feat: initial commit

app.py

@@ -0,0 +1,23 @@
+import streamlit as st
+from summarizer import summarize_text
+
+
+def main():
+    st.title("Text Summarizer")
+
+    text = st.text_area("Enter text to summarize")
+
+    if st.button("Summarize"):
+        if text:
+            summarized_text = summarize_text(text)
+            st.subheader("Original Text")
+            st.write(text)
+
+            st.subheader("Summarized Text")
+            st.write(summarized_text)
+        else:
+            st.warning("Please enter some text to summarize")
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,2 @@
+streamlit
+transformers[torch]

samples.py

@@ -0,0 +1,36 @@
+ARTICLE_FROM_HFACE = (
+    "PG&E stated it scheduled the blackouts in response to forecasts for high winds "
+    "amid dry conditions. The aim is to reduce the risk of wildfires. Nearly 800 thousand customers were "
+    "scheduled to be affected by the shutoffs which were expected to last through at least midday tomorrow."
+)
+
+ARTICLE_FROM_BOOMAI = """
+The integration of Artificial Intelligence (AI) in customer engagement strategies has marked a
+new era in the business-consumer relationship. AI technologies are transforming how
+businesses interact with their customers, offering personalized experiences and enhancing
+customer satisfaction.
+One of the key applications of AI in customer engagement is through chatbots and virtual
+assistants. These AI-powered tools can handle a wide range of customer service inquiries,
+providing instant responses and support 24/7. They are programmed to learn from interactions,
+enabling them to deliver more accurate and helpful responses over time. This not only improves
+the efficiency of customer service but also allows human agents to focus on more complex
+queries. Another significant impact of AI is in the realm of data analysis and customer insights.
+AI algorithms can process vast amounts of data from various customer touchpoints and extract
+meaningful patterns and trends. This data-driven approach enables businesses to understand
+customer behavior and preferences in-depth, leading to more targeted and effective marketing
+strategies. Personalization is also a major benefit of AI in customer engagement. By analyzing
+past interactions and purchases, AI can help businesses tailor their communications and
+recommendations to individual customers. This level of personalization enhances the customer
+experience, increases brand loyalty, and can lead to higher conversion rates.
+AI is also reshaping customer engagement through predictive analytics. By forecasting future
+customer behaviors and trends, businesses can proactively address potential issues and seize
+opportunities. This forward-looking approach helps in maintaining a competitive edge and
+staying relevant in the market. However, the use of AI in customer engagement also presents
+challenges, particularly in terms of privacy and ethical considerations. Businesses must ensure
+that customer data is handled responsibly, and AI interactions are transparent and secure.
+In conclusion, AI is playing a crucial role in revolutionizing customer engagement. Its ability to
+provide personalized, efficient, and data-driven interactions is not only enhancing the customer
+experience but also driving business growth and innovation. As AI technology continues to
+evolve, its impact on customer engagement is expected to grow even further, shaping the future
+of business-customer relationships.
+"""

summarizer.py

@@ -0,0 +1,15 @@
+from transformers import AutoTokenizer, BartForConditionalGeneration
+
+model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
+tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
+
+
+def summarize_text(text_to_summarize):
+    inputs = tokenizer([text_to_summarize], max_length=1024, return_tensors="pt")
+    summary_ids = model.generate(
+        inputs["input_ids"], num_beams=2, min_length=0, max_length=100
+    )
+    summarized_text = tokenizer.batch_decode(
+        summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )[0]
+    return summarized_text