Create app.py

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+import PyPDF2
+from groq import Groq
+import os
+
+# Set up Groq API key
+os.environ["GROQ_API_KEY"] = "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"
+
+# Initialize Groq client
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+
+# Function to extract PDF content
+def extract_pdf_content(pdf_file):
+    pdf_text = ""
+    reader = PyPDF2.PdfReader(pdf_file)
+    for page in reader.pages:
+        pdf_text += page.extract_text()
+    return pdf_text
+
+# Function to chunk text
+def chunk_text(text, chunk_size=1000, overlap=200):
+    chunks = []
+    start = 0
+    while start < len(text):
+        end = start + chunk_size
+        chunk = text[start:end]
+        chunks.append(chunk)
+        start += chunk_size - overlap
+    return chunks
+
+# Function to find relevant chunks
+def find_relevant_chunks(chunks, query, num_chunks=3):
+    return chunks[:num_chunks]  # Simple retrieval
+
+# Chatbot function
+def chatbot_response(user_query, chunks):
+    relevant_chunks = find_relevant_chunks(chunks, user_query)
+    combined_context = "\n\n".join(relevant_chunks)
+    context = f"PDF Content:\n{combined_context}\n\nUser Query: {user_query}"
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": context}],
+        model="llama-3.3-70b-versatile",
+    )
+    return chat_completion.choices[0].message.content
+
+# Streamlit UI
+st.title("PDF Query Chatbot")
+st.write("Upload a PDF and