Upload 4 files

app.py

@@ -0,0 +1,98 @@
+import os
+import utils
+import streamlit as st
+from streaming import StreamHandler
+
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import PyPDFLoader
+from langchain.memory import ConversationBufferMemory
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import ConversationalRetrievalChain
+from langchain.vectorstores import DocArrayInMemorySearch
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+
+st.header('Chatbot for AEO ')
+st.write('Please upload the necessary files about AEO in the sidebar and ask questions in the chat.')
+
+
+
+
+class CustomDataChatbot:
+
+    def __init__(self):
+        self.oepn_ai_key =  utils.configure_openai_api_key()
+        self.openai_model = "gpt-3.5-turbo"
+
+    def save_file(self, file):
+        folder = 'tmp'
+        if not os.path.exists(folder):
+            os.makedirs(folder)
+        
+        file_path = f'./{folder}/{file.name}'
+        with open(file_path, 'wb') as f:
+            f.write(file.getvalue())
+        return file_path
+
+    @st.spinner('Analyzing documents..')
+    def setup_qa_chain(self, uploaded_files):
+        # Load documents
+        docs = []
+        for file in uploaded_files:
+            file_path = self.save_file(file)
+            loader = PyPDFLoader(file_path)
+            docs.extend(loader.load())
+        
+        # Split documents
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1500,
+            chunk_overlap=200
+        )
+        splits = text_splitter.split_documents(docs)
+
+        # Create embeddings and store in vectordb
+       
+        embeddings = OpenAIEmbeddings(openai_api_key = self.oepn_ai_key)
+        vectordb = DocArrayInMemorySearch.from_documents(splits, embeddings)
+
+        # Define retriever
+        retriever = vectordb.as_retriever(
+            search_type='mmr',
+            search_kwargs={'k':2, 'fetch_k':4}
+        )
+
+        # Setup memory for contextual conversation        
+        memory = ConversationBufferMemory(
+            memory_key='chat_history',
+            return_messages=True
+        )
+
+        # Setup LLM and QA chain
+        llm = ChatOpenAI(model_name=self.openai_model, temperature=0, streaming=True)
+        qa_chain = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory, verbose=True)
+        return qa_chain
+
+    @utils.enable_chat_history
+    def main(self):
+
+        # User Inputs
+        uploaded_files = st.sidebar.file_uploader(label='Upload PDF files', type=['pdf'], accept_multiple_files=True)
+        if not uploaded_files:
+            st.error("Please upload PDF documents to continue!")
+            st.stop()
+
+        user_query = st.chat_input(placeholder="Ask me anything!")
+
+        if uploaded_files and user_query:
+            qa_chain = self.setup_qa_chain(uploaded_files)
+
+            utils.display_msg(user_query, 'user')
+
+            with st.chat_message("assistant"):
+                st_cb = StreamHandler(st.empty())
+                response = qa_chain.run(user_query, callbacks=[st_cb])
+                st.session_state.messages.append({"role": "assistant", "content": response})
+
+if __name__ == "__main__":
+    obj = CustomDataChatbot()
+    obj.main()

requirements.txt

@@ -0,0 +1,8 @@
+langchain==0.0.228
+openai==0.27.8
+streamlit==1.24.0
+duckduckgo-search==3.8.3
+pypdf==3.12.0
+sentence-transformers==2.2.2
+docarray==0.32.1
+tiktoken

streaming.py

@@ -0,0 +1,11 @@
+from langchain.callbacks.base import BaseCallbackHandler
+
+class StreamHandler(BaseCallbackHandler):
+    
+    def __init__(self, container, initial_text=""):
+        self.container = container
+        self.text = initial_text
+
+    def on_llm_new_token(self, token: str, **kwargs):
+        self.text += token
+        self.container.markdown(self.text)

utils.py

@@ -0,0 +1,55 @@
+import os
+import random
+import streamlit as st
+
+#decorator
+def enable_chat_history(func):
+    if os.environ.get("OPENAI_API_KEY"):
+
+        # to clear chat history after swtching chatbot
+        current_page = func.__qualname__
+        if "current_page" not in st.session_state:
+            st.session_state["current_page"] = current_page
+        if st.session_state["current_page"] != current_page:
+            try:
+                st.cache_resource.clear()
+                del st.session_state["current_page"]
+                del st.session_state["messages"]
+            except:
+                pass
+
+        # to show chat history on ui
+        if "messages" not in st.session_state:
+            st.session_state["messages"] = [{"role": "assistant", "content": "How can I help you?"}]
+        for msg in st.session_state["messages"]:
+            st.chat_message(msg["role"]).write(msg["content"])
+
+    def execute(*args, **kwargs):
+        func(*args, **kwargs)
+    return execute
+
+def display_msg(msg, author):
+    """Method to display message on the UI
+
+    Args:
+        msg (str): message to display
+        author (str): author of the message -user/assistant
+    """
+    st.session_state.messages.append({"role": author, "content": msg})
+    st.chat_message(author).write(msg)
+
+def configure_openai_api_key():
+    openai_api_key = st.sidebar.text_input(
+        label="OpenAI API Key",
+        type="password",
+        value=st.session_state['OPENAI_API_KEY'] if 'OPENAI_API_KEY' in st.session_state else '',
+        placeholder="sk-..."
+        )
+    if openai_api_key:
+        st.session_state['OPENAI_API_KEY'] = openai_api_key
+        os.environ['OPENAI_API_KEY'] = openai_api_key
+    else:
+        st.error("Please add your OpenAI API key to continue.")
+        st.info("Obtain your key from this link: https://platform.openai.com/account/api-keys")
+        st.stop()
+    return openai_api_key