chalisesagun's picture
Rename app,py to app.py
946c19c verified
import os
import tempfile
import streamlit as st
from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader, UnstructuredMarkdownLoader, WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain_community.chat_models import ChatOpenAI
# Streamlit App Title
st.title("📄 DeepSeek-Powered RAG Chatbot")
# Step 1: Input API Key
api_key = st.text_input("🔑 Enter your DeepSeek API Key:", type="password")
if api_key:
# Set the API key as an environment variable (optional)
os.environ["DEEPSEEK_API_KEY"] = api_key
# Step 2: Upload Document or Enter Web Link
input_option = st.radio("Choose input type:", ("Upload Document", "Web Link"))
if input_option == "Upload Document":
uploaded_file = st.file_uploader("📂 Upload a document", type=["pdf", "docx", "md"])
else:
web_link = st.text_input("🌐 Enter the web link:")
# Use session state to persist the vector_store
if "vector_store" not in st.session_state:
st.session_state.vector_store = None
if (input_option == "Upload Document" and uploaded_file and st.session_state.vector_store is None) or \
(input_option == "Web Link" and web_link and st.session_state.vector_store is None):
try:
with st.spinner("Processing document..."):
if input_option == "Upload Document":
# Save the uploaded file temporarily
with tempfile.NamedTemporaryFile(delete=False, suffix=f".{uploaded_file.name.split('.')[-1]}") as tmp_file:
tmp_file.write(uploaded_file.getvalue())
tmp_file_path = tmp_file.name
# Load the document based on file type
if uploaded_file.name.endswith(".pdf"):
loader = PyPDFLoader(tmp_file_path)
elif uploaded_file.name.endswith(".docx"):
loader = Docx2txtLoader(tmp_file_path)
elif uploaded_file.name.endswith(".md"):
loader = UnstructuredMarkdownLoader(tmp_file_path)
else:
st.error("Unsupported file type!")
st.stop()
documents = loader.load()
# Remove the temporary file
os.unlink(tmp_file_path)
else:
# Load the web page content
loader = WebBaseLoader(web_link)
documents = loader.load()
# Split the document into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = text_splitter.split_documents(documents)
# Generate embeddings and store them in a vector database
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
st.session_state.vector_store = FAISS.from_documents(chunks, embeddings)
st.success("Document processed successfully!")
except Exception as e:
st.error(f"Error processing document: {e}")
st.stop()
# Step 3: Ask Questions About the Document
if st.session_state.vector_store:
st.subheader("💬 Chat with Your Document")
user_query = st.text_input("Ask a question:")
if user_query:
try:
# Set up the RAG pipeline with DeepSeek LLM
retriever = st.session_state.vector_store.as_retriever()
llm = ChatOpenAI(
model="deepseek-chat",
openai_api_key=api_key,
openai_api_base="https://api.deepseek.com/v1",
temperature=0.85,
max_tokens=1000 # Adjust token limit for safety
)
qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
# Generate response
with st.spinner("Generating response..."):
response = qa_chain.run(user_query)
# Check if the response is relevant or not
if "I don't know" in response or "not in the document" in response.lower():
response = "I'm here to assist you with questions about uploaded documents or related web links."
st.write(f"**Answer:** {response}")
except Exception as e:
st.error(f"Error generating response: {e}")
else:
st.warning("Please enter your DeepSeek API key to proceed.")