143 lines
5.7 KiB
Python
143 lines
5.7 KiB
Python
# utils/core.py
|
||
|
||
import asyncio
|
||
import aiohttp
|
||
import re
|
||
|
||
import globals
|
||
from langchain_community.vectorstores import FAISS
|
||
from langchain_text_splitters import CharacterTextSplitter, RecursiveCharacterTextSplitter
|
||
from langchain_core.documents import Document
|
||
from utils.logger import get_logger
|
||
|
||
logger = get_logger('core')
|
||
|
||
|
||
# switch_model() removed - llama-swap handles model switching automatically
|
||
|
||
|
||
async def is_miku_addressed(message) -> bool:
|
||
# Check if this is a DM (no guild)
|
||
if message.guild is None:
|
||
# In DMs, always respond to every message
|
||
return True
|
||
|
||
# Safety check: ensure guild and guild.me exist
|
||
if not message.guild or not message.guild.me:
|
||
logger.warning(f"Invalid guild or guild.me in message from {message.author}")
|
||
return False
|
||
|
||
# If message contains a ping for Miku, return true
|
||
if message.guild.me in message.mentions:
|
||
return True
|
||
|
||
# If message is a reply, check the referenced message author
|
||
if message.reference:
|
||
try:
|
||
referenced_msg = await message.channel.fetch_message(message.reference.message_id)
|
||
if referenced_msg.author == message.guild.me:
|
||
return True
|
||
except Exception as e:
|
||
logger.warning(f"Could not fetch referenced message: {e}")
|
||
|
||
cleaned = message.content.strip().lower()
|
||
|
||
# Base names for Miku in different scripts
|
||
base_names = [
|
||
'miku', 'мику', 'みく', 'ミク', '未来'
|
||
]
|
||
|
||
# Japanese honorifics - all scripts combined for simpler matching
|
||
honorifics_all_scripts = [
|
||
# Latin
|
||
'chan', 'san', 'kun', 'nyan', 'hime', 'tan', 'chin', 'heika',
|
||
'denka', 'kakka', 'shi', 'chama', 'kyun', 'dono', 'sensei', 'senpai', 'jou',
|
||
# Hiragana
|
||
'ちゃん', 'さん', 'くん', 'にゃん', 'ひめ', 'たん', 'ちん', 'へいか',
|
||
'でんか', 'かっか', 'し', 'ちゃま', 'きゅん', 'どの', 'せんせい', 'せんぱい', 'じょう',
|
||
# Katakana
|
||
'チャン', 'サン', 'クン', 'ニャン', 'ヒメ', 'タン', 'チン', 'ヘイカ',
|
||
'デンカ', 'カッカ', 'シ', 'チャマ', 'キュン', 'ドノ', 'センセイ', 'センパイ', 'ジョウ',
|
||
# Cyrillic
|
||
'чан', 'сан', 'кун', 'ньян', 'химе', 'тан', 'чин', 'хэйка',
|
||
'дэнка', 'какка', 'си', 'чама', 'кюн', 'доно', 'сэнсэй', 'сэнпай', 'жо'
|
||
]
|
||
|
||
# Optional o- prefix in different scripts
|
||
o_prefixes = ['o-', 'о-', 'お', 'オ']
|
||
|
||
# Strategy: Just check if any base name appears (case insensitive for latin/cyrillic)
|
||
# Then allow any honorific to optionally follow
|
||
|
||
for base in base_names:
|
||
base_lower = base.lower()
|
||
|
||
# Check for just the base name
|
||
if re.search(r'(?<![a-zа-яa-я\w])' + re.escape(base_lower) + r'(?![a-zа-яa-я\w])', cleaned):
|
||
return True
|
||
|
||
# Check with optional o- prefix
|
||
for prefix in o_prefixes:
|
||
prefix_pattern = prefix.lower() if prefix != 'お' and prefix != 'オ' else prefix
|
||
pattern = r'(?<![a-zа-яa-я\w])' + re.escape(prefix_pattern) + r'\s*' + re.escape(base_lower) + r'(?![a-zа-яa-я\w])'
|
||
if re.search(pattern, cleaned):
|
||
return True
|
||
|
||
# Check base name followed by any honorific (no spacing requirement to catch mixed script)
|
||
for honorific in honorifics_all_scripts:
|
||
honorific_lower = honorific.lower()
|
||
# Allow optional dash, space, or no separator between name and honorific
|
||
pattern = (r'(?<![a-zа-яa-я\w])' + re.escape(base_lower) +
|
||
r'[-\s]*' + re.escape(honorific_lower) +
|
||
r'(?![a-zа-яa-я\w])')
|
||
if re.search(pattern, cleaned):
|
||
return True
|
||
|
||
# Check with o- prefix + base + honorific
|
||
for prefix in o_prefixes:
|
||
prefix_lower = prefix.lower() if prefix != 'お' and prefix != 'オ' else prefix
|
||
for honorific in honorifics_all_scripts:
|
||
honorific_lower = honorific.lower()
|
||
pattern = (r'(?<![a-zа-яa-я\w])' + re.escape(prefix_lower) +
|
||
r'[-\s]*' + re.escape(base_lower) +
|
||
r'[-\s]*' + re.escape(honorific_lower) +
|
||
r'(?![a-zа-яa-я\w])')
|
||
if re.search(pattern, cleaned):
|
||
return True
|
||
|
||
return False
|
||
|
||
# Vectorstore functionality disabled - not needed with current structured context approach
|
||
# If you need embeddings in the future, you can use a different embedding provider
|
||
# For now, the bot uses structured prompts from context_manager.py
|
||
|
||
# def load_miku_knowledge():
|
||
# with open("miku_lore.txt", "r", encoding="utf-8") as f:
|
||
# text = f.read()
|
||
#
|
||
# from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||
#
|
||
# text_splitter = RecursiveCharacterTextSplitter(
|
||
# chunk_size=520,
|
||
# chunk_overlap=50,
|
||
# separators=["\n\n", "\n", ".", "!", "?", ",", " ", ""]
|
||
# )
|
||
#
|
||
# docs = [Document(page_content=chunk) for chunk in text_splitter.split_text(text)]
|
||
#
|
||
# vectorstore = FAISS.from_documents(docs, embeddings)
|
||
# return vectorstore
|
||
#
|
||
# def load_miku_lyrics():
|
||
# with open("miku_lyrics.txt", "r", encoding="utf-8") as f:
|
||
# lyrics_text = f.read()
|
||
#
|
||
# text_splitter = CharacterTextSplitter(chunk_size=520, chunk_overlap=50)
|
||
# docs = [Document(page_content=chunk) for chunk in text_splitter.split_text(lyrics_text)]
|
||
#
|
||
# vectorstore = FAISS.from_documents(docs, embeddings)
|
||
# return vectorstore
|
||
#
|
||
# miku_vectorstore = load_miku_knowledge()
|
||
# miku_lyrics_vectorstore = load_miku_lyrics()
|