From e492c7028d261305102736890e6ed6efe0e509f8 Mon Sep 17 00:00:00 2001
From: davidmezzetti <561939+davidmezzetti@users.noreply.github.com>
Date: Mon, 15 Nov 2021 10:23:23 -0500
Subject: [PATCH] Add article summarization example, closes #144

---
 README.md           |  1 +
 docs/examples.md    |  1 +
 examples/article.py | 66 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 68 insertions(+)
 create mode 100644 examples/article.py

diff --git a/README.md b/README.md
index c8b86d81..f8d5cbc6 100644
--- a/README.md
+++ b/README.md
@@ -137,6 +137,7 @@ Series of example applications with txtai. Links to hosted versions on [Hugging
 | [Basic similarity search](https://github.com/neuml/txtai/blob/master/examples/similarity.py) | Basic similarity search example. Data from the original txtai demo. |[🤗](https://hf.co/spaces/NeuML/similarity)|
 | [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. |*Local run only*|
 | [Image search](https://github.com/neuml/txtai/blob/master/examples/images.py) | Image similarity search application. Index a directory of images and run searches to identify images similar to the input query. |[🤗](https://hf.co/spaces/NeuML/imagesearch)|
+| [Summarize an article](https://github.com/neuml/txtai/blob/master/examples/article.py) | Summarize an article. Workflow that extracts text from a webpage and builds a summary. |[🤗](https://hf.co/spaces/NeuML/articlesummary)|
 | [Wiki search](https://github.com/neuml/txtai/blob/master/examples/wiki.py) | Wikipedia search application. Queries Wikipedia API and summarizes the top result. |[🤗](https://hf.co/spaces/NeuML/wikisummary)|
 | [Workflow builder](https://github.com/neuml/txtai/blob/master/examples/workflows.py) | Build and execute txtai workflows. Connect summarization, text extraction, transcription, translation and similarity search pipelines together to run unified workflows. |[🤗](https://hf.co/spaces/NeuML/txtai)|
 
diff --git a/docs/examples.md b/docs/examples.md
index 4e88db43..945ea0be 100644
--- a/docs/examples.md
+++ b/docs/examples.md
@@ -54,5 +54,6 @@ Series of example applications with txtai. Links to hosted versions on [Hugging
 | [Basic similarity search](https://github.com/neuml/txtai/blob/master/examples/similarity.py) | Basic similarity search example. Data from the original txtai demo. |[🤗](https://hf.co/spaces/NeuML/similarity)|
 | [Book search](https://github.com/neuml/txtai/blob/master/examples/books.py) | Book similarity search application. Index book descriptions and query using natural language statements. |*Local run only*|
 | [Image search](https://github.com/neuml/txtai/blob/master/examples/images.py) | Image similarity search application. Index a directory of images and run searches to identify images similar to the input query. |[🤗](https://hf.co/spaces/NeuML/imagesearch)|
+| [Summarize an article](https://github.com/neuml/txtai/blob/master/examples/article.py) | Summarize an article. Workflow that extracts text from a webpage and builds a summary. |[🤗](https://hf.co/spaces/NeuML/articlesummary)|
 | [Wiki search](https://github.com/neuml/txtai/blob/master/examples/wiki.py) | Wikipedia search application. Queries Wikipedia API and summarizes the top result. |[🤗](https://hf.co/spaces/NeuML/wikisummary)|
 | [Workflow builder](https://github.com/neuml/txtai/blob/master/examples/workflows.py) | Build and execute txtai workflows. Connect summarization, text extraction, transcription, translation and similarity search pipelines together to run unified workflows. |[🤗](https://hf.co/spaces/NeuML/txtai)|
diff --git a/examples/article.py b/examples/article.py
new file mode 100644
index 00000000..b58ced57
--- /dev/null
+++ b/examples/article.py
@@ -0,0 +1,66 @@
+"""
+Application that builds a summary of an article.
+
+Requires streamlit to be installed.
+  pip install streamlit
+"""
+
+import os
+
+import streamlit as st
+
+from txtai.pipeline import Summary, Textractor
+from txtai.workflow import UrlTask, Task, Workflow
+
+
+class Application:
+    """
+    Main application.
+    """
+
+    def __init__(self):
+        """
+        Creates a new application.
+        """
+
+        textract = Textractor(paragraphs=True, minlength=100, join=True)
+        summary = Summary("sshleifer/distilbart-cnn-12-6")
+
+        self.workflow = Workflow([UrlTask(textract), Task(summary)])
+
+    def run(self):
+        """
+        Runs a Streamlit application.
+        """
+
+        st.title("Article Summary")
+        st.markdown("This application builds a summary of an article.")
+
+        url = st.text_input("URL")
+        if url:
+            # Run workflow and get summary
+            summary = list(self.workflow([url]))[0]
+
+            # Write results
+            st.write(summary)
+            st.markdown("*Source: " + url + "*")
+
+
+@st.cache(allow_output_mutation=True)
+def create():
+    """
+    Creates and caches a Streamlit application.
+
+    Returns:
+        Application
+    """
+
+    return Application()
+
+
+if __name__ == "__main__":
+    os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+    # Create and run application
+    app = create()
+    app.run()