Update app.py

app.py

@@ -18,7 +18,7 @@ arising from the use of this tool. Please use responsibly and cross-check result
 # ---------------------
 # Model Setup
 # ---------------------
-MODEL_NAME = "allenai/scibert_scivocab_cased"  # Example model for tokenization/embedding
+MODEL_NAME = "allenai/scibert_scivocab_cased"  # Example tokenizer model (not directly used for summarization)
 SUMMARIZATION_MODEL = "allenai/led-base-16384"  # Example summarization model with a large context window
 
 # Load summarization model and tokenizer
@@ -29,8 +29,6 @@ summarizer_model = AutoModelForSeq2SeqLM.from_pretrained(SUMMARIZATION_MODEL)
 # Utility Functions
 # ---------------------
 def extract_text_from_pdf(pdf_file):
-    # This function extracts text from a PDF file. Requires PyPDF2 or similar library.
-    # For Hugging Face Spaces, PyPDF2 often works.
     try:
         import PyPDF2
         reader = PyPDF2.PdfReader(pdf_file)
@@ -42,12 +40,10 @@ def extract_text_from_pdf(pdf_file):
         return f"Error reading PDF: {e}"
 
 def clean_text(text):
-    # Basic cleaning function
     text = re.sub(r'\s+', ' ', text).strip()
     return text
 
 def summarize_text(text):
-    # Summarize the given text
     inputs = summarizer_tokenizer(text, return_tensors="pt", truncation=True, max_length=16384)
     with torch.no_grad():
         summary_ids = summarizer_model.generate(
@@ -61,25 +57,51 @@ def summarize_text(text):
     summary = summarizer_tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return summary
 
+def extract_methods(text):
+    # A very naive approach: search for paragraphs containing method-related keywords
+    # and return them as "Key Methods".
+    methods_keywords = ["method", "methods", "technique", "procedure", "protocol", "experimental approach"]
+    paragraphs = re.split(r'\n+|\. ', text)
+    method_sentences = [p.strip() for p in paragraphs if any(kw in p.lower() for kw in methods_keywords)]
+    if method_sentences:
+        return " ".join(method_sentences)
+    else:
+        return "No explicit methods found using simple keyword search."
+
+def extract_references(text):
+    # A naive approach for references:
+    # Look for patterns like "et al., 20XX", "(Author, Year)", or numeric citations [XX].
+    # This is a heuristic and may produce false positives.
+    # Common patterns: 
+    # - Something like "Smith et al., 2020"
+    # - (Smith et al., 2020)
+    # - [1], [2], etc., at the end of sentences.
+    references_pattern = r"([A-Z][a-zA-Z]+ et al\.,?\s?\d{4})|(\(\S+ et al\.,?\s?\d{4}\))|(\[\d+\])"
+    refs_found = re.findall(references_pattern, text)
+    # refs_found will be a list of tuples due to multiple groups, flatten them:
+    flat_refs = []
+    for tup in refs_found:
+        for ref in tup:
+            if ref:
+                flat_refs.append(ref.strip())
+    flat_refs = list(set(flat_refs))  # remove duplicates
+    if flat_refs:
+        return "Possible References Found:\n" + "\n".join(flat_refs)
+    else:
+        return "No explicit references found using simple pattern search."
+
 def analyze_text(text):
-    # In a more elaborate system, you might:
-    # 1. Extract main findings using IE or NER.
-    # 2. Identify methods mentioned.
-    # 3. Extract references (regex patterns for citations).
-    # Here we just do a simple summarization.
     text_clean = clean_text(text)
     if len(text_clean) < 50:
-        return "Please provide a longer text snippet or PDF."
+        return "Please provide a longer text snippet or PDF.", "", ""
     
     summary = summarize_text(text_clean)
-    
-    # Dummy logic for key methods and references (in a real app, use NLP-based extraction)
-    methods = "Key methods extraction is not yet implemented."  
-    references = "Reference extraction is not yet implemented."
+    methods = extract_methods(text_clean)
+    references = extract_references(text_clean)
     return summary, methods, references
 
 def process_input(pdf_file, text_snippet):
-    # If PDF is provided, extract text from PDF
+    # If PDF is provided, extract text
     input_text = ""
     if pdf_file is not None:
         input_text = extract_text_from_pdf(pdf_file)