Upload 5 files

.env

@@ -0,0 +1 @@
+GROQ_API_KEY = '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'

Dockerfile

@@ -0,0 +1,34 @@
+# Use the official Python 3.9 image as the base image
+FROM python:3.9
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy the requirements file to the working directory
+COPY requirements.txt /app/requirements.txt
+
+# Install the required dependencies
+RUN pip install --no-cache-dir --upgrade -r /app/requirements.txt
+
+# Set environment variables for Streamlit and other configurations
+ENV PYTHONUNBUFFERED=1 \
+    PATH="/home/user/.local/bin:$PATH" \
+    HOME=/home/user
+
+# Set up a new user named "user"
+RUN useradd user
+
+# Switch to the "user" user
+USER user
+
+# Set the working directory to the user's home directory
+WORKDIR /home/user/app
+
+# Copy the app content to the container and change ownership to the user
+COPY --chown=user . /home/user/app
+
+# Expose the port Streamlit will use
+EXPOSE 8501
+
+# Run the Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

Groq_app.py

@@ -0,0 +1,121 @@
+import streamlit as st 
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template
+from langchain.llms import HuggingFaceHub
+from langchain_community.llms import Ollama
+from langchain_groq import ChatGroq
+import os 
+
+
+
+
+#extraction of the text from the pdfs
+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
+
+#dividing the raw text in different chunks
+def get_text_chunks(text):
+    text_splitter = CharacterTextSplitter(
+        separator= "\n" ,
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function= len
+        )
+    
+    chunks = text_splitter.split_text(text)
+    return chunks 
+
+#creating a vector store embeddings from huggingface 
+def get_vectorstore(text_chunks):
+   # embeddings = OpenAIEmbeddings()
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+#creating a conversation chain to store the context for follow up question
+def get_conversation_chain(vectorstore, groq_api_key):
+
+    #llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+    #llm = Ollama(model="llama2")
+    llm=ChatGroq(groq_api_key=groq_api_key,
+             model_name="llama3-70b-8192")
+    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
+
+
+#handling the user input 
+def handle_userinput(user_question):
+    response = st.session_state.conversation({'question' : user_question})
+    #st.write(response)
+    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():
+    load_dotenv()
+    #os.environ['OPENAI_API_KEY']=os.getenv("OPENAI_API_KEY")
+    groq_api_key=os.getenv('GROQ_API_KEY')
+
+    st.set_page_config("Chat with your pdf!!!!", page_icon=":books:")
+
+    st.write(css, unsafe_allow_html=True)
+
+    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 your pdf!!! :books:")
+
+    #question section
+    user_question = st.text_input("Wanna ask something???")
+
+    if user_question:
+        handle_userinput(user_question)
+
+
+
+    with st.sidebar:
+        st.subheader("Your documents")
+        #generally supports single file at a time. Need the enable the option to access multiple files
+        pdf_docs = st.file_uploader("Upload your pdf file", type=["pdf"], accept_multiple_files=True)
+        if st.button("Process"):
+            with st.spinner("Processing"):
+                #get the pdf text 
+                raw_text = get_pdf_text(pdf_docs)
+
+                #get the text chunks 
+                text_chunks = get_text_chunks(raw_text)
+
+                #create the vector store with embeddings 
+                vectorstore = get_vectorstore(text_chunks)
+                
+                #create the conversation chain
+                st.session_state.conversation = get_conversation_chain(vectorstore, groq_api_key)
+
+
+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://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ2ovj66Fvluoa25tuClVVp4-caGbDPxVfdfg&s" 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://media.npr.org/assets/img/2013/05/06/tonystark_wide-92e2d9abcce4413d58f728f2b5f126cef71afd97.jpg">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,13 @@
+streamlit 
+pypdf2
+langchain
+langchain_core
+langchain_community
+langchain-groq
+python-dotenv
+faiss-cpu
+huggingface_hub
+openai
+InstructorEmbedding
+sentence-transformers==2.2.2
+torch