Spaces:
Running
Running
File size: 4,664 Bytes
180a8b0 |
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 |
import streamlit as st
import asyncio
import os
from f1_ai import F1AI
from dotenv import load_dotenv
# Load environment variables from .streamlit/secrets.toml into os.environ
for key, value in st.secrets.items():
os.environ[key] = value
# Initialize session state
if 'f1_ai' not in st.session_state:
# Use HuggingFace by default for Spaces deployment
st.session_state.f1_ai = F1AI(llm_provider="huggingface")
if 'chat_history' not in st.session_state:
st.session_state.chat_history = []
# Set page config
st.set_page_config(page_title="F1-AI: Formula 1 RAG Application", layout="wide")
# Title and description
st.title("F1-AI: Formula 1 RAG Application")
st.markdown("""
This application uses Retrieval-Augmented Generation (RAG) to answer questions about Formula 1.
""")
# Add tabs
tab1, tab2 = st.tabs(["Chat", "Add Content"])
with tab1:
# Custom CSS for better styling
st.markdown("""
<style>
.stChatMessage {
padding: 1rem;
border-radius: 0.5rem;
margin-bottom: 1rem;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
.stChatMessage.user {
background-color: #f0f2f6;
}
.stChatMessage.assistant {
background-color: #ffffff;
}
.source-link {
font-size: 0.8rem;
color: #666;
text-decoration: none;
}
</style>
""", unsafe_allow_html=True)
# Display chat history with enhanced formatting
for message in st.session_state.chat_history:
with st.chat_message(message["role"]):
if message["role"] == "assistant" and isinstance(message["content"], dict):
st.markdown(message["content"]["answer"])
if message["content"]["sources"]:
st.markdown("---")
st.markdown("**Sources:**")
for source in message["content"]["sources"]:
st.markdown(f"- [{source['url']}]({source['url']})")
else:
st.markdown(message["content"])
# Question input
if question := st.chat_input("Ask a question about Formula 1"):
# Add user question to chat history
st.session_state.chat_history.append({"role": "user", "content": question})
# Display user question
with st.chat_message("user"):
st.write(question)
# Generate and display response with enhanced formatting
with st.chat_message("assistant"):
with st.spinner("🤔 Analyzing Formula 1 knowledge..."):
response = asyncio.run(st.session_state.f1_ai.ask_question(question))
st.markdown(response["answer"])
# Display sources if available
if response["sources"]:
st.markdown("---")
st.markdown("**Sources:**")
for source in response["sources"]:
st.markdown(f"- [{source['url']}]({source['url']})")
# Add assistant response to chat history
st.session_state.chat_history.append({"role": "assistant", "content": response})
with tab2:
st.header("Add Content to Knowledge Base")
urls_input = st.text_area("Enter URLs (one per line)",
placeholder="https://en.wikipedia.org/wiki/Formula_One\nhttps://www.formula1.com/en/latest/article....")
max_chunks = st.slider("Maximum chunks per URL", min_value=10, max_value=500, value=100, step=10)
if st.button("Ingest Data"):
if urls_input:
urls = [url.strip() for url in urls_input.split("\n") if url.strip()]
if urls:
with st.spinner(f"Ingesting data from {len(urls)} URLs... This may take several minutes."):
progress_bar = st.progress(0)
# Process URLs one by one for better UI feedback
for i, url in enumerate(urls):
st.write(f"Processing: {url}")
asyncio.run(st.session_state.f1_ai.ingest([url], max_chunks_per_url=max_chunks))
progress_bar.progress((i + 1) / len(urls))
st.success("✅ Data ingestion complete!")
else:
st.error("Please enter at least one valid URL.")
else:
st.error("Please enter at least one URL to ingest.")
# Add a footer with credits
st.markdown("---")
st.markdown("F1-AI: A Formula 1 RAG Application • Powered by Hugging Face, Pinecone, and LangChain") |