Create app.py

app.py

@@ -0,0 +1,95 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+import os
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+
+# --- Get API key from environment variable ---
+GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY", "")
+
+# Assume PDF file is already in the current directory
+PDF_FILE = "Librarianship.pdf"  # Change this to your PDF filename
+
+
+def get_pdf_text(pdf_file):
+    text = ""
+    with open(pdf_file, "rb") as file:
+        pdf_reader = PdfReader(file)
+        for page in pdf_reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
+    return text
+
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    return text_splitter.split_text(text)
+
+
+def get_vector_store(text_chunks, api_key):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("/tmp/faiss_index")
+
+
+def get_conversational_chain(api_key):
+    prompt_template = """
+    You are a helpful assistant that only answers based on the context provided from the PDF document.
+    Do not use any external knowledge or assumptions. If the answer is not found in the context below, reply with "I don't know."
+    Context:
+    {context}
+    Question:
+    {question}
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0, google_api_key=api_key)
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+
+def user_input(user_question, api_key):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+    new_db = FAISS.load_local("/tmp/faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+    chain = get_conversational_chain(api_key)
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+    st.write("Reply: ", response["output_text"])
+
+
+def main():
+    st.set_page_config(page_title="Chat PDF")
+    st.header("Retrieval-Augmented Generation - Gemini 2.0")
+    st.markdown("---")
+
+    api_key = GOOGLE_API_KEY
+
+    if not api_key:
+        st.error("Please set the GOOGLE_API_KEY environment variable.")
+        st.stop()
+
+    if "pdf_processed" not in st.session_state:
+        st.session_state["pdf_processed"] = False
+
+    if not st.session_state["pdf_processed"]:
+        with st.spinner("Processing PDF..."):
+            raw_text = get_pdf_text(PDF_FILE)
+            text_chunks = get_text_chunks(raw_text)
+            get_vector_store(text_chunks, api_key)
+            st.session_state["pdf_processed"] = True
+            st.success("PDF processed! You can now ask questions.")
+
+    st.subheader("Ask a question about your PDF")
+    user_question = st.text_input("Ask a question")
+    if user_question:
+        user_input(user_question, api_key)
+
+
+if __name__ == "__main__":
+    main()