Update app.py

app.py

@@ -1,127 +1,34 @@
-import os
-import streamlit as st
-from PyPDF2 import PdfReader
-from sentence_transformers import SentenceTransformer
-import faiss
-import matplotlib.pyplot as plt
-import numpy as np
-from groq import Groq
-
-GROQ_API_KEY = "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"
-client = Groq(api_key=GROQ_API_KEY)
-
-# Initialize Embedding Model
-embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
-
-# Initialize FAISS Index
-embedding_dim = 384  # Dimensionality of 'all-MiniLM-L6-v2'
-faiss_index = faiss.IndexFlatL2(embedding_dim)
-
-# Store Metadata
-metadata_store = []
-
-def extract_text_from_pdf(pdf_file):
-    pdf_reader = PdfReader(pdf_file)
-    text = ""
-    for page in pdf_reader.pages:
-        text += page.extract_text()
-    return text
-
-def chunk_text(text, chunk_size=500):
-    words = text.split()
-    return [' '.join(words[i:i+chunk_size]) for i in range(0, len(words), chunk_size)]
-
-def generate_embeddings(chunks):
-    return embedding_model.encode(chunks)
-
-def store_embeddings(embeddings, metadata):
-    faiss_index.add(np.array(embeddings))
-    metadata_store.extend(metadata)
-
-def retrieve_relevant_chunks(query, k=5):
-    query_embedding = embedding_model.encode([query])
-    distances, indices = faiss_index.search(query_embedding, k)
-    
-    valid_results = [
-        (metadata_store[i], distances[0][j])
-        for j, i in enumerate(indices[0])
-        if i < len(metadata_store)
-    ]
-    return valid_results
-
-def identify_research_gaps():
-    gap_summary = []
+def identify_major_research_gaps():
+    # Extract high-level contradictions or differences
+    key_differences = []
     for i, chunk_1 in enumerate(metadata_store):
         for j, chunk_2 in enumerate(metadata_store):
             if i >= j:  # Avoid duplicate comparisons
                 continue
+            # Example heuristic to identify key differences
             if "not" in chunk_1["chunk"] and "is" in chunk_2["chunk"]:
-                gap_summary.append(f"Potential contradiction between chunks {i} and {j}")
-    return gap_summary
-
-def ask_groq_api(question, context):
-    chat_completion = client.chat.completions.create(
-        messages=[{"role": "user", "content": f"{context}\n\n{question}"}],
-        model="llama3-8b-8192"
-    )
-    return chat_completion.choices[0].message.content
-
-# Streamlit App
-st.set_page_config(page_title="Research Analyzer", page_icon="📚")
-
-st.title("📄 Research Paper Analyzer with Gap Identification")
-st.write("Easily analyze and identify gaps in your research papers. 🧠")
-
-uploaded_files = st.file_uploader("📤 Upload PDF Files", accept_multiple_files=True, type="pdf")
-
-if uploaded_files:
-    st.success("📂 Files uploaded successfully! Processing...")
-    
-    all_chunks = []
-    all_metadata = []
-    
-    for uploaded_file in uploaded_files:
-        text = extract_text_from_pdf(uploaded_file)
-        chunks = chunk_text(text)
-        embeddings = generate_embeddings(chunks)
-        metadata = [{"chunk": chunk, "file_name": uploaded_file.name} for chunk in chunks]
-        store_embeddings(embeddings, metadata)
-        all_chunks.extend(chunks)
-        all_metadata.extend(metadata)
-
-    st.success("✅ Files processed and embeddings created!")
-
-    if st.button("📚 View Topic Summaries"):
-        for chunk in all_chunks[:3]:
-            st.write("🔹", chunk)
-
-    user_question = st.text_input("❓ Ask a question about the uploaded papers:")
-    if user_question:
-        relevant_chunks = retrieve_relevant_chunks(user_question)
-        if relevant_chunks:
-            context = "\n\n".join([chunk['chunk'] for chunk, _ in relevant_chunks])
-            answer = ask_groq_api(user_question, context)
-            st.write("**Answer:**", answer)
-        else:
-            st.write("⚠️ No relevant sections found for your question.")
-
-    if st.button("🔍 Identify Research Gaps"):
-        research_gaps = identify_research_gaps()
-        if research_gaps:
-            st.write("### 🛠️ Research Gaps Identified:")
-            for gap in research_gaps:
-                st.write(f"🔸 {gap}")
-        else:
-            st.write("✅ No significant research gaps identified.")
-
-    if st.button("📊 Generate Scatter Plot"):
-        st.write("📈 Generating scatter plot for methods vs. results...")
-        # Example scatter plot (replace with real data)
-        x = np.random.rand(10)
-        y = np.random.rand(10)
-        plt.scatter(x, y)
-        plt.xlabel("Methods")
-        plt.ylabel("Results")
-        st.pyplot(plt)
-
-    st.text_area("📝 Annotate Your Insights:", height=100, key="annotations")
+                key_differences.append(
+                    f"Potential inconsistency in methodologies or interpretations between sections of the document."
+                )
+            elif "should" in chunk_1["chunk"] and "must" in chunk_2["chunk"]:
+                key_differences.append(
+                    f"Divergence in recommendations or conclusions observed between sections."
+                )
+
+    # Summarize key points for display
+    if key_differences:
+        summary = (
+            f"The analysis identified several key areas of divergence in the reviewed research papers:\n\n"
+            + "\n".join(f"• {difference}" for difference in set(key_differences))
+            + "\n\n"
+            "These findings indicate areas where further investigation or clarification may be beneficial."
+        )
+        return summary
+    else:
+        return "No significant research gaps or inconsistencies were identified across the reviewed papers."
+
+# Replace logic inside the button event
+if st.button("🔍 Identify Research Gaps"):
+    research_gap_summary = identify_major_research_gaps()
+    st.write("### 🛠️ Research Gaps Identified:")
+    st.write(research_gap_summary)