Update app.py

app.py

@@ -1,35 +1,87 @@
-from langchain.agents import create_csv_agent
-from langchain.llms import OpenAI
+
+
+import streamlit as st
+from langchain.document_loaders import DirectoryLoader, TextLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI as LangchainOpenAI
 from dotenv import load_dotenv
 import os
-import streamlit as st
 
+# Load environment variables
+load_dotenv()
+
+# Initialize Streamlit
+st.set_page_config(page_title="Ask the Docs")
+st.header("Ask the Docs 📚")
+st.write('Unleash your credit card superpowers')
+st.write('Revolutionize the way you track and manage your credit cards.')
+st.write('Experience hassle-free financial control with Anek.')
+
+# Initialize chat session state with a welcome message
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "Welcome to CreditCardChat! Your personal credit card advisor 😉. Drop in your queries."}]
+
+# Display previous chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+
+# Load Documents from Directory
+text_loader_kwargs = {'encoding': 'utf-8'}
+loader = DirectoryLoader(r'C:\Users\iamma\Documents\JupyterHub\MODELS\V1\credit_card_texts17AUG', glob="**/*.txt", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
+docs = loader.load()
 
-def main():
-    load_dotenv()
+# Embedding Configuration
+openai_api_key = os.getenv('OPENAI_API_KEY')
+embedding = OpenAIEmbeddings(openai_api_key=openai_api_key)
 
-    # Load the OpenAI API key from the environment variable
-    if os.getenv("OPENAI_API_KEY") is None or os.getenv("OPENAI_API_KEY") == "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":
-        print("OPENAI_API_KEY is not set")
-        exit(1)
-    else:
-        print("OPENAI_API_KEY is set")
+try:
+    embeddings = embedding.embed_documents([doc.page_content for doc in docs])
+except Exception as e:
+    st.write(f"An error occurred: {e}")
+    st.stop()
 
-    st.set_page_config(page_title="Ask your CSV")
-    st.header("Ask your CSV 📈")
+# FAISS Database Configuration
+try:
+    db = FAISS.from_documents(docs, embedding)
+except Exception as e:
+    st.write(f"An error occurred while creating FAISS database: {e}")
+    st.stop()
 
-    csv_file = st.file_uploader("Upload a CSV file", type="csv")
-    if csv_file is not None:
+# Initialize Langchain components
+llm = LangchainOpenAI(openai_api_key=openai_api_key)
+qa_chain = RetrievalQA.from_chain_type(llm, retriever=db.as_retriever())
 
-        agent = create_csv_agent(
-            OpenAI(temperature=0), csv_file, verbose=True)
+# User-provided question
+# ... (previous imports and initialization)
 
-        user_question = st.text_input("Ask a question about your CSV: ")
+# User-provided question
+if user_question := st.chat_input("Ask a question about the documents: "):
+    # Manually append user's question to session state and display immediately
+    st.session_state.messages.append({"role": "user", "content": user_question})
+    
+    # Display chat messages including the new question
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.write(message["content"])
+    
+    # Placeholder for assistant's response
+    with st.chat_message("assistant"):
+        assistant_placeholder = st.empty()
 
-        if user_question is not None and user_question != "":
-            with st.spinner(text="In progress..."):
-                st.write(agent.run(user_question))
+    try:
+        # Get the model's response
+        result_dict = qa_chain({"query": user_question})
+        result = result_dict.get("result", "I don't know.")
 
+        # Update assistant's message
+        assistant_placeholder.write(result)
+        st.session_state.messages.append({"role": "assistant", "content": result})
 
-if __name__ == "__main__":
-    main()
+    except Exception as e:
+        assistant_placeholder.write(f"An error occurred: {e}")
+        st.session_state.messages.append({"role": "assistant", "content": f"An error occurred: {e}"})