update app.py

app.py

@@ -10,6 +10,7 @@ from langchain.document_loaders import PyPDFLoader
 from langchain.document_loaders import TextLoader
 from langchain.document_loaders import Docx2txtLoader
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from dotenv import load_dotenv  # Add this line for loading environment variables
 import os
 import tempfile
 
@@ -30,7 +31,7 @@ def conversation_chat(query, chain, history):
     history.append((query, result["answer"]))
     return result["answer"]
 
-def display_chat_history():
+def display_chat_history(chain):
     reply_container = st.container()
     container = st.container()
 
@@ -48,8 +49,8 @@ def display_chat_history():
                     message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
                     message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
 
-def create_conversational_chain(vector_store, text_chunks):
-    st.write("Text chunks lengths:", [len(chunk) for chunk in text_chunks])  # Add this line to print lengths
+def create_conversational_chain(vector_store):
+    load_dotenv()
     replicate_api_token = "r8_AA3K1fhDykqLa5M74E5V0w5ss1z0P9S3foWJl"  # Replace with your actual token
     os.environ["REPLICATE_API_TOKEN"] = replicate_api_token
 
@@ -97,14 +98,13 @@ def main():
         text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
         text_chunks = text_splitter.split_documents(text)
 
-        # Create embeddings
-        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={'device': 'cpu'})
-        vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
-
-        # Create the chain object
-        chain = create_conversational_chain(vector_store, text_chunks)
+        st.write("Text chunks lengths:", [len(chunk) for chunk in text_chunks])
 
-        display_chat_history()
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+                                           model_kwargs={'device': 'cpu'})
+        vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
+        chain = create_conversational_chain(vector_store)
+        display_chat_history(chain)
 
 if __name__ == "__main__":
     main()