Update app.py
Browse files
app.py
CHANGED
|
@@ -1,3 +1,4 @@
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
from hazm import Normalizer, SentenceTokenizer
|
| 3 |
import os
|
|
@@ -517,10 +518,7 @@ import concurrent.futures
|
|
| 517 |
from hazm import Normalizer
|
| 518 |
from rapidfuzz import fuzz
|
| 519 |
from langchain.schema import SystemMessage, HumanMessage
|
| 520 |
-
from collections import Counter
|
| 521 |
-
import heapq
|
| 522 |
|
| 523 |
-
# مسیر پوشه اسناد
|
| 524 |
folder_path = '46'
|
| 525 |
normalizer = Normalizer()
|
| 526 |
|
|
@@ -546,34 +544,27 @@ def load_and_process_documents(path):
|
|
| 546 |
|
| 547 |
return doc_texts
|
| 548 |
|
| 549 |
-
# پردازش فایلها
|
| 550 |
doc_texts = load_and_process_documents(folder_path)
|
| 551 |
|
| 552 |
-
# خواندن استاپ وردها
|
| 553 |
with open("stopwords.txt", "r", encoding="utf-8") as f:
|
| 554 |
stop_words = set(line.strip() for line in f if line.strip())
|
| 555 |
|
| 556 |
-
# حذف استاپوردها از متن
|
| 557 |
def remove_stop_words(text, stop_words):
|
| 558 |
words = text.split()
|
| 559 |
return " ".join([word for word in words if word not in stop_words])
|
| 560 |
|
| 561 |
-
# حذف عبارات ایست
|
| 562 |
-
def remove_stop_phrases(text, stop_words):
|
| 563 |
-
for phrase in stop_words:
|
| 564 |
-
text = text.replace(phrase, "")
|
| 565 |
-
return text
|
| 566 |
-
|
| 567 |
-
# استخراج خطوط حاوی کلمات کوئری
|
| 568 |
def extract_keywords_from_text(text, query_words):
|
| 569 |
matched_lines = []
|
| 570 |
lines = text.split("\n")
|
|
|
|
| 571 |
for line in lines:
|
| 572 |
if any(query_word in line for query_word in query_words):
|
| 573 |
matched_lines.append(line)
|
| 574 |
return matched_lines
|
| 575 |
|
| 576 |
-
|
|
|
|
|
|
|
| 577 |
def summarize_text_by_frequency(text, num_sentences=1):
|
| 578 |
sentences = text.split('\n')
|
| 579 |
word_freq = Counter()
|
|
@@ -592,43 +583,48 @@ def summarize_text_by_frequency(text, num_sentences=1):
|
|
| 592 |
summarized_sentences = heapq.nlargest(num_sentences, sentence_scores, key=sentence_scores.get)
|
| 593 |
return "\n".join(summarized_sentences)
|
| 594 |
|
| 595 |
-
|
|
|
|
|
|
|
|
|
|
| 596 |
def find_closest_lines(query, doc_texts, stop_words, top_n=15):
|
| 597 |
cleaned_query = remove_stop_words(query, stop_words)
|
| 598 |
query_words = cleaned_query.split()
|
| 599 |
|
| 600 |
all_matched_lines = []
|
|
|
|
| 601 |
for filename, text in doc_texts.items():
|
| 602 |
matched_lines = extract_keywords_from_text(text, query_words)
|
| 603 |
for line in matched_lines:
|
| 604 |
-
similarity = fuzz.partial_ratio(query, line)
|
| 605 |
all_matched_lines.append((line, similarity))
|
| 606 |
-
|
| 607 |
all_matched_lines.sort(key=lambda x: x[1], reverse=True)
|
|
|
|
| 608 |
closest_lines = [line for line, _ in all_matched_lines[:top_n]]
|
| 609 |
|
| 610 |
return closest_lines
|
| 611 |
|
| 612 |
-
|
| 613 |
-
|
| 614 |
-
|
| 615 |
-
|
| 616 |
|
| 617 |
if query:
|
| 618 |
closest_lines = find_closest_lines(query, doc_texts, stop_words, top_n=15)
|
| 619 |
-
|
| 620 |
-
# حذف است
|
| 621 |
cleaned_closest_lines = [
|
| 622 |
-
|
| 623 |
-
|
| 624 |
]
|
| 625 |
-
|
| 626 |
-
# خلاصهسازی
|
| 627 |
summarized_text = summarize_text_by_frequency("\n".join(cleaned_closest_lines), num_sentences=1)
|
| 628 |
-
|
| 629 |
-
|
| 630 |
st.markdown(summarized_text)
|
| 631 |
|
|
|
|
| 632 |
if summarized_text:
|
| 633 |
prompt = f"""
|
| 634 |
لطفاً با توجه به سؤال زیر و محتوای خطوط مرتبط، یک پاسخ نهایی حرفهای، دقیق و روان تولید کن.
|
|
@@ -640,16 +636,18 @@ if query:
|
|
| 640 |
{summarized_text}
|
| 641 |
پاسخ نهایی:
|
| 642 |
"""
|
| 643 |
-
|
|
|
|
| 644 |
response = llm([
|
| 645 |
-
SystemMessage(content="تو رزم یار ارتش هستی و
|
| 646 |
HumanMessage(content=prompt)
|
| 647 |
])
|
| 648 |
-
|
|
|
|
| 649 |
rewritten = response.content.strip()
|
| 650 |
-
|
| 651 |
# نمایش نتیجه
|
| 652 |
st.markdown(f'<div class="chat-message">{rewritten}</div>', unsafe_allow_html=True)
|
| 653 |
-
|
| 654 |
else:
|
| 655 |
-
st.warning("هیچ خط مرتبطی پیدا نشد.")
|
|
|
|
| 1 |
+
|
| 2 |
import streamlit as st
|
| 3 |
from hazm import Normalizer, SentenceTokenizer
|
| 4 |
import os
|
|
|
|
| 518 |
from hazm import Normalizer
|
| 519 |
from rapidfuzz import fuzz
|
| 520 |
from langchain.schema import SystemMessage, HumanMessage
|
|
|
|
|
|
|
| 521 |
|
|
|
|
| 522 |
folder_path = '46'
|
| 523 |
normalizer = Normalizer()
|
| 524 |
|
|
|
|
| 544 |
|
| 545 |
return doc_texts
|
| 546 |
|
|
|
|
| 547 |
doc_texts = load_and_process_documents(folder_path)
|
| 548 |
|
|
|
|
| 549 |
with open("stopwords.txt", "r", encoding="utf-8") as f:
|
| 550 |
stop_words = set(line.strip() for line in f if line.strip())
|
| 551 |
|
|
|
|
| 552 |
def remove_stop_words(text, stop_words):
|
| 553 |
words = text.split()
|
| 554 |
return " ".join([word for word in words if word not in stop_words])
|
| 555 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 556 |
def extract_keywords_from_text(text, query_words):
|
| 557 |
matched_lines = []
|
| 558 |
lines = text.split("\n")
|
| 559 |
+
|
| 560 |
for line in lines:
|
| 561 |
if any(query_word in line for query_word in query_words):
|
| 562 |
matched_lines.append(line)
|
| 563 |
return matched_lines
|
| 564 |
|
| 565 |
+
from collections import Counter
|
| 566 |
+
import heapq
|
| 567 |
+
|
| 568 |
def summarize_text_by_frequency(text, num_sentences=1):
|
| 569 |
sentences = text.split('\n')
|
| 570 |
word_freq = Counter()
|
|
|
|
| 583 |
summarized_sentences = heapq.nlargest(num_sentences, sentence_scores, key=sentence_scores.get)
|
| 584 |
return "\n".join(summarized_sentences)
|
| 585 |
|
| 586 |
+
|
| 587 |
+
|
| 588 |
+
|
| 589 |
+
|
| 590 |
def find_closest_lines(query, doc_texts, stop_words, top_n=15):
|
| 591 |
cleaned_query = remove_stop_words(query, stop_words)
|
| 592 |
query_words = cleaned_query.split()
|
| 593 |
|
| 594 |
all_matched_lines = []
|
| 595 |
+
|
| 596 |
for filename, text in doc_texts.items():
|
| 597 |
matched_lines = extract_keywords_from_text(text, query_words)
|
| 598 |
for line in matched_lines:
|
| 599 |
+
similarity = fuzz.partial_ratio(query, line) # محاسبه شباهت خط با سوال
|
| 600 |
all_matched_lines.append((line, similarity))
|
| 601 |
+
|
| 602 |
all_matched_lines.sort(key=lambda x: x[1], reverse=True)
|
| 603 |
+
|
| 604 |
closest_lines = [line for line, _ in all_matched_lines[:top_n]]
|
| 605 |
|
| 606 |
return closest_lines
|
| 607 |
|
| 608 |
+
def remove_stop_phrases(text, stop_words):
|
| 609 |
+
for phrase in stop_words:
|
| 610 |
+
text = text.replace(phrase, "")
|
| 611 |
+
return text
|
| 612 |
|
| 613 |
if query:
|
| 614 |
closest_lines = find_closest_lines(query, doc_texts, stop_words, top_n=15)
|
| 615 |
+
|
| 616 |
+
# حذف استپوردها از خطوط و سپس پاکسازی نهایی متن
|
| 617 |
cleaned_closest_lines = [
|
| 618 |
+
remove_stop_phrases(line, stop_words)
|
| 619 |
+
for line in closest_lines
|
| 620 |
]
|
| 621 |
+
|
|
|
|
| 622 |
summarized_text = summarize_text_by_frequency("\n".join(cleaned_closest_lines), num_sentences=1)
|
| 623 |
+
|
| 624 |
+
summarized_cleaned = remove_stop_phrases(summarized_text, stop_words)
|
| 625 |
st.markdown(summarized_text)
|
| 626 |
|
| 627 |
+
|
| 628 |
if summarized_text:
|
| 629 |
prompt = f"""
|
| 630 |
لطفاً با توجه به سؤال زیر و محتوای خطوط مرتبط، یک پاسخ نهایی حرفهای، دقیق و روان تولید کن.
|
|
|
|
| 636 |
{summarized_text}
|
| 637 |
پاسخ نهایی:
|
| 638 |
"""
|
| 639 |
+
|
| 640 |
+
# ارسال پیام به مدل به صورت صحیح
|
| 641 |
response = llm([
|
| 642 |
+
SystemMessage(content="تو رزم یار ارتش هستی و از کتاب و دیتای موجود به سوالات پاسخ میدی."),
|
| 643 |
HumanMessage(content=prompt)
|
| 644 |
])
|
| 645 |
+
|
| 646 |
+
# فرض بر این است که خروجی مدل به صورت دیکشنری است
|
| 647 |
rewritten = response.content.strip()
|
| 648 |
+
|
| 649 |
# نمایش نتیجه
|
| 650 |
st.markdown(f'<div class="chat-message">{rewritten}</div>', unsafe_allow_html=True)
|
| 651 |
+
|
| 652 |
else:
|
| 653 |
+
st.warning("هیچ خط مرتبطی پیدا نشد.")
|