOW, cfg.memory_backend)
+            logger.typewriter_log("ONLY THE FOLLOWING MEMORY BACKENDS ARE SUPPORTED: ", Fore.RED, f'{supported_memory}')
+            logger.typewriter_log(f"Defaulting to: ", Fore.YELLOW, cfg.memory_backend)
         else:
             cfg.memory_backend = chosen
 
 
 # TODO: fill in llm values here
 check_openai_api_key()
-cfg = Config()
 parse_arguments()
 logger.set_level(logging.DEBUG if cfg.debug_mode else logging.INFO)
 ai_name = ""

scripts/memory/__init__.py

@@ -1,4 +1,5 @@
 from memory.local import LocalCache
+from memory.no_memory import NoMemory
 
 # List of supported memory backends
 # Add a backend to this list if the import attempt is successful
@@ -34,6 +35,8 @@ def get_memory(cfg, init=False):
                   " use Redis as a memory backend.")
         else:
             memory = RedisMemory(cfg)
+    elif cfg.memory_backend == "no_memory":
+        memory = NoMemory(cfg)
 
     if memory is None:
         memory = LocalCache(cfg)
@@ -50,4 +53,5 @@ __all__ = [
     "LocalCache",
     "RedisMemory",
     "PineconeMemory",
+    "NoMemory"
 ]

scripts/memory/base.py

@@ -2,13 +2,13 @@
 import abc
 from config import AbstractSingleton, Config
 import openai
-cfg = Config()
 
+cfg = Config()
 
 def get_ada_embedding(text):
     text = text.replace("\n", " ")
     if cfg.use_azure:
-        return openai.Embedding.create(input=[text], engine=cfg.azure_embeddigs_deployment_id, model="text-embedding-ada-002")["data"][0]["embedding"]
+        return openai.Embedding.create(input=[text], engine=cfg.get_azure_deployment_id_for_model("text-embedding-ada-002"))["data"][0]["embedding"]
     else:
         return openai.Embedding.create(input=[text], model="text-embedding-ada-002")["data"][0]["embedding"]
 

scripts/memory/no_memory.py

@@ -0,0 +1,65 @@
+from typing import Optional, List, Any
+
+from memory.base import MemoryProviderSingleton
+
+class NoMemory(MemoryProviderSingleton):
+    def __init__(self, cfg):
+        """
+        Initializes the NoMemory provider.
+
+        Args:
+            cfg: The config object.
+
+        Returns: None
+        """
+        pass
+
+    def add(self, data: str) -> str:
+        """
+        Adds a data point to the memory. No action is taken in NoMemory.
+
+        Args:
+            data: The data to add.
+
+        Returns: An empty string.
+        """
+        return ""
+
+    def get(self, data: str) -> Optional[List[Any]]:
+        """
+        Gets the data from the memory that is most relevant to the given data.
+        NoMemory always returns None.
+
+        Args:
+            data: The data to compare to.
+
+        Returns: None
+        """
+        return None
+
+    def clear(self) -> str:
+        """
+        Clears the memory. No action is taken in NoMemory.
+
+        Returns: An empty string.
+        """
+        return ""
+
+    def get_relevant(self, data: str, num_relevant: int = 5) -> Optional[List[Any]]:
+        """
+        Returns all the data in the memory that is relevant to the given data.
+        NoMemory always returns None.
+
+        Args:
+            data: The data to compare to.
+            num_relevant: The number of relevant data to return.
+
+        Returns: None
+        """
+        return None
+
+    def get_stats(self):
+        """
+        Returns: An empty dictionary as there are no stats in NoMemory.
+        """
+        return {}

scripts/memory/pinecone.py

@@ -2,7 +2,8 @@
 import pinecone
 
 from memory.base import MemoryProviderSingleton, get_ada_embedding
-
+from logger import logger
+from colorama import Fore, Style
 
 class PineconeMemory(MemoryProviderSingleton):
     def __init__(self, cfg):
@@ -17,6 +18,15 @@ class PineconeMemory(MemoryProviderSingleton):
         # for now this works.
         # we'll need a more complicated and robust system if we want to start with memory.
         self.vec_num = 0
+
+        try:
+            pinecone.whoami()
+        except Exception as e:
+            logger.typewriter_log("FAILED TO CONNECT TO PINECONE", Fore.RED, Style.BRIGHT + str(e) + Style.RESET_ALL)
+            logger.double_check("Please ensure you have setup and configured Pinecone properly for use. " +
+                               f"You can check out {Fore.CYAN + Style.BRIGHT}https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup{Style.RESET_ALL} to ensure you've set up everything correctly.")
+            exit(1)
+
         if table_name not in pinecone.list_indexes():
             pinecone.create_index(table_name, dimension=dimension, metric=metric, pod_type=pod_type)
         self.index = pinecone.Index(table_name)

scripts/memory/redismem.py

@@ -7,6 +7,8 @@ from redis.commands.search.indexDefinition import IndexDefinition, IndexType
 import numpy as np
 
 from memory.base import MemoryProviderSingleton, get_ada_embedding
+from logger import logger
+from colorama import Fore, Style
 
 
 SCHEMA = [
@@ -44,6 +46,16 @@ class RedisMemory(MemoryProviderSingleton):
             db=0  # Cannot be changed
         )
         self.cfg = cfg
+
+        # Check redis connection
+        try:
+            self.redis.ping()
+        except redis.ConnectionError as e:
+            logger.typewriter_log("FAILED TO CONNECT TO REDIS", Fore.RED, Style.BRIGHT + str(e) + Style.RESET_ALL)
+            logger.double_check("Please ensure you have setup and configured Redis properly for use. " +
+                                f"You can check out {Fore.CYAN + Style.BRIGHT}https://github.com/Torantulino/Auto-GPT#redis-setup{Style.RESET_ALL} to ensure you've set up everything correctly.")
+            exit(1)
+
         if cfg.wipe_redis_on_start:
             self.redis.flushall()
         try: