Upload 4 files

.env

@@ -0,0 +1,2 @@
+GROQ_API_KEY = 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
+NLTK_DATA=C:\Users\sanath\AppData\Roaming\nltk_data\tokenizers\punkt_tab

Dockerfile

@@ -0,0 +1,39 @@
+# Use the official Python image from the Docker Hub
+FROM python:3.10
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y poppler-utils && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set up the working directory
+WORKDIR /code
+
+# Copy the current directory contents into the container
+COPY requirements.txt /code/requirements.txt
+
+# Install the requirements from the requirements.txt
+RUN pip install --no-cache-dir -r /code/requirements.txt
+
+# Create a new user and switch to it
+RUN useradd -m user
+USER user
+
+# Set the environment variables for the user's home and path
+ENV HOME=/home/user \
+    PATH=$HOME/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container's $HOME/app folder, setting owner to user
+COPY --chown=user . $HOME/app
+
+# Copy the .env file into the container
+COPY --chown=user .env $HOME/app/.env
+
+# Make port 7860 available to the world outside this container
+EXPOSE 7860
+
+# Start the Streamlit app
+CMD ["streamlit", "run", "app.py"]

app.py

@@ -0,0 +1,99 @@
+from dotenv import load_dotenv
+import streamlit as st
+from langchain_community.document_loaders import UnstructuredPDFLoader
+from langchain_text_splitters.character import CharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_groq import ChatGroq
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+import os
+import nltk
+
+# Load environment variables
+load_dotenv()
+
+import nltk
+nltk.download('punkt_tab')
+
+
+working_dir = os.getcwd()
+
+def load_documents(file_path):
+    loader = UnstructuredPDFLoader(file_path)
+    documents = loader.load()
+    return documents
+
+def setup_vectorstore(documents):
+    embeddings = HuggingFaceEmbeddings()
+    text_splitter = CharacterTextSplitter(
+        separator="/n", 
+        chunk_size=1000,
+        chunk_overlap=200
+    )
+    doc_chunks = text_splitter.split_documents(documents)
+    vectorstores = FAISS.from_documents(doc_chunks, embeddings)
+    return vectorstores
+
+def create_chain(vectorstores):
+    llm = ChatGroq(
+        model="llama-3.1-70b-versatile",
+        temperature=0
+    )
+    retriever = vectorstores.as_retriever()
+    memory = ConversationBufferMemory(
+        llm=llm,
+        output_key="answer",
+        memory_key="chat_history",
+        return_messages=True
+    )
+    chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=retriever,
+        memory=memory,
+        verbose=True
+    )
+    return chain
+
+st.set_page_config(
+    page_title="Chat with your documents",
+    page_icon="📑",
+    layout="centered"
+)
+
+st.title("📝Chat With your docs 😎")
+
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+uploaded_file = st.file_uploader(label="Upload your PDF")
+
+if uploaded_file:
+    file_path = f"{working_dir}{uploaded_file.name}"
+    with open(file_path, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+
+    if "vectorstores" not in st.session_state:
+        st.session_state.vectorstores = setup_vectorstore(load_documents(file_path))
+
+    if "conversation_chain" not in st.session_state:
+        st.session_state.conversation_chain = create_chain(st.session_state.vectorstores)
+
+for message in st.session_state.chat_history:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+user_input = st.chat_input("Ask any questions relevant to uploaded pdf")
+
+if user_input:
+    st.session_state.chat_history.append({"role": "user", "content": user_input})
+    with st.chat_message("user"):
+        st.markdown(user_input)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.conversation_chain({"question": user_input})
+        assistant_response = response["answer"]
+        st.markdown(assistant_response)
+        st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
+
+

requirements.txt

@@ -0,0 +1,13 @@
+python-dotenv==1.0.1
+streamlit==1.37.0
+langchain-community==0.2.10
+langchain-text-splitters==0.2.2
+langchain-groq==0.1.9
+unstructured
+unstructured[pdf]
+faiss-cpu
+transformers==4.43.3
+sentence-transformers==3.0.1
+nltk==3.9.1
+pi_heif
+