Spaces:
Sleeping
Sleeping
File size: 5,538 Bytes
487bbdc 6a245c3 487bbdc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
import os
# --- Fix for Hugging Face permission issue ---
os.environ["STREAMLIT_BROWSER_GATHERUSAGESTATS"] = "false"
os.environ["STREAMLIT_HOME"] = "/tmp"
os.makedirs("/tmp/.streamlit", exist_ok=True)
with open("/tmp/.streamlit/config.toml", "w") as f:
f.write("[browser]\ngatherUsageStats = false\n[server]\nheadless = true\n")
#-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
## 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.chains.combine_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 uploads and chat history")
st.write("Upload PDFs 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="llama-3.1-8b-instant")
## 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 PDFs
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
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}
},
)
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")
|