167 lines
6.6 KiB
Python
167 lines
6.6 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()
|
||
cleaned_lower = cleaned.lower()
|
||
|
||
# Base names for Miku in different scripts
|
||
base_names = [
|
||
'miku', 'мику', 'みく', 'ミク', '未来'
|
||
]
|
||
|
||
# Japanese honorifics - all scripts combined
|
||
honorifics = [
|
||
# 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', 'нян', 'химе', 'тан', 'чин', 'хейка', 'хеика',
|
||
'денка', 'какка', 'си', 'чама', 'кюн', 'доно', 'сенсэй', 'сенсеи', 'сенпай', 'сенпаи', 'джо'
|
||
]
|
||
|
||
# o- prefix variants
|
||
o_prefixes = ['o-', 'о-', 'お', 'オ']
|
||
|
||
# Build all possible name variations to check
|
||
name_patterns = []
|
||
|
||
for base in base_names:
|
||
base_lower = base.lower()
|
||
base_escaped = re.escape(base_lower)
|
||
|
||
# Base name alone
|
||
name_patterns.append(base_escaped)
|
||
|
||
# With honorifics (allows optional dash/space between)
|
||
for honorific in honorifics:
|
||
honorific_lower = honorific.lower()
|
||
honorific_escaped = re.escape(honorific_lower)
|
||
# Build pattern: base + optional [dash or space] + honorific
|
||
name_patterns.append(base_escaped + r'[\-\s]*' + honorific_escaped)
|
||
|
||
# With o- prefix
|
||
for prefix in o_prefixes:
|
||
prefix_lower = prefix.lower()
|
||
prefix_escaped = re.escape(prefix_lower)
|
||
# o-prefix + optional space + base
|
||
name_patterns.append(prefix_escaped + r'\s*' + base_escaped)
|
||
|
||
# With o- prefix + honorific
|
||
for honorific in honorifics:
|
||
honorific_lower = honorific.lower()
|
||
honorific_escaped = re.escape(honorific_lower)
|
||
# o-prefix + space + base + dash/space + honorific
|
||
name_patterns.append(prefix_escaped + r'\s*' + base_escaped + r'[\-\s]*' + honorific_escaped)
|
||
|
||
# Check all patterns - she must be "addressed" not just mentioned
|
||
for pattern in name_patterns:
|
||
try:
|
||
# Pattern 1: Start of message + punctuation/end
|
||
# "Miku, ..." or "みく！" or "ミクちゃん、..."
|
||
start_p = r'^' + pattern + r'(?:[,，、!！?？.。\s]+|$)'
|
||
if re.search(start_p, cleaned_lower, re.IGNORECASE):
|
||
return True
|
||
|
||
# Pattern 2: End of message (optionally preceded by punctuation)
|
||
# "..., Miku" or "...みく" or "...ミクちゃん！"
|
||
end_p = r'(?:[,，、!！?？.。\s]+|^)' + pattern + r'[!！?？.。\s]*$'
|
||
if re.search(end_p, cleaned_lower, re.IGNORECASE):
|
||
return True
|
||
|
||
# Pattern 3: Middle (surrounded by punctuation)
|
||
# "..., Miku, ..." or "...、ミク、..."
|
||
middle_p = r'[,，、!！?？.。\s]+' + pattern + r'[,，、!！?？.。\s]+'
|
||
if re.search(middle_p, cleaned_lower, re.IGNORECASE):
|
||
return True
|
||
|
||
# Pattern 4: Just the name alone
|
||
# "Miku" or "みく！" or "ミクちゃん"
|
||
alone_p = r'^\s*' + pattern + r'[!！?？.。]*\s*$'
|
||
if re.search(alone_p, cleaned_lower, re.IGNORECASE):
|
||
return True
|
||
except re.error as e:
|
||
# Log the problematic pattern and skip it
|
||
logger.error(f"REGEX ERROR - Pattern: '{pattern}' | Start regex: '{start_p}' | Error: {e}")
|
||
continue
|
||
|
||
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()
|