I am trying to build a conversational chatbot using VS Code. The code is following:
## RAG Q&A Conversation With PDF Including Chat History
import streamlit as st
from langchain.chains import create_history_aware_retriever, create_retrieval_chain
from langchain.chainsbine_documents import create_stuff_documents_chain
from langchain_chroma import Chroma
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_groq import ChatGroq
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
import os
from dotenv import load_dotenv
load_dotenv()
os.environ['HF_TOKEN']=os.getenv("HF_TOKEN")
embeddings=HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
## set up Streamlit
st.title("Conversational RAG With PDF uplaods and chat history")
st.write("Upload Pdf's and chat with their content")
## Input the Groq API Key
api_key=st.text_input("Enter your Groq API key:",type="password")
## Check if groq api key is provided
if api_key:
llm=ChatGroq(groq_api_key=api_key,model_name="Gemma2-9b-It")
## chat interface
session_id=st.text_input("Session ID",value="default_session")
## statefully manage chat history
if 'store' not in st.session_state:
st.session_state.store={}
uploaded_files=st.file_uploader("Choose A PDf file",type="pdf",accept_multiple_files=True)
## Process uploaded PDF's
if uploaded_files:
documents=[]
for uploaded_file in uploaded_files:
temppdf=f"./temp.pdf"
with open(temppdf,"wb") as file:
file.write(uploaded_file.getvalue())
file_name=uploaded_file.name
loader=PyPDFLoader(temppdf)
docs=loader.load()
documents.extend(docs)
# Split and create embeddings for the documents
text_splitter = RecursiveCharacterTextSplitter(chunk_size=5000, chunk_overlap=500)
splits = text_splitter.split_documents(documents)
vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
retriever = vectorstore.as_retriever()
contextualize_q_system_prompt=(
"Given a chat history and the latest user question"
"which might 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."
)
contextualize_q_prompt = ChatPromptTemplate.from_messages(
[
("system", contextualize_q_system_prompt),
MessagesPlaceholder("chat_history"),
("human", "{input}"),
]
)
history_aware_retriever=create_history_aware_retriever(llm,retriever,contextualize_q_prompt)
## Answer question
# Answer question
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, say that you "
"don't know. Use three sentences maximum and keep the "
"answer concise."
"\n\n"
"{context}"
)
qa_prompt = ChatPromptTemplate.from_messages(
[
("system", system_prompt),
MessagesPlaceholder("chat_history"),
("human", "{input}"),
]
)
question_answer_chain=create_stuff_documents_chain(llm,qa_prompt)
rag_chain=create_retrieval_chain(history_aware_retriever,question_answer_chain)
def get_session_history(session:str)->BaseChatMessageHistory:
if session_id not in st.session_state.store:
st.session_state.store[session_id]=ChatMessageHistory()
return st.session_state.store[session_id]
conversational_rag_chain=RunnableWithMessageHistory(
rag_chain,get_session_history,
input_messages_key="input",
history_messages_key="chat_history",
output_messages_key="answer"
)
user_input = st.text_input("Your question:")
if user_input:
session_history=get_session_history(session_id)
response = conversational_rag_chain.invoke(
{"input": user_input},
config={
"configurable": {"session_id":session_id}
}, # constructs a key "abc123" in `store`.
)
st.write(st.session_state.store)
st.write("Assistant:", response['answer'])
st.write("Chat History:", session_history.messages)
else:
st.warning("Please enter the GRoq API Key")
Following is the error I am getting on my vs code terminal:
Examining the path of torch.classes raised:
Traceback (most recent call last):
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\web\bootstrap.py", line 345, in run
if asyncio.get_running_loop().is_running():
RuntimeError: no running event loop
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\watcher\local_sources_watcher.py", line 217, in get_module_paths
potential_paths = extract_paths(module)
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\watcher\local_sources_watcher.py", line 210, in <lambda>
lambda m: list(m.__path__._path),
File "D:\projects\PDF_chatbot\venv\lib\site-packages\torch\_classes.py", line 13, in __getattr__
proxy = torch._C._get_custom_class_python_wrapper(self.name, attr)
RuntimeError: Tried to instantiate class '__path__._path', but it does not exist! Ensure that it is registered via torch::class_
I tried reinstalling the requirements but its not working. Following is the image of error I am getting on streamlit UI: Error on the streamlit webapp after uploading pdf and asking any question
I am trying to build a conversational chatbot using VS Code. The code is following:
## RAG Q&A Conversation With PDF Including Chat History
import streamlit as st
from langchain.chains import create_history_aware_retriever, create_retrieval_chain
from langchain.chainsbine_documents import create_stuff_documents_chain
from langchain_chroma import Chroma
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_groq import ChatGroq
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
import os
from dotenv import load_dotenv
load_dotenv()
os.environ['HF_TOKEN']=os.getenv("HF_TOKEN")
embeddings=HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
## set up Streamlit
st.title("Conversational RAG With PDF uplaods and chat history")
st.write("Upload Pdf's and chat with their content")
## Input the Groq API Key
api_key=st.text_input("Enter your Groq API key:",type="password")
## Check if groq api key is provided
if api_key:
llm=ChatGroq(groq_api_key=api_key,model_name="Gemma2-9b-It")
## chat interface
session_id=st.text_input("Session ID",value="default_session")
## statefully manage chat history
if 'store' not in st.session_state:
st.session_state.store={}
uploaded_files=st.file_uploader("Choose A PDf file",type="pdf",accept_multiple_files=True)
## Process uploaded PDF's
if uploaded_files:
documents=[]
for uploaded_file in uploaded_files:
temppdf=f"./temp.pdf"
with open(temppdf,"wb") as file:
file.write(uploaded_file.getvalue())
file_name=uploaded_file.name
loader=PyPDFLoader(temppdf)
docs=loader.load()
documents.extend(docs)
# Split and create embeddings for the documents
text_splitter = RecursiveCharacterTextSplitter(chunk_size=5000, chunk_overlap=500)
splits = text_splitter.split_documents(documents)
vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
retriever = vectorstore.as_retriever()
contextualize_q_system_prompt=(
"Given a chat history and the latest user question"
"which might 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."
)
contextualize_q_prompt = ChatPromptTemplate.from_messages(
[
("system", contextualize_q_system_prompt),
MessagesPlaceholder("chat_history"),
("human", "{input}"),
]
)
history_aware_retriever=create_history_aware_retriever(llm,retriever,contextualize_q_prompt)
## Answer question
# Answer question
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, say that you "
"don't know. Use three sentences maximum and keep the "
"answer concise."
"\n\n"
"{context}"
)
qa_prompt = ChatPromptTemplate.from_messages(
[
("system", system_prompt),
MessagesPlaceholder("chat_history"),
("human", "{input}"),
]
)
question_answer_chain=create_stuff_documents_chain(llm,qa_prompt)
rag_chain=create_retrieval_chain(history_aware_retriever,question_answer_chain)
def get_session_history(session:str)->BaseChatMessageHistory:
if session_id not in st.session_state.store:
st.session_state.store[session_id]=ChatMessageHistory()
return st.session_state.store[session_id]
conversational_rag_chain=RunnableWithMessageHistory(
rag_chain,get_session_history,
input_messages_key="input",
history_messages_key="chat_history",
output_messages_key="answer"
)
user_input = st.text_input("Your question:")
if user_input:
session_history=get_session_history(session_id)
response = conversational_rag_chain.invoke(
{"input": user_input},
config={
"configurable": {"session_id":session_id}
}, # constructs a key "abc123" in `store`.
)
st.write(st.session_state.store)
st.write("Assistant:", response['answer'])
st.write("Chat History:", session_history.messages)
else:
st.warning("Please enter the GRoq API Key")
Following is the error I am getting on my vs code terminal:
Examining the path of torch.classes raised:
Traceback (most recent call last):
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\web\bootstrap.py", line 345, in run
if asyncio.get_running_loop().is_running():
RuntimeError: no running event loop
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\watcher\local_sources_watcher.py", line 217, in get_module_paths
potential_paths = extract_paths(module)
File "D:\projects\PDF_chatbot\venv\lib\site-packages\streamlit\watcher\local_sources_watcher.py", line 210, in <lambda>
lambda m: list(m.__path__._path),
File "D:\projects\PDF_chatbot\venv\lib\site-packages\torch\_classes.py", line 13, in __getattr__
proxy = torch._C._get_custom_class_python_wrapper(self.name, attr)
RuntimeError: Tried to instantiate class '__path__._path', but it does not exist! Ensure that it is registered via torch::class_
I tried reinstalling the requirements but its not working. Following is the image of error I am getting on streamlit UI: Error on the streamlit webapp after uploading pdf and asking any question
Share Improve this question asked Mar 11 at 9:34 Arpit shouryaArpit shourya 11 Answer
Reset to default 0deactivate # Exit venv
venv\Scripts\activate # Reactivate (Windows)
source venv/bin/activate # Reactivate (Mac/Linux)
streamlit run your_script.py
Run this in terminal and run VSCode as administrator