Starting a book reading module so that Ruby can read in her downtime.

This commit is contained in:
Dani 2025-04-19 08:55:20 -04:00
parent 21748f119f
commit 287eee0d34
3 changed files with 61 additions and 1 deletions

3
.gitignore vendored
View File

@ -171,4 +171,5 @@ cython_debug/
/tokenizer_vocab.txt
/logs/core_dreams.txt
/logs/best_dream.txt
/.vscode/launch.json
/.vscode/launch.json
/books

View File

@ -8,6 +8,7 @@ from datetime import datetime, timedelta
from dashboard import start_dashboard
from tokenizer import Tokenizer
from trainer import RubyTrainer
from reader import BookReader
import logging
# Setup logging
@ -41,12 +42,17 @@ class Ruby(discord.Client):
super().__init__(intents=intents)
self.tokenizer = Tokenizer()
self.trainer = RubyTrainer(self.tokenizer)
self.reader = BookReader(trainer=self.trainer,
book_path="books//wizard_of_oz.txt", # or whatever book you want
interval=180 # read every 3 minutes (adjust if needed)
)
self.last_message_time = datetime.utcnow()
self.idle_threshold = timedelta(seconds=120)
self.log_path = os.path.join("logs", "messages.log")
os.makedirs("logs", exist_ok=True)
async def setup_hook(self):
self.loop.create_task(self.reader.start_reading())
self.loop.create_task(self.idle_dream_loop())
async def set_activity(self, text=None):

53
reader.py Normal file
View File

@ -0,0 +1,53 @@
import os
import asyncio
from datetime import datetime
class BookReader:
def __init__(self, trainer, book_path, state_path="readstate.txt", log_path="logs/read.log", interval=180):
self.trainer = trainer
self.book_path = book_path
self.state_path = state_path
self.log_path = log_path
self.interval = interval # seconds between reading cycles
self.current_line = 0
os.makedirs(os.path.dirname(self.log_path), exist_ok=True)
if os.path.exists(self.state_path):
try:
with open(self.state_path, "r", encoding="utf-8") as f:
self.current_line = int(f.read().strip())
except Exception:
self.current_line = 0
def _save_state(self):
with open(self.state_path, "w", encoding="utf-8") as f:
f.write(str(self.current_line))
def _log_read(self, text: str, score: float, tag: str = "Book"):
with open(self.log_path, "a", encoding="utf-8") as f:
f.write(f"[{datetime.utcnow().isoformat()}] ({tag}) {score:.2f} | {text.strip()}\\n")
async def start_reading(self):
if not os.path.exists(self.book_path):
print(f"[BOOK] File not found: {self.book_path}")
return
with open(self.book_path, "r", encoding="utf-8") as f:
lines = f.readlines()
print(f"[BOOK] Starting to read {self.book_path} from line {self.current_line}...")
while self.current_line < len(lines):
passage = lines[self.current_line].strip()
if len(passage.split()) >= 5:
score = self.trainer.score_sentence(passage)
if self.trainer.is_reinforceable(passage) and score >= 2.5:
self.trainer.train_on_tokens_from_text(passage)
self._log_read(passage, score)
self.current_line += 1
self._save_state()
await asyncio.sleep(self.interval)
print("[BOOK] Finished reading the book.")