Update app.py

app.py

@@ -1,7 +1,108 @@
-import gradio as gr
+import os
+import streamlit as st
+from langchain_chroma import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.chains.question_answering import load_qa_chain
+from langchain.memory import ConversationBufferMemory
+from langchain_core.prompts import PromptTemplate
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+from sentence_transformers import SentenceTransformer
 
-def greet(name):
-    return "Hello " + name + "!!"
+st.title("Chatbot")
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Load environment variables
+load_dotenv()
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+assert GROQ_API_KEY, "GROQ_API_KEY environment variable not set."
+
+# One-time setup in session state
+if 'initialized' not in st.session_state:
+    st.session_state.initialized = False
+
+    try:
+        with st.spinner("Initializing..."):
+            # Initialize embeddings model
+            model_path = "sentence-transformers/all-MiniLM-L12-v2"  # Use a smaller, faster model
+            
+            st.session_state.embedding_function = HuggingFaceEmbeddings(
+                model_name=model_path,
+                model_kwargs={'device': 'cpu'},
+                encode_kwargs={'normalize_embeddings': False}
+            )
+            
+            # Set up document search
+            persist_directory = "doc_db"
+            st.session_state.docsearch = Chroma(
+                persist_directory=persist_directory,
+                embedding_function=st.session_state.embedding_function
+            )
+
+            # Initialize ChatGroq model
+            st.session_state.chat_model = ChatGroq(
+                model="llama-3.1-8b-instant",
+                temperature=0,
+                api_key=GROQ_API_KEY
+            )
+
+            # Define prompt template and memory
+            template = """You are a chatbot having a conversation with a human. Your name is Devrim.
+            Given the following extracted parts of a long document and a question, create a final answer. If the answer is not in the document or irrelevant, just say that you don't know, don't try to make up an answer.
+            {context}
+            {chat_history}
+            Human: {human_input}
+            Chatbot:"""
+
+            prompt = PromptTemplate(
+                input_variables=["chat_history", "human_input", "context"], template=template
+            )
+            st.session_state.memory = ConversationBufferMemory(memory_key="chat_history", input_key="human_input")
+
+            # Load QA chain
+            st.session_state.qa_chain = load_qa_chain(
+                llm=st.session_state.chat_model, 
+                chain_type="stuff", 
+                memory=st.session_state.memory, 
+                prompt=prompt
+            )
+
+            st.session_state.initialized = True
+            st.success("Initialization successful.")
+
+    except Exception as e:
+        st.session_state.initialized = False
+        st.error(f"Initialization failed: {e}")
+
+# Clear chat history buttons
+if st.button("Clear Chat History"):
+    if 'memory' in st.session_state:
+        st.session_state.memory.clear()
+    st.experimental_rerun()  # Refresh the app to reflect the cleared history
+
+# Display chat history if initialized
+if st.session_state.initialized and 'memory' in st.session_state:
+    if st.session_state.memory.buffer_as_messages:
+        for message in st.session_state.memory.buffer_as_messages:
+            if message.type == "ai":
+                st.chat_message(name="ai", avatar="🤖").write(message.content)
+            else:
+                st.chat_message(name="human", avatar="👤").write(message.content)
+
+# Input for new query
+query = st.chat_input("Ask something")
+if query:
+    try:
+        with st.spinner("Answering..."):
+            # Perform similarity search and get response
+            docs = st.session_state.docsearch.similarity_search(query, k=1)  # Reduced k for speed
+            response = st.session_state.qa_chain(
+                {"input_documents": docs, "human_input": query}, 
+                return_only_outputs=True
+            )["output_text"]
+
+            # Display new message
+            st.chat_message(name="human", avatar="👤").write(query)
+            st.chat_message(name="ai", avatar="🤖").write(response)
+
+    except Exception as e:
+        st.error(f"An error occurred: {e}")