Create app.py

app.py

@@ -0,0 +1,114 @@
+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 langchain.llms import HuggingFaceHub
+# from htmlTemplates import css,user_template,bot_template
+from langchain.embeddings import HuggingFaceEmbeddings
+
+
+
+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',
+        chunk_size = 1000,
+        chunk_overlap = 200,
+        # length_fucntion = len(text)
+    )
+    chuncks = text_splitter.split_text(text)
+    return chuncks
+
+
+
+def get_vectorstore(text_chunks):
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+
+def get_conversations_chain(vectorstores):
+    llm = HuggingFaceHub(repo_id ='mistralai/Mistral-7B-Instruct-v0.3',model_kwargs={"temperature":0.5, "max_length":512},huggingfacehub_api_token=API_KEY)
+
+
+    memory = ConversationBufferMemory(
+        memory_key = 'chat_history',return_messages = True
+    )
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm = llm,
+        retriever = vectorstores.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():
+    load_dotenv()
+    st.set_page_config(page_title="Chat with multiple PDFs",
+                       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 multiple PDFs :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"):
+                # 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_vectorstore(text_chunks)
+
+                # create conversation chain
+                st.session_state.conversation = get_conversations_chain(
+                    vectorstore)
+
+
+if __name__ == '__main__':
+    main()