Upload 4 files

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>
+'''

python-version.txt

@@ -0,0 +1 @@
+3.9

rag_with_pdf.py

@@ -0,0 +1,99 @@
+# -*- coding: utf-8 -*-
+"""RAG With PDF.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1FVkw8Ozi4IN97pMN-vat02c3QHQoDkEJ
+"""
+
+!pip install streamlit PyPDF2 langchain-community
+
+import streamlit as st
+# from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template
+from langchain.llms import HuggingFaceHub
+
+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(text):
+  text_splitter=CharacterTextSplitter(
+      separator="\n",
+      chunks=1000,
+      chunk_overlap=200,
+      length_function=len
+  )
+  chunks=text_splitter.split_text(text)
+  return chunks
+
+def get_vectorstore(text_chunks):
+  embeddings=HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+  vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+  return vectorstore
+
+def get_conversation_chain(vectorstore):
+  llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+  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
+
+def handle_userinput(user_question):
+  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)
+
+def main():
+  st.set_page_config(page_title="Chat with My RAG",
+  page_icon=":books:")
+  st.write(css,unsafe_allow_html=True)
+
+  if "conversation" not in st.session_state:
+    st.session_state.conversation = None
+  else:
+    st.session_state.chat_history = None
+
+  st.header("Chat with My RAG :books:")
+  user_question=st.text_input("Ask a question about your documents:")
+  if user_question:
+    handle_userinput(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"):
+        raw_text =get_pdf_text(pdf_docs)
+
+        text_chunks = get_text_chunks(raw_text)
+
+        vectorstore = get_vectorstore(text_chunks)
+
+        st.session_state.conversation = get_conversation_chain(vectorstore)
+
+
+if __name__ == '__main__':
+  main()
+

requirements.txt

@@ -0,0 +1,14 @@
+langchain==0.0.184
+PyPDF2==3.0.1
+python-dotenv==1.0.0
+streamlit==1.18.1
+openai==0.27.6
+faiss-cpu==1.7.4
+altair==4
+tiktoken==0.4.0
+# uncomment to use huggingface llms
+# huggingface-hub==0.14.1
+
+# uncomment to use instructor embeddings
+# InstructorEmbedding==1.0.1
+# sentence-transformers==2.2.2