File size: 8,607 Bytes
40a5d34 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
"""File operations for AutoGPT"""
from __future__ import annotations
import os
import os.path
from typing import Generator
import requests
from colorama import Back, Fore
from requests.adapters import HTTPAdapter, Retry
from autogpt.spinner import Spinner
from autogpt.utils import readable_file_size
from autogpt.workspace import WORKSPACE_PATH, path_in_workspace
LOG_FILE = "file_logger.txt"
LOG_FILE_PATH = WORKSPACE_PATH / LOG_FILE
def check_duplicate_operation(operation: str, filename: str) -> bool:
"""Check if the operation has already been performed on the given file
Args:
operation (str): The operation to check for
filename (str): The name of the file to check for
Returns:
bool: True if the operation has already been performed on the file
"""
log_content = read_file(LOG_FILE)
log_entry = f"{operation}: {filename}\n"
return log_entry in log_content
def log_operation(operation: str, filename: str) -> None:
"""Log the file operation to the file_logger.txt
Args:
operation (str): The operation to log
filename (str): The name of the file the operation was performed on
"""
log_entry = f"{operation}: {filename}\n"
# Create the log file if it doesn't exist
if not os.path.exists(LOG_FILE_PATH):
with open(LOG_FILE_PATH, "w", encoding="utf-8") as f:
f.write("File Operation Logger ")
append_to_file(LOG_FILE, log_entry, shouldLog=False)
def split_file(
content: str, max_length: int = 4000, overlap: int = 0
) -> Generator[str, None, None]:
"""
Split text into chunks of a specified maximum length with a specified overlap
between chunks.
:param content: The input text to be split into chunks
:param max_length: The maximum length of each chunk,
default is 4000 (about 1k token)
:param overlap: The number of overlapping characters between chunks,
default is no overlap
:return: A generator yielding chunks of text
"""
start = 0
content_length = len(content)
while start < content_length:
end = start + max_length
if end + overlap < content_length:
chunk = content[start : end + overlap - 1]
else:
chunk = content[start:content_length]
# Account for the case where the last chunk is shorter than the overlap, so it has already been consumed
if len(chunk) <= overlap:
break
yield chunk
start += max_length - overlap
def read_file(filename: str) -> str:
"""Read a file and return the contents
Args:
filename (str): The name of the file to read
Returns:
str: The contents of the file
"""
try:
filepath = path_in_workspace(filename)
with open(filepath, "r", encoding="utf-8") as f:
content = f.read()
return content
except Exception as e:
return f"Error: {str(e)}"
def ingest_file(
filename: str, memory, max_length: int = 4000, overlap: int = 200
) -> None:
"""
Ingest a file by reading its content, splitting it into chunks with a specified
maximum length and overlap, and adding the chunks to the memory storage.
:param filename: The name of the file to ingest
:param memory: An object with an add() method to store the chunks in memory
:param max_length: The maximum length of each chunk, default is 4000
:param overlap: The number of overlapping characters between chunks, default is 200
"""
try:
print(f"Working with file {filename}")
content = read_file(filename)
content_length = len(content)
print(f"File length: {content_length} characters")
chunks = list(split_file(content, max_length=max_length, overlap=overlap))
num_chunks = len(chunks)
for i, chunk in enumerate(chunks):
print(f"Ingesting chunk {i + 1} / {num_chunks} into memory")
memory_to_add = (
f"Filename: {filename}\n" f"Content part#{i + 1}/{num_chunks}: {chunk}"
)
memory.add(memory_to_add)
print(f"Done ingesting {num_chunks} chunks from {filename}.")
except Exception as e:
print(f"Error while ingesting file '{filename}': {str(e)}")
def write_to_file(filename: str, text: str) -> str:
"""Write text to a file
Args:
filename (str): The name of the file to write to
text (str): The text to write to the file
Returns:
str: A message indicating success or failure
"""
if check_duplicate_operation("write", filename):
return "Error: File has already been updated."
try:
filepath = path_in_workspace(filename)
directory = os.path.dirname(filepath)
if not os.path.exists(directory):
os.makedirs(directory)
with open(filepath, "w", encoding="utf-8") as f:
f.write(text)
log_operation("write", filename)
return "File written to successfully."
except Exception as e:
return f"Error: {str(e)}"
def append_to_file(filename: str, text: str, shouldLog: bool = True) -> str:
"""Append text to a file
Args:
filename (str): The name of the file to append to
text (str): The text to append to the file
Returns:
str: A message indicating success or failure
"""
try:
filepath = path_in_workspace(filename)
with open(filepath, "a") as f:
f.write(text)
if shouldLog:
log_operation("append", filename)
return "Text appended successfully."
except Exception as e:
return f"Error: {str(e)}"
def delete_file(filename: str) -> str:
"""Delete a file
Args:
filename (str): The name of the file to delete
Returns:
str: A message indicating success or failure
"""
if check_duplicate_operation("delete", filename):
return "Error: File has already been deleted."
try:
filepath = path_in_workspace(filename)
os.remove(filepath)
log_operation("delete", filename)
return "File deleted successfully."
except Exception as e:
return f"Error: {str(e)}"
def search_files(directory: str) -> list[str]:
"""Search for files in a directory
Args:
directory (str): The directory to search in
Returns:
list[str]: A list of files found in the directory
"""
found_files = []
if directory in {"", "/"}:
search_directory = WORKSPACE_PATH
else:
search_directory = path_in_workspace(directory)
for root, _, files in os.walk(search_directory):
for file in files:
if file.startswith("."):
continue
relative_path = os.path.relpath(os.path.join(root, file), WORKSPACE_PATH)
found_files.append(relative_path)
return found_files
def download_file(url, filename):
"""Downloads a file
Args:
url (str): URL of the file to download
filename (str): Filename to save the file as
"""
safe_filename = path_in_workspace(filename)
try:
message = f"{Fore.YELLOW}Downloading file from {Back.LIGHTBLUE_EX}{url}{Back.RESET}{Fore.RESET}"
with Spinner(message) as spinner:
session = requests.Session()
retry = Retry(total=3, backoff_factor=1, status_forcelist=[502, 503, 504])
adapter = HTTPAdapter(max_retries=retry)
session.mount("http://", adapter)
session.mount("https://", adapter)
total_size = 0
downloaded_size = 0
with session.get(url, allow_redirects=True, stream=True) as r:
r.raise_for_status()
total_size = int(r.headers.get("Content-Length", 0))
downloaded_size = 0
with open(safe_filename, "wb") as f:
for chunk in r.iter_content(chunk_size=8192):
f.write(chunk)
downloaded_size += len(chunk)
# Update the progress message
progress = f"{readable_file_size(downloaded_size)} / {readable_file_size(total_size)}"
spinner.update_message(f"{message} {progress}")
return f'Successfully downloaded and locally stored file: "{filename}"! (Size: {readable_file_size(total_size)})'
except requests.HTTPError as e:
return f"Got an HTTP Error whilst trying to download file: {e}"
except Exception as e:
return "Error: " + str(e)
|