Update app.py

app.py

@@ -7,33 +7,30 @@ from langchain_community.llms import llamacpp
 from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
-from langchain.chains import create_history_aware_retriever, create_retrieval_chain,ConversationalRetrievalChain
+from langchain.chains import create_history_aware_retriever, create_retrieval_chain, ConversationalRetrievalChain
 from langchain.document_loaders import TextLoader
 from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_community.chat_message_histories.streamlit import StreamlitChatMessageHistory
 from langchain.prompts import PromptTemplate
-from langchain.chains import create_history_aware_retriever, create_retrieval_chain
 from langchain.vectorstores import Chroma
-from utills import load_txt_documents , split_docs,  load_uploaded_documents,retriever_from_chroma
-from langchain.text_splitter import TokenTextSplitter,RecursiveCharacterTextSplitter
-
+from utils import load_txt_documents, split_docs, load_uploaded_documents, retriever_from_chroma
+from langchain.text_splitter import TokenTextSplitter, RecursiveCharacterTextSplitter
 
 script_dir = os.path.dirname(os.path.abspath(__file__))
-data_path =  os.path.join(script_dir, "data/")
+data_path = os.path.join(script_dir, "data/")
 model_path = os.path.join(script_dir, 'qwen2-0_5b-instruct-q4_0.gguf')
 store = {}
 
-
 model_name = "sentence-transformers/all-mpnet-base-v2"
 model_kwargs = {'device': 'cpu'}
 encode_kwargs = {'normalize_embeddings': True}
 
-
 hf = HuggingFaceEmbeddings(
     model_name=model_name,
     model_kwargs=model_kwargs,
     encode_kwargs=encode_kwargs
 )
+
 def get_vectorstore(text_chunks):
     model_name = "sentence-transformers/all-mpnet-base-v2"
     model_kwargs = {'device': 'cpu'}
@@ -42,14 +39,11 @@ def get_vectorstore(text_chunks):
         model_name=model_name,
         model_kwargs=model_kwargs,
         encode_kwargs=encode_kwargs
-)
+    )
 
-    vectorstore = Chroma.from_documents(texts=text_chunks, embedding=hf,persist_directory="docs/chroma/")
+    vectorstore = Chroma.from_documents(texts=text_chunks, embedding=hf, persist_directory="docs/chroma/")
     return vectorstore
 
-
-
-
 def get_pdf_text(pdf_docs):
     text = ""
     for pdf in pdf_docs:
@@ -58,7 +52,6 @@ def get_pdf_text(pdf_docs):
             text += page.extract_text()
     return text
 
-
 def get_text_chunks(text):
     text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
         separator="\n",
@@ -69,31 +62,29 @@ def get_text_chunks(text):
     chunks = text_splitter.split_text(text)
     return chunks
 
-
-
 def create_conversational_rag_chain(vectorstore):
     retriever = retriever_from_chroma(docs, hf, "mmr", 6)
 
     callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
-    llm = LlamaCpp(
-                model_path= os.path.join(script_dir, 'qwen2-0_5b-instruct-q4_0.gguf'),
-                n_gpu_layers=1,
-                temperature=0.1,
-                top_p=0.9,
-                n_ctx=22000,
-                max_tokens=200,
-                repeat_penalty=1.7,
-                callback_manager=callback_manager,
-                verbose=False,
-            )
+    llm = llamacpp.LlamaCpp(
+        model_path=os.path.join(script_dir, 'qwen2-0_5b-instruct-q4_0.gguf'),
+        n_gpu_layers=1,
+        temperature=0.1,
+        top_p=0.9,
+        n_ctx=22000,
+        max_tokens=200,
+        repeat_penalty=1.7,
+        callback_manager=callback_manager,
+        verbose=False,
+    )
 
     contextualize_q_system_prompt = """Given a context, chat history and the latest user question
     which maybe reference context in the chat history, formulate a standalone question
     which can be understood without the chat history. Do NOT answer the question,
     just reformulate it if needed and otherwise return it as is."""
 
-    ha_retriever = history_aware_retriever(llm, retriever, contextualize_q_system_prompt)
+    ha_retriever = create_history_aware_retriever(llm, retriever, contextualize_q_system_prompt)
 
     qa_system_prompt = """You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Be as informative as possible, be polite and formal.\n{context}"""
 
@@ -121,13 +112,12 @@ def create_conversational_rag_chain(vectorstore):
         )
 
     return create_rag_chain()
-conversational_rag_chain = create_conversational_rag_chain()
 
 def main(conversational_rag_chain):
     """Main function for the Streamlit app."""
     # Initialize chat history if not already present in session state
     msgs = st.session_state.get("chat_history", StreamlitChatMessageHistory(key="special_app_key"))
-    chain_with_history = conversational_rag_chain
+    chain_with_history = create_conversational_rag_chain()
 
     st.title("Conversational RAG Chatbot")
 
@@ -144,8 +134,9 @@ def main(conversational_rag_chain):
 
         # Display retrieved documents (if any and present in response)
         if "docs" in response and response["documents"]:
-                st.write(f"Expanding document {index+1}...")
-            display_documents(docs, expand_document)  # Pass click function
+            for index, doc in enumerate(response["documents"]):
+                with st.expander(f"Document {index + 1}"):
+                    st.write(doc)
 
     # Update chat history in session state
     st.session_state["chat_history"] = msgs