Create app.py

app.py

@@ -0,0 +1,111 @@
+import os
+import streamlit as st
+from PyPDF2 import PdfReader
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import matplotlib.pyplot as plt
+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')  # Open-source model
+
+# Initialize FAISS index
+dimension = 384  # Embedding size of the model
+index = faiss.IndexFlatL2(dimension)
+
+# Helper Functions
+def extract_text_from_pdfs(files):
+    """Extract text from multiple PDF files."""
+    all_text = ""
+    for file in files:
+        reader = PdfReader(file)
+        for page in reader.pages:
+            all_text += page.extract_text()
+    return all_text
+
+def create_chunks(text, chunk_size=500):
+    """Split text into chunks of a specified size."""
+    words = text.split()
+    return [' '.join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
+
+def generate_embeddings(chunks):
+    """Generate embeddings for the given chunks."""
+    return embedding_model.encode(chunks, convert_to_numpy=True)
+
+def query_groq(prompt):
+    """Query the Groq model for a response."""
+    response = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="llama3-8b-8192"
+    )
+    return response.choices[0].message.content
+
+def visualize_comparative_insights(methods, results):
+    """Generate a scatter plot of methods vs. results."""
+    plt.figure(figsize=(8, 6))
+    plt.scatter(methods, results, c='blue', alpha=0.7)
+    plt.title("Methods vs. Results")
+    plt.xlabel("Methods")
+    plt.ylabel("Results")
+    st.pyplot(plt)
+
+# Streamlit App
+st.title("Research Paper Analyzer")
+st.write("Upload research papers, ask questions, and gain AI-driven insights!")
+
+# Step 1: PDF Upload
+uploaded_files = st.file_uploader("Upload your PDF files", type=["pdf"], accept_multiple_files=True)
+if uploaded_files:
+    with st.spinner("Processing the PDFs..."):
+        # Extract text
+        pdf_text = extract_text_from_pdfs(uploaded_files)
+        st.success("PDFs processed successfully!")
+
+        # Step 2: Chunking
+        chunks = create_chunks(pdf_text)
+        st.info(f"Documents split into {len(chunks)} chunks.")
+
+        # Step 3: Embedding Creation
+        embeddings = generate_embeddings(chunks)
+        index.add(np.array(embeddings))
+        st.success("Embeddings stored in FAISS database.")
+
+        # Step 4: Query
+        user_query = st.text_input("Ask a question:")
+        if user_query:
+            with st.spinner("Searching and generating a response..."):
+                # Embed user query
+                query_embedding = embedding_model.encode([user_query], convert_to_numpy=True)
+
+                # Search in FAISS
+                distances, indices = index.search(np.array(query_embedding), k=5)
+                relevant_chunks = [chunks[i] for i in indices[0]]
+
+                # Combine retrieved chunks as context
+                context = " ".join(relevant_chunks)
+
+                # Query Groq model
+                prompt = f"Context: {context}\n\nQuestion: {user_query}\n\nAnswer:"
+                answer = query_groq(prompt)
+
+                # Display response
+                st.write("### Answer:")
+                st.write(answer)
+
+        # Step 5: Comparative Insights
+        if st.button("Generate Comparative Insights"):
+            # Example data for visualization
+            methods = [1, 2, 3, 4, 5]  # Replace with actual methods data
+            results = [3.2, 4.1, 5.6, 4.8, 6.0]  # Replace with actual results data
+            visualize_comparative_insights(methods, results)
+
+        # Step 6: Bibliography Suggestions
+        if st.button("Suggest Related Papers"):
+            related_papers = ["Paper A", "Paper B", "Paper C"]  # Replace with actual suggestions
+            st.write("### Suggested Papers:")
+            for paper in related_papers:
+                st.write(f"- {paper}")