Upload 2 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"

app.py

@@ -0,0 +1,98 @@
+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
+nltk.download('punkt')
+nltk_data_dir = os.getenv("NLTK_DATA")
+
+
+load_dotenv()
+
+working_dir = os.path.dirname(os.path.abspath(__file__))
+
+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})