Spaces:
Sleeping
Sleeping
File size: 3,949 Bytes
78efe79 440418c f3985af dc80b35 22dee1c fe505c6 407a575 32c38ef f3985af 440418c 1831164 440418c 22dee1c 440418c 22dee1c 08baccf 535a9f2 dc80b35 40d0e92 74ccf1c 12bb502 78efe79 08baccf dc80b35 08baccf 78efe79 40d0e92 dc80b35 78efe79 5f46973 fe505c6 5f46973 ccbb5ef 5f46973 fe505c6 04edbaa fe505c6 535a9f2 fe505c6 86bc42a fe505c6 01dd380 fe505c6 01dd380 34428f1 dc80b35 |
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 |
import discord
import logging
import os
from huggingface_hub import InferenceClient
import asyncio
import subprocess
from datasets import load_dataset
# ๋ก๊น
์ค์
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s:%(levelname)s:%(name)s: %(message)s', handlers=[logging.StreamHandler()])
# ์ธํ
ํธ ์ค์
intents = discord.Intents.default()
intents.message_content = True
intents.messages = True
intents.guilds = True
intents.guild_messages = True
# ๋ฐ์ดํฐ์
๋ก๋
data_files = ['train_0.csv', 'train_1.csv', 'train_2.csv', 'train_3.csv', 'train_4.csv', 'train_5.csv']
law_dataset = load_dataset('csv', data_files=data_files)
# ์ถ๋ก API ํด๋ผ์ด์ธํธ ์ค์
hf_client = InferenceClient("CohereForAI/c4ai-command-r-plus", token=os.getenv("HF_TOKEN"))
# ํน์ ์ฑ๋ ID
SPECIFIC_CHANNEL_ID = int(os.getenv("DISCORD_CHANNEL_ID"))
# ๋ํ ํ์คํ ๋ฆฌ๋ฅผ ์ ์ฅํ ์ ์ญ ๋ณ์
conversation_history = []
class MyClient(discord.Client):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.is_processing = False
async def on_ready(self):
logging.info(f'{self.user}๋ก ๋ก๊ทธ์ธ๋์์ต๋๋ค!')
subprocess.Popen(["python", "web.py"])
logging.info("Web.py server has been started.")
async def on_message(self, message):
if message.author == self.user:
return
if not self.is_message_in_specific_channel(message):
return
if self.is_processing:
return
self.is_processing = True
try:
response = await generate_response(message)
await message.channel.send(response)
finally:
self.is_processing = False
def is_message_in_specific_channel(self, message):
return message.channel.id == SPECIFIC_CHANNEL_ID or (
isinstance(message.channel, discord.Thread) and message.channel.parent_id == SPECIFIC_CHANNEL_ID
)
async def generate_response(message):
global conversation_history
user_input = message.content
user_mention = message.author.mention
system_message = f"{user_mention}, DISCORD์์ ์ฌ์ฉ์๋ค์ ์ง๋ฌธ์ ๋ตํ๋ ์ด์์คํดํธ์
๋๋ค."
answer = search_in_dataset(user_input, law_dataset)
full_response_text = system_message + "\n\n" + answer
await message.channel.send(full_response_text)
conversation_history.append({"role": "assistant", "content": full_response_text})
def search_in_dataset(query, dataset):
response = []
for record in dataset['train']:
if record['์ฌ๊ฑด๋ช
'] and query in record['์ฌ๊ฑด๋ช
']:
# ์ฌ๊ฑด๋ช
์ผ๋ก ๊ฒ์ ์ ์ฌ๊ฑด๋ฒํธ๋ง ๋ฐํ
response.append(f"์ฌ๊ฑด๋ฒํธ: {record['์ฌ๊ฑด๋ฒํธ']}")
elif record['์ฌ๊ฑด๋ฒํธ'] == query:
# ์ฌ๊ฑด๋ฒํธ๋ก ๊ฒ์ ์ ์ ์ฒด ๋ด์ฉ ๋ฐํ
detail = (
f"ํ๋ก์ ๋ณด์ผ๋ จ๋ฒํธ: {record['ํ๋ก์ ๋ณด์ผ๋ จ๋ฒํธ']}\n"
f"์ฌ๊ฑด๋ช
: {record['์ฌ๊ฑด๋ช
']}\n"
f"์ฌ๊ฑด๋ฒํธ: {record['์ฌ๊ฑด๋ฒํธ']}\n"
f"์ ๊ณ ์ผ์: {record['์ ๊ณ ์ผ์']}\n"
f"์ ๊ณ : {record['์ ๊ณ ']}\n"
f"๋ฒ์๋ช
: {record['๋ฒ์๋ช
']}\n"
f"์ฌ๊ฑด์ข
๋ฅ๋ช
: {record['์ฌ๊ฑด์ข
๋ฅ๋ช
']}\n"
f"ํ๊ฒฐ์ ํ: {record['ํ๊ฒฐ์ ํ']}\n"
f"ํ์์ฌํญ: {record['ํ์์ฌํญ']}\n"
f"ํ๊ฒฐ์์ง: {record['ํ๊ฒฐ์์ง']}\n"
f"์ฐธ์กฐ์กฐ๋ฌธ: {record['์ฐธ์กฐ์กฐ๋ฌธ']}\n"
f"์ฐธ์กฐํ๋ก: {record['์ฐธ์กฐํ๋ก']}\n"
f"์ ๋ฌธ: {record['์ ๋ฌธ']}\n"
)
response.append(detail)
return "\n".join(response) if response else "๊ด๋ จ ๋ฒ๋ฅ ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์์ต๋๋ค."
if __name__ == "__main__":
discord_client = MyClient(intents=intents)
discord_client.run(os.getenv('DISCORD_TOKEN'))
|