Provisional solution to @ines's Streamlit caching problem with Spacy

spacy_example.py

import streamlit as st
import spacy
from spacy import displacy

SPACY_MODEL_NAMES = ["en_core_web_sm", "de_core_news_sm"]
DEFAULT_TEXT = "Mark Zuckerberg is the CEO of Facebook."
HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem">{}</div>"""


@st.cache(ignore_hash=True)
def load_model(name):
    return spacy.load(name)

@st.cache(ignore_hash=True)
def process_text(text):
    return nlp(text)

st.title("Interactive spaCy visualizer")
st.markdown(
    """
A little Streamlit app that lets you process text with [spaCy](https://spacy.io)
models and visualize named entities and dependencies, or get the `Doc` object's
JSON representation. Uses spaCy's built-in
[displaCy](http://spacy.io/usage/visualizers) visualizer under the hood.
"""
)

spacy_model = st.selectbox("Model name", SPACY_MODEL_NAMES)
model_load_state = st.info(f"Loading model '{spacy_model}'...")
nlp = load_model(spacy_model)
model_load_state.success(f"✅ Loaded model '{spacy_model}'.")

text = st.text_input("Text to analyze", DEFAULT_TEXT)
button_deps = st.button("Analyze dependencies")
button_ents = st.button("Analyze named entities")
button_json = st.button("Get JSON")

doc = process_text(text)

if button_deps:
    html = displacy.render(doc)
    # Double newlines seem to mess with the rendering
    html = html.replace("\n\n", "\n")
    st.write(HTML_WRAPPER.format(html))
if button_ents:
    html = displacy.render(doc, style="ent")
    st.write(HTML_WRAPPER.format(html))
if button_json:
    st.write(doc.to_json())

To update this snippet for latest Streamlit release, we need to replace "ignore_hash=True" with "allow_output_mutation=True".
Thanks!