Create app.py

app.py

@@ -0,0 +1,61 @@
+import os
+import streamlit as st
+import PyPDF2
+import docx
+from sentence_transformers import SentenceTransformer
+from groq import Groq
+from transformers import pipeline
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+# Set up Groq API
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+
+# Load embedding model
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Title and UI
+st.set_page_config(page_title="A&Q From a File", page_icon="📖")
+st.title("📖 A&Q From a File")
+
+# File Upload
+uploaded_file = st.file_uploader("Upload a PDF or DOCX file", type=["pdf", "docx"])
+
+if uploaded_file:
+    text = ""
+    
+    # Extract text from PDF
+    if uploaded_file.type == "application/pdf":
+        pdf_reader = PyPDF2.PdfReader(uploaded_file)
+        for page in pdf_reader.pages:
+            text += page.extract_text() + "\n"
+    
+    # Extract text from DOCX
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        doc = docx.Document(uploaded_file)
+        for para in doc.paragraphs:
+            text += para.text + "\n"
+    
+    # Chunking the text
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500, chunk_overlap=50
+    )
+    chunks = text_splitter.split_text(text)
+    
+    # Embed chunks
+    embeddings = embedder.encode(chunks, convert_to_tensor=True)
+    
+    # Query Input
+    user_query = st.text_input("Ask a question about the file:")
+    if user_query:
+        
+        # Query Groq API
+        chat_completion = client.chat.completions.create(
+            messages=[
+                {"role": "user", "content": f"Answer this question based on the uploaded document: {user_query}"}
+            ],
+            model="llama-3.3-70b-versatile",
+        )
+        
+        # Display answer
+        st.subheader("Answer:")
+        st.write(chat_completion.choices[0].message.content)