Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
import os | |
import streamlit as st | |
import streamlit_analytics | |
from utils import add_logo_to_sidebar, add_footer, add_email_signup_form | |
streamlit_analytics.start_tracking() | |
st.set_page_config( | |
page_title="Legal AI Demos", | |
page_icon="π", | |
layout="wide", | |
initial_sidebar_state="expanded", | |
menu_items={ | |
'Get Help': 'mailto:[email protected]', | |
'Report a bug': None, | |
'About': "## This a demo showcasing different Legal AI Actions" | |
} | |
) | |
add_logo_to_sidebar() | |
st.title("π Welcome - Legal AI Demos from simplexico!") | |
st.sidebar.success("π Select a demo above.") | |
st.markdown( | |
""" | |
Here at simplexico, we've put together a collection of demos showcasing what AI can do in legal. | |
AI tends to get spoken about in vague terms. We like to think about AI in terms of the specific | |
**action** it can perform. These demos are meant to cut through all the hype and noise so you can simplify see | |
for yourself what AI can and can't do. | |
Here you will find demos for the most common Legal AI Actions including: | |
- π· **Label** - Using AI to **label** text | |
- β **Extract** - Using AI to **extract** information from text | |
- π **Compare** - Using AI to **compare** passages of text | |
- π **Organise** - Using AI to **organise** a collection of texts | |
- π **Find** - Using AI to **find** relevant information from a collection of texts | |
- βοΈ **Draft** - Using AI to **draft** text | |
- π **Summarise** - Using AI to **summarise** text | |
π’ FYI - These demos are to help you understand AI better. The AI models have not been optimised for prediction performance. | |
### π Select a demo from the sidebar to see some examples of what Legal AI can do! | |
""") | |
add_email_signup_form() | |
st.markdown( | |
""" | |
### π What goes into making an AI model? | |
Building an AI model is a lot like cooking. | |
A π©βπ³ chef (data scientist) combines the π₯ ingredients (data) according to a recipe π (algorithm) | |
and π³ cooks the meal (trains the model) in the πͺ kitchen (computing environment). | |
Once the π₯§ meal (AI model) is ready, it can be π served (deployed) to a ππ»customer (user) | |
ready to be π½ eaten (used) and enjoyed π (meeting the user's needs). | |
### π Showcasing our recipes | |
Our Legal AI Chefs π§βπ³ have prepared a selection of recipes π and with publicly sourced | |
ingredients π₯ they have created some fantastic meals π₯§ (AI demos) for you to try. | |
We've also peppered on some explainability so you can see what the AI model is thinking. | |
Try them out π½! | |
### βΉ About Us | |
simplexico offers white-glove Legal AI education, design and development services. We are on a mission to help | |
legal professionals step into a future of collaboration with AI. | |
We have the Legal AI Chefs π©βπ³ and recipes π. | |
You have the ingredients π₯ (data). | |
We can tailor some yummy Legal AI meals for your taste π₯§! | |
""" | |
) | |
add_footer() | |
streamlit_analytics.stop_tracking(unsafe_password=os.environ["ANALYTICS_PASSWORD"]) |