Upload 2 files

llm5.py

@@ -0,0 +1,103 @@
+import streamlit as st
+from PyPDF2 import PdfFileReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import GooglePalmEmbeddings
+from langchain.llms import GooglePalm
+from langchain.vectorstores import FAISS
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+import os
+from langchain.document_loaders import UnstructuredURLLoader
+import tempfile
+
+# Set your Google API Key here
+os.environ['GOOGLE_API_KEY'] = 'YOUR_API_KEY'
+
+direct_links = [
+    "https://zollege.in/exams/comedk-uget",
+    "https://zollege.in/exams/comedk-uget/cutoff",
+    'https://www.iimrohtak.ac.in/panel/assets/images/prospectus/16881265522765.pdf',
+    'https://www.iimrohtak.ac.in/panel/assets/images/lor/16884755042121.pdf',
+    'https://www.iimrohtak.ac.in/dpm.php',
+    'https://www.iimrohtak.ac.in/dpm-admission.php'
+    'https://www.iimrohtak.ac.in/areas-of-specialisation.php',
+    'https://www.iimrohtak.ac.in/financial-assistance.php',
+    'https://www.iimrohtak.ac.in/panel/assets/images/prospectus/16903487969776.pdf',
+    'https://www.iimrohtak.ac.in/faqs-for-dpm.php',
+    'https://www.iimrohtak.ac.in/dpm-student.php',
+    'https://www.iimrohtak.ac.in/publication.php',
+    'https://www.iimrohtak.ac.in/dpm-contact.php',
+    'https://www.iimrohtak.ac.in/ipm.php'
+]
+
+# Example PDF files (replace with your own file paths)
+pdf_files = ["sample.pdf", "sample2.pdf"]
+
+def get_data(direct_links, pdf_files):
+    direct_link_loader = UnstructuredURLLoader(urls=direct_links)
+    direct_link_data = direct_link_loader.load()
+    pdf_data = get_pdf_text(pdf_files)
+    return direct_link_data + pdf_data
+
+def get_pdf_text(pdf_files):
+    text = ""
+    for pdf_file in pdf_files:
+        with open(pdf_file, "rb") as file:
+            pdf_reader = PdfFileReader(file)
+            for page_num in range(pdf_reader.numPages):
+                text += pdf_reader.getPage(page_num).extractText()
+    return text
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vector_store(text_chunks):
+    embeddings = GooglePalmEmbeddings()
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    return vector_store
+
+def get_conversational_chain(vector_store):
+    llm = GooglePalm()
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=vector_store.as_retriever(), memory=memory)
+    return conversation_chain
+
+def user_input(user_question):
+    response = st.session_state.conversation({'question': user_question})
+    st.session_state.chatHistory = response['chat_history']
+    for i, message in enumerate(st.session_state.chatHistory):
+        if i % 2 == 0:
+            st.write("Human: ", message.content)
+        else:
+            st.write("Bot: ", message.content)
+
+def main():
+    st.set_page_config("Chat with Multiple PDFs")
+    st.header("Chat with Multiple PDF 💬")
+    user_question = st.text_input("Ask a Question from the PDF Files")
+    if "conversation" not in st.session_state:
+        st.session_state.conversation = None
+    if "chatHistory" not in st.session_state:
+        st.session_state.chatHistory = None
+    if user_question:
+        user_input(user_question)
+    with st.sidebar:
+        st.title("Settings")
+        st.subheader("Upload your Documents")
+        pdf_uploads = st.file_uploader("Upload your PDF Files and Click on the Process Button", accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                pdf_files = [tempfile.NamedTemporaryFile(delete=False).name for _ in pdf_uploads]
+                for uploaded_file, pdf_file in zip(pdf_uploads, pdf_files):
+                    with open(pdf_file, "wb") as file:
+                        file.write(uploaded_file.read())
+                combined_text = get_data(direct_links, pdf_files)
+                text_chunks = get_text_chunks(combined_text)
+                vector_store = get_vector_store(text_chunks)
+                st.session_state.conversation = get_conversational_chain(vector_store)
+                st.success("Done")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,3 @@
+langchain
+streamlit
+PyPDF2