Refactor summary generation to use Gradio client for TextRank, Luhn, LSA, and LexRank summarizers; improve error handling and logging

main.py

@@ -17,20 +17,16 @@ def create_client(api_key):
 
 def generate_summary(client, corpus):
     response = {}
-    print("Generating Math Summary")
     math_summary = generate_math_summary(corpus)
     if not math_summary:
         print("Error generating Math Summary")
         response['summary_status'] = "error"
         response['summary'] = None
-        response['mindmap_status'] = "success"
+        response['mindmap_status'] = "error"
         response['mindmap'] = None
         return response
     else:
-        print("Math Summary Generated Successfully")
-        print("Generating NLP Summary and Mindmap")
         response = generate_nlp_summary_and_mindmap(client, corpus)
-        print("NLP Summary and Mindmap Generated Successfully")
         return response
 
 def main(corpus):

math_summarizer.py

@@ -1,54 +1,40 @@
-from sumy.parsers.plaintext import PlaintextParser
-from sumy.nlp.tokenizers import Tokenizer
-from sumy.summarizers.text_rank import TextRankSummarizer
-from sumy.summarizers.luhn import LuhnSummarizer
-from sumy.summarizers.lex_rank import LexRankSummarizer
-from sumy.summarizers.lsa import LsaSummarizer
-from sumy.nlp.stemmers import Stemmer
-from sumy.utils import get_stop_words
-import nltk
+from gradio_client import Client
 import threading
 
-LANGUAGE = "english"
-SENTENCES_COUNT = 15
-
 def generate_textrank_summary(research_paper_text):
-    nltk.download('punkt', quiet=True)
-    nltk.download('punkt_tab', quiet=True)
-    parser = PlaintextParser.from_string(research_paper_text, Tokenizer(LANGUAGE))
-    stemmer = Stemmer(LANGUAGE)
-    summarizer = TextRankSummarizer(stemmer)
-    summarizer.stop_words = get_stop_words(LANGUAGE)
-    sentences = summarizer(parser.document, SENTENCES_COUNT)
-    summary = ""
-    for sentence in sentences:
-        summary += str(sentence) + ""
+    print("Generating TextRank summary")
+    client = Client("raannakasturi/TextRankSummarizer")
+    summary = client.predict(
+        text_corpus=research_paper_text,
+        api_name="/textrank_summarizer"
+    )
     return summary
 
 def generate_luhn_summary(research_paper_text):
-    nltk.download('punkt', quiet=True)
-    nltk.download('punkt_tab', quiet=True)
-    parser = PlaintextParser.from_string(research_paper_text, Tokenizer(LANGUAGE))
-    stemmer = Stemmer(LANGUAGE)
-    summarizer = LuhnSummarizer(stemmer)
-    summarizer.stop_words = get_stop_words(LANGUAGE)
-    sentences = summarizer(parser.document, SENTENCES_COUNT)
-    summary = ""
-    for sentence in sentences:
-        summary += str(sentence) + ""
+    print("Generating Luhn summary")
+    client = Client("raannakasturi/LuhnSummarizer")
+    summary = client.predict(
+        text_corpus=research_paper_text,
+        api_name="/luhn_summarizer"
+    )
     return summary
 
 def generate_lsa_summary(research_paper_text):
-    nltk.download('punkt', quiet=True)
-    nltk.download('punkt_tab', quiet=True)
-    parser = PlaintextParser.from_string(research_paper_text, Tokenizer(LANGUAGE))
-    stemmer = Stemmer(LANGUAGE)
-    summarizer = LsaSummarizer(stemmer)
-    summarizer.stop_words = get_stop_words(LANGUAGE)
-    sentences = summarizer(parser.document, SENTENCES_COUNT)
-    summary = ""
-    for sentence in sentences:
-        summary += str(sentence) + ""
+    print("Generating LSA summary")
+    client = Client("raannakasturi/LSASummarizer")
+    summary = client.predict(
+        text_corpus=research_paper_text,
+        api_name="/lsa_summarizer"
+    )
+    return summary
+
+def generate_lexrank_summary(research_paper_text):
+    print("Generating LexRank summary")
+    client = Client("raannakasturi/LexRankSummarizer")
+    summary = client.predict(
+        text_corpus=research_paper_text,
+        api_name="/lexrank_summarizer"
+    )
     return summary
 
 def sanitize_text(input_string):
@@ -64,9 +50,10 @@ def sanitize_text(input_string):
         raise
 
 def generate_math_summary(research_paper_text):
+    print("Generating math summary")
     sanitized_text = sanitize_text(research_paper_text)
     try:
-        textrank_summary = luhn_summary = lsa_summary = None
+        textrank_summary = luhn_summary = lsa_summary = lexrank_summary = None
         def run_textrank():
             nonlocal textrank_summary
             textrank_summary = generate_textrank_summary(sanitized_text)
@@ -76,15 +63,20 @@ def generate_math_summary(research_paper_text):
         def run_lsa():
             nonlocal lsa_summary
             lsa_summary = generate_lsa_summary(sanitized_text)
+        def run_lexrank():
+            nonlocal lexrank_summary
+            lexrank_summary = generate_lexrank_summary(sanitized_text)
         threads = []
         threads.append(threading.Thread(target=run_textrank))
         threads.append(threading.Thread(target=run_luhn))
         threads.append(threading.Thread(target=run_lsa))
+        threads.append(threading.Thread(target=run_lexrank))
         for thread in threads:
             thread.start()
         for thread in threads:
             thread.join()
-        math_summary = textrank_summary.replace("\n", "") + f"\n {'-'*30} \n" + luhn_summary.replace("\n", "") + f"\n {'-'*30} \n" + lsa_summary.replace("\n", "")
+        math_summary = textrank_summary.replace("\n", "") + luhn_summary.replace("\n", "") + lsa_summary.replace("\n", "") + lexrank_summary.replace("\n", "")
+        print("Math summary generated")
         return math_summary
     except Exception as e:
         print(e)

nlp_summarizer.py

@@ -53,4 +53,5 @@ def generate_nlp_summary_and_mindmap(client, temp_summary):
         thread.start()
     for thread in threads:
         thread.join()
+    print("NLP Summary and Mindmap generated")
     return response