104 lines
3.2 KiB
Python
104 lines
3.2 KiB
Python
from typing import List, Dict, Any
|
|
import json
|
|
import asyncio
|
|
import aiohttp
|
|
import time
|
|
import re
|
|
|
|
|
|
|
|
model_url = "http://192.168.130.206:4001/v1"
|
|
model = "google/gemma-3-27b-it"
|
|
|
|
|
|
class LLMModel:
|
|
def __init__(self):
|
|
|
|
self.instruction = """
|
|
You are a helpful assistant that help to me to modify and change the input question.
|
|
I will give you a question and its text and you must replace the words of question with synonyms or similar words.
|
|
|
|
## Important:
|
|
- replace the words of question with synonyms or similar words.
|
|
|
|
-the question must be in persian language.
|
|
|
|
return the question nothing else.
|
|
"""
|
|
|
|
async def run_llm(self, session, question, text):
|
|
"""
|
|
Run the llm model.
|
|
Args:
|
|
session: The session to use for the request.
|
|
question: The question to evaluate the text.
|
|
text: The text to evaluate.
|
|
Returns:
|
|
The result of the text.
|
|
"""
|
|
headers = {"Content-Type": "application/json"}
|
|
|
|
input_message = f"""{{"question": "{question}", "text": "{text}"}}"""
|
|
messages = [{"role": "system", "content": self.instruction}, {"role": "user", "content": input_message}]
|
|
|
|
payload = {
|
|
"model": model,
|
|
"messages": messages,
|
|
"max_tokens": 100
|
|
}
|
|
try:
|
|
async with session.post(model_url + "/chat/completions", headers=headers, json=payload) as resp:
|
|
resp.raise_for_status()
|
|
response = await resp.json()
|
|
|
|
result = response['choices'][0]['message']['content']
|
|
print(f"question: {question}")
|
|
print(f"result: {result}")
|
|
print("--------------------------------")
|
|
|
|
return result
|
|
|
|
except Exception as e:
|
|
try:
|
|
print(f"Error in llm model {response}: {e}")
|
|
except:
|
|
print(f"Error in llm model: {e}")
|
|
return ""
|
|
|
|
|
|
async def run_llm_async(self, question_list, text_list):
|
|
"""
|
|
Send all chunk requests concurrently.
|
|
Args:
|
|
question_list: The list of questions.
|
|
text_list: The list of texts.
|
|
Returns:
|
|
The list of results.
|
|
"""
|
|
async with aiohttp.ClientSession() as session:
|
|
tasks = [self.run_llm(session, question, text) for question, text in zip(question_list, text_list)]
|
|
results = await asyncio.gather(*tasks)
|
|
return results
|
|
|
|
|
|
def modify_question_llm(self, query_list: List[str], text_list: List[str]) -> List[Dict[str, Any]]:
|
|
"""
|
|
Modify question of the documents based on the query using the LLM model.
|
|
Args:
|
|
query_list: The list of queries.
|
|
text_list: The list of texts.
|
|
Returns:
|
|
The list of modified questions.
|
|
"""
|
|
if not text_list:
|
|
return []
|
|
|
|
start_time = time.time()
|
|
results = asyncio.run(self.run_llm_async(query_list, text_list))
|
|
end_time = time.time()
|
|
# print(f"Time taken for llm model: {end_time - start_time} seconds")
|
|
|
|
return results
|
|
|
|
|