Create app.py

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from langchain.document_loaders import PyPDFLoader
+from transformers import pipeline
+
+# ----------------------------
+# APP CONFIG
+# ----------------------------
+st.set_page_config(page_title="📘 PDF Question Answering", layout="wide")
+st.title("📘 PDF Question Answering App")
+st.markdown("Upload a PDF and ask questions about its content.")
+
+# ----------------------------
+# GLOBAL VARIABLES
+# ----------------------------
+qa_chain = None
+
+# ----------------------------
+# FUNCTIONS
+# ----------------------------
+def load_pdf(pdf_file):
+    loader = PyPDFLoader(pdf_file.name)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=100)
+    docs = text_splitter.split_documents(documents)
+    return docs
+
+def build_vectorstore(docs):
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vectorstore = FAISS.from_documents(docs, embeddings)
+    return vectorstore
+
+def build_qa_chain(vectorstore):
+    llm = HuggingFacePipeline(
+        pipeline=pipeline(
+            "text2text-generation",
+            model="google/flan-t5-base",
+            max_length=512,
+            temperature=0
+        )
+    )
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=vectorstore.as_retriever(search_kwargs={"k":3}),
+        chain_type="stuff"
+    )
+    return qa_chain
+
+# ----------------------------
+# STREAMLIT UI
+# ----------------------------
+uploaded_file = st.file_uploader("Upload a PDF", type=["pdf"])
+
+if uploaded_file:
+    with st.spinner("Processing PDF..."):
+        docs = load_pdf(uploaded_file)
+        vectorstore = build_vectorstore(docs)
+        qa_chain = build_qa_chain(vectorstore)
+    st.success("✅ PDF uploaded & processed. You can now ask questions!")
+
+if qa_chain:
+    query = st.text_input("Ask a question about the PDF:")
+    if query:
+        with st.spinner("Searching..."):
+            answer = qa_chain.run(query)
+        st.markdown("### Answer:")
+        st.write(answer)