Add article summarization example, closes #144

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)|
 

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)|

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()