Add application file

app.py

@@ -0,0 +1,127 @@
+import os
+import streamlit as st
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.embeddings import HuggingFaceInstructEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_openai import ChatOpenAI
+from langchain_community.llms import HuggingFaceHub
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain_community.document_loaders import DirectoryLoader
+from htmlTemplates import css, bot_template, user_template
+from langchain.globals import set_verbose
+set_verbose(False)  # Updated function call
+
+
+def read_files_from_directory(directory):
+    files = []
+    for filename in os.listdir(directory):
+        if filename.endswith(".pdf"):
+            files.append(os.path.join(directory, filename))
+    return files
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+def get_text_chunks(raw_text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+        )
+    chunks = text_splitter.split_text(raw_text)
+    return chunks
+
+def get_vector_store(text_chunks):
+    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    embeddings = OpenAIEmbeddings(openai_api_key=os.getenv('OPENAI_API_KEY'))
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+def get_conversation_chain(vectorstore):
+    llm = ChatOpenAI(openai_api_key=os.getenv('OPENAI_API_KEY'))
+   # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+#    llm = HuggingFaceHub(repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct", model_kwargs={"temperature":0.5, "max_length":512})
+  #  llm = HuggingFaceHub(repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct")
+
+    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory
+    )
+    return conversation_chain
+
+# get handler user input method
+def handle_user_input(user_question):
+    if st.session_state.conversation is not None:
+
+        response = st.session_state.conversation({'question': user_question})
+        st.session_state.chat_history = response['chat_history']
+
+        for i, message in enumerate(st.session_state.chat_history):
+            if i % 2 == 0:
+                st.write(user_template.replace(
+                    "{{MSG}}", message.content), unsafe_allow_html=True)
+            else:
+                st.write(bot_template.replace(
+                    "{{MSG}}", message.content), unsafe_allow_html=True)
+    else:
+        st.write("Please upload PDFs and click process")
+
+def main():
+    load_dotenv()
+
+    st.set_page_config(page_title="Onki AI Assistant - Chat with multiple PDFs", page_icon=":books:")
+    st.write(css, unsafe_allow_html=True)
+    
+    #load knowledge data PDF
+    files = read_files_from_directory('./data')
+    raw_knowledge_text = get_pdf_text(files)
+    raw_knowledge_chunks = get_text_chunks(raw_knowledge_text)
+    vectorstore_knowledge = get_vector_store(raw_knowledge_chunks)
+
+    st.session_state.conversation = get_conversation_chain(vectorstore_knowledge)
+
+    if "conversation" not in st.session_state:
+        st.session_state.conversation = None
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = None
+
+    st.header("Chat with multiple PDFs :books:")
+    user_question = st.text_input("Ask a question about your documents:")
+
+    if user_question:
+        handle_user_input(user_question)
+    
+    with st.sidebar:
+
+        st.subheader("Your documents")
+        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                # get pdf text
+                raw_text = get_pdf_text(pdf_docs)
+
+                # get the text chunks
+                text_chunks = get_text_chunks(raw_text)
+
+                # create vector store
+                vectorstore = get_vector_store(text_chunks)
+
+                vectorstore.merge_from(vectorstore_knowledge)
+
+                #create conversation chain
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+
+if __name__ == '__main__':
+    main()

htmlTemplates.py

@@ -0,0 +1,44 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    background-color: #2b313e
+}
+.chat-message.bot {
+    background-color: #475063
+}
+.chat-message .avatar {
+  width: 20%;
+}
+.chat-message .avatar img {
+  max-width: 78px;
+  max-height: 78px;
+  border-radius: 50%;
+  object-fit: cover;
+}
+.chat-message .message {
+  width: 80%;
+  padding: 0 1.5rem;
+  color: #fff;
+}
+'''
+
+bot_template = '''
+<div class="chat-message bot">
+    <div class="avatar">
+        <img src="https://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.png" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="avatar">
+        <img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,9 @@
+#unstructured[pdf]
+#python-magic
+streamlit
+python-dotenv
+PyPDF2
+langchain
+langchain_openai
+langchain_community
+faiss-cpu