Create app.py

app.py

@@ -0,0 +1,45 @@
+import streamlit as st
+import PyPDF2
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.llms import Groq
+from dotenv import load_dotenv
+import os
+
+# Load environment variables
+load_dotenv()
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+# Streamlit UI
+st.title("📄 PDF Q&A Assistant")
+st.write("Upload a PDF and ask questions about its content!")
+
+# Upload PDF
+uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
+
+if uploaded_file:
+    # Extract text from PDF
+    pdf_loader = PyPDFLoader(uploaded_file)
+    documents = pdf_loader.load()
+    
+    # Split text into chunks for processing
+    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = text_splitter.split_documents(documents)
+    
+    # Create embeddings and store in FAISS vector database
+    embeddings = HuggingFaceEmbeddings()
+    vector_db = FAISS.from_documents(docs, embeddings)
+    retriever = vector_db.as_retriever()
+    
+    # Load Groq API model for Q&A
+    llm = Groq(api_key=GROQ_API_KEY, model_name="mixtral-8x7b")  # Change model as needed
+    qa_chain = RetrievalQA(llm=llm, retriever=retriever)
+    
+    # User input for questions
+    query = st.text_input("Ask a question about the PDF:")
+    if query:
+        answer = qa_chain.run(query)
+        st.write("**Answer:**", answer)