Update app.py

app.py

@@ -1,106 +1,53 @@
 import streamlit as st
 from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from transformers import pipeline
 import os
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
-import google.generativeai as genai
-from langchain.vectorstores import FAISS
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain.chains.question_answering import load_qa_chain
-from langchain.prompts import PromptTemplate
 from dotenv import load_dotenv
 
+# Load environment variables
 load_dotenv()
-os.getenv("GOOGLE_API_KEY")
-genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
-
-
-
-
+os.getenv("HUGGINGFACE_TOKEN")
 
+# Initialize the Hugging Face pipeline for question-answering
+qa_pipeline = pipeline(
+    "question-answering",
+    model="deepset/roberta-base-squad2",
+    tokenizer="deepset/roberta-base-squad2",
+)
 
 def get_pdf_text(pdf_docs):
-    text=""
+    text = ""
     for pdf in pdf_docs:
-        pdf_reader= PdfReader(pdf)
+        pdf_reader = PdfReader(pdf)
         for page in pdf_reader.pages:
-            text+= page.extract_text()
-    return  text
-
-
-
-def get_text_chunks(text):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
-    chunks = text_splitter.split_text(text)
-    return chunks
-
-
-def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-
-def get_conversational_chain():
-
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-
-    Answer:
-    """
-
-    model = ChatGoogleGenerativeAI(model="gemini-pro",
-                             temperature=0.3)
-
-    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):
-    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
-    
-    new_db = FAISS.load_local("faiss_index", embeddings)
-    docs = new_db.similarity_search(user_question)
-
-    chain = get_conversational_chain()
-
-    
-    response = chain(
-        {"input_documents":docs, "question": user_question}
-        , return_only_outputs=True)
-
-    print(response)
-    st.write("Reply: ", response["output_text"])
-
-
-
+            text += page.extract_text() + "\n"
+    return text
 
 def main():
-    st.set_page_config("Chat PDF")
-    st.header("Chat with PDF using Gemini💁")
-
-    user_question = st.text_input("Ask a Question from the PDF Files")
+    st.set_page_config(page_title="Chat with PDF", page_icon="📄")
+    st.header("Chat with PDF using Hugging Face 🤖")
 
-    if user_question:
-        user_input(user_question)
+    # Upload PDF files
+    pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True)
 
-    with st.sidebar:
-        st.title("Menu:")
-        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
-        if st.button("Submit & Process"):
+    if st.button("Submit & Process"):
+        if pdf_docs:
             with st.spinner("Processing..."):
                 raw_text = get_pdf_text(pdf_docs)
-                text_chunks = get_text_chunks(raw_text)
-                get_vector_store(text_chunks)
-                st.success("Done")
+                st.session_state.raw_text = raw_text  # Store raw text in session state
+                st.success("PDF processed successfully!")
+        else:
+            st.warning("Please upload at least one PDF file.")
 
+    # User input for questions
+    if 'raw_text' in st.session_state:
+        user_question = st.text_input("Ask a Question from the PDF Files")
 
+        if user_question:
+            response = qa_pipeline(question=user_question, context=st.session_state.raw_text)
+            st.write("Answer:", response['answer'])
+    else:
+        st.info("Please upload PDF files to start chatting.")
 
 if __name__ == "__main__":
-    main()
+    main()