Update app.py

app.py

@@ -1,37 +1,33 @@
-
-from langchain.chains import RetrievalQA
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.callbacks.manager import CallbackManager
-#from langchain_community.llms import Ollama
-#from langchain_community.embeddings.ollama import OllamaEmbeddings
-from langchain_community.vectorstores import Chroma
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.document_loaders import PyPDFLoader
-from langchain.prompts import PromptTemplate
-from langchain.memory import ConversationBufferMemory
 import streamlit as st
 import os
 import time
 from langchain_community.llms import HuggingFaceEndpoint
-
-
 from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import Chroma
+from langchain.prompts import PromptTemplate
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import RetrievalQA
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.callbacks.manager import CallbackManager
 
+# Model and Embedding Configuration
 model_name = "sentence-transformers/all-mpnet-base-v2"
 model_kwargs = {'device': 'cpu'}
 encode_kwargs = {'normalize_embeddings': False}
+
 embeddings = HuggingFaceEmbeddings(
     model_name=model_name,
     model_kwargs=model_kwargs,
     encode_kwargs=encode_kwargs
 )
 
-if not os.path.exists('files'):
-    os.mkdir('files')
-
-if not os.path.exists('jj'):
-    os.mkdir('jj')
+# Directory setup
+os.makedirs('files', exist_ok=True)
+os.makedirs('jj', exist_ok=True)
 
+# Streamlit session state setup
 if 'template' not in st.session_state:
     st.session_state.template = """You are a knowledgeable chatbot, here to help with questions of the user. Your tone should be professional and informative.Try to give answer in tabular and shortcut.
 
@@ -51,51 +47,39 @@ if 'memory' not in st.session_state:
         return_messages=True,
         input_key="question")
 if 'vectorstore' not in st.session_state:
-    #st.session_state.vectorstore = Chroma(persist_directory='jj', embedding_function=OllamaEmbeddings(base_url='http://localhost:11434',model="mistral")
-    st.session_state.vectorstore = Chroma(persist_directory='jj', embedding_function=embeddings) 
-    
+    # Proper embedding configuration, avoids meta tensor errors
+    st.session_state.vectorstore = Chroma(persist_directory='jj', embedding_function=embeddings)
+
 if 'llm' not in st.session_state:
-    #st.session_state.llm = Ollama(base_url="http://localhost:11434",model="mistral",verbose=True,callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),)
     st.session_state.llm = HuggingFaceEndpoint(repo_id="mistralai/Mistral-7B-Instruct-v0.2", Temperature=0.9)
-    
-# Initialize session state
+
 if 'chat_history' not in st.session_state:
     st.session_state.chat_history = []
 
 st.title("PDF Chatbot")
 
-# Upload a PDF file
 uploaded_file = st.file_uploader("Upload your PDF", type='pdf')
-
 for message in st.session_state.chat_history:
     with st.chat_message(message["role"]):
         st.markdown(message["message"])
 
 if uploaded_file is not None:
-    if not os.path.isfile("files/"+uploaded_file.name+".pdf"):
+    file_path = os.path.join("files", uploaded_file.name + ".pdf")
+    if not os.path.isfile(file_path):
         with st.status("Analyzing your document..."):
             bytes_data = uploaded_file.read()
-            f = open("files/"+uploaded_file.name+".pdf", "wb")
-            f.write(bytes_data)
-            f.close()
-            loader = PyPDFLoader("files/"+uploaded_file.name+".pdf")
+            with open(file_path, "wb") as f:
+                f.write(bytes_data)
+            loader = PyPDFLoader(file_path)
             data = loader.load()
 
-            # Initialize text splitter
-            text_splitter = RecursiveCharacterTextSplitter(
-                chunk_size=1500,
-                chunk_overlap=0,
-                length_function=len
-            )
+            text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=0, length_function=len)
             all_splits = text_splitter.split_documents(data)
 
-            # Create and persist the vector store
-            #st.session_state.vectorstore = Chroma.from_documents(documents=all_splits,embedding=OllamaEmbeddings(model="mistral"))
-            st.session_state.vectorstore = Chroma.from_documents(documents=all_splits,embedding=embeddings)
+            st.session_state.vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)
             st.session_state.vectorstore.persist()
 
     st.session_state.retriever = st.session_state.vectorstore.as_retriever()
-    # Initialize the QA chain
     if 'qa_chain' not in st.session_state:
         st.session_state.qa_chain = RetrievalQA.from_chain_type(
             llm=st.session_state.llm,
@@ -109,7 +93,6 @@ if uploaded_file is not None:
             }
         )
 
-    # Chat input
     if user_input := st.chat_input("You:", key="user_input"):
         user_message = {"role": "user", "message": user_input}
         st.session_state.chat_history.append(user_message)
@@ -123,13 +106,10 @@ if uploaded_file is not None:
             for chunk in response['result'].split():
                 full_response += chunk + " "
                 time.sleep(0.05)
-                # Add a blinking cursor to simulate typing
                 message_placeholder.markdown(full_response + "▌")
             message_placeholder.markdown(full_response)
 
         chatbot_message = {"role": "assistant", "message": response['result']}
         st.session_state.chat_history.append(chatbot_message)
-
-
 else:
-    st.write("Please upload a PDF... file.")
+    st.write("Please upload a PDF... file.")