update tensors and add text to prediction

app.py

@@ -2,7 +2,6 @@ from collections import Counter
 import pandas as pd
 import streamlit as st
 import json
-from plotly import express as px
 from safetensors import safe_open
 from semantic_search import predict
 from sentence_transformers import SentenceTransformer
@@ -154,7 +153,7 @@ model = SentenceTransformer(
 
 st.set_page_config(layout="wide")
 
-st.title("Musterdatenkatalog")
+st.title("Musterdatenkatalog (MDK)")
 
 st.markdown(
     """
@@ -168,13 +167,24 @@ st.markdown(
 )
 
 st.markdown(
-    '<p class="font">This demo showcases the algorithm of Musterdatenkatalog (MDK) of the Bertelsmann Stiftung. The MDK is a taxonomy of Open Data in municipalities in Germany. It is intended to help municipalities in Germany, as well as data analysts and journalists, to get an overview of the topics and the extent to which cities have already published data sets.</p>',
+    """
+<style>
+.prediction {
+    font-size:10px !important;
+}
+</style>
+""",
     unsafe_allow_html=True,
 )
 
 
 st.markdown(
-    '<p class="font"> For more details checkout the <a href=https://www.bertelsmann-stiftung.de/de/unsere-projekte/smart-country/musterdatenkatalog> Musterdatenkatalog.</p>',
+    '<p class="font">This demo showcases the algorithm of Musterdatenkatalog (MDK) of the Bertelsmann Stiftung. The MDK is a taxonomy of Open Data in municipalities in Germany. It is intended to help municipalities in Germany, as well as data analysts and journalists, to get an overview of the topics and the extent to which cities have already published data sets.</p>',
+    unsafe_allow_html=True,
+)
+
+st.markdown(
+    '<p class="font"> For more details checkout the <a href=https://www.bertelsmann-stiftung.de/de/unsere-projekte/smart-country/musterdatenkatalog> Musterdatenkatalog </a>.</p>',
     unsafe_allow_html=True,
 )
 
@@ -184,11 +194,14 @@ col1.metric("Datensätze", len(data))
 col2.metric("Themen", len(theme_counts))
 col3.metric("Bezeichnungen", len(labels_counts))
 
-st.title("Taxonomy")
+st.header("Explore the MDK-Classifier")
 
-st.plotly_chart(fig)
-
-st.title("Predict a Dataset")
+st.markdown(
+    '<p class="font"> This section allows you to predict a label from the MDK Taxonomy for a title of a dataset from municipalities. You can either enter your own dataset title or click on one of the examples. Checkout also <a href=https://www.govdata.de/> GOVDATA </a> for more dataset title examples. \
+    \
+    If you click on predict, the model will predict the most likely label for the dataset title. You can also change the number of labels that should be predicted. For example, if you change the Top Results to 3, the model will predict the 3 most likely labels for the dataset title in descending order. </p>',
+    unsafe_allow_html=True,
+)
 
 st.markdown(
     """
@@ -218,9 +231,23 @@ st.markdown(
 
 col1, col2 = st.columns([1.2, 1])
 
+st.markdown(
+    """
+<style>
+.example {
+    font-size:24px !important;
+}
+</style>
+""",
+    unsafe_allow_html=True,
+)
+
 
 with col2:
-    st.subheader("Example Input Dataset Names")
+    st.markdown(
+        '<p class="example">Example Titles of Datasets</p>',
+        unsafe_allow_html=True,
+    )
     examples = [
         "Spielplätze",
         "Berliner Weihnachtsmärkte 2022",
@@ -235,15 +262,28 @@ with col2:
 
 
 with col1:
+    tabs_font_css = """
+    <style>
+    div[class*="stTextInput"] label p {
+    font-size: 2px;
+    }
+    </style>    
+    """
+
+    st.write(tabs_font_css, unsafe_allow_html=True)
+
+    st.markdown(
+        '<p class="example">Enter a dataset title</p>',
+        unsafe_allow_html=True,
+    )
+
     if "query" not in st.session_state:
-        query = st.text_input(
-            "Enter dataset name",
-        )
+        query = st.text_input("")
     if "query" in st.session_state and st.session_state.query in examples:
-        query = st.text_input("Enter dataset name", value=st.session_state.query)
+        query = st.text_input("Enter a dataset title", value=st.session_state.query)
     if "query" in st.session_state and st.session_state.query not in examples:
         del st.session_state["query"]
-        query = st.text_input("Enter dataset name")
+        query = st.text_input("Enter a dataset title")
 
     top_k = st.select_slider("Top Results", options=[1, 2, 3, 4, 5], value=1)
 
@@ -257,4 +297,9 @@ with col1:
 
     if st.button("Predict"):
         for prediction in predictions:
-            st.write(prediction)
+            st.markdown(f'<p class="font"> {prediction} <p>', unsafe_allow_html=True)
+
+
+st.header("Musterdatenkatalog Taxonomy")
+
+st.plotly_chart(fig)

corpus_embeddings.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b84a249335502cd14ad3ea5b7ce5523266b7e6dddfd5110ba6fdd5cd41828a
-size 746592
+oid sha256:64143d425585aed670f2556432cb5c38d721a1902f75ffb8e57102e46ea00aaf
+size 743520