Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,92 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+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 langchain.llms import HuggingFaceHub
+from htmlTemplates import css, bot_template, user_template
+import os
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
+    return text
+
+
+def get_text_chunks(text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+    return text_splitter.split_text(text)
+
+
+def get_vectorstore(text_chunks):
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+
+
+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
+    )
+
+    return ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory
+    )
+
+
+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 your PDFs", page_icon="📚")
+    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 PDFs 📚")
+    user_question = st.text_input("Ask something about your PDFs:")
+    if user_question:
+        handle_userinput(user_question)
+
+    with st.sidebar:
+        st.subheader("Your documents")
+        pdf_docs = st.file_uploader("Upload PDFs", 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()