Update app.py

app.py

@@ -7,7 +7,93 @@
 import streamlit as st
 from dotenv import load_dotenv
 
+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 htmlTemplates import css, bot_template, user_template
+from langchain.llms import HuggingFaceHub
+
+
+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
+
+#  Chunk size and overlap must not exceed the models capacity!
+#
+def get_text_chunks(text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=800,    #  1000
+        chunk_overlap=200,
+        length_function=len
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+
+def get_vectorstore(text_chunks):
+    # embeddings = OpenAIEmbeddings()
+
+    #  pip install InstructorEmbedding
+    #  pip install sentence-transformers==2.2.2
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+
+    #  from InstructorEmbedding import INSTRUCTOR
+    # model = INSTRUCTOR('hkunlp/instructor-xl')
+    # sentence = "3D ActionSLAM: wearable person tracking in multi-floor environments"
+    # instruction = "Represent the Science title:"
+    # embeddings = model.encode([[instruction, sentence]])
+
+    # embeddings = model.encode(text_chunks)
+    print('have Embeddings:   ')
+
+    # text_chunks="this is a test"
+    #   FAISS,  Chroma and other vector databases
+    #
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    print('FAISS succeeds:   ')
+
+    return vectorstore
+
+def get_conversation_chain(vectorstore):
+    # llm = ChatOpenAI()
+    #  llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+    #  google/bigbird-roberta-base     facebook/bart-large
+    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)
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory,
+    )
+    return conversation_chain
+
+def handle_userinput(user_question):
+
+    response = st.session_state.conversation({'question': user_question})
+    # response = st.session_state.conversation({'summarization': user_question})
+    st.session_state.chat_history = response['chat_history']
+
+
+    # st.empty()
+
+    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)
+