--- title: Best Towards Data Science posts — May 2024 | daily.dev description: The most upvoted Towards Data Science posts from May 2024, curated by the daily.dev community. canonical: https://daily.dev/sources/tds/best-of/2024/05 twitter:card: summary_large_image twitter:site: @dailydotdev og:url: https://daily.dev/sources/tds/best-of/2024/05 og:type: website og:site_name: daily.dev og:title: Best Towards Data Science posts — May 2024 | daily.dev og:description: The most upvoted Towards Data Science posts from May 2024, curated by the daily.dev community. og:image: https://media.daily.dev/image/upload/s--VAY5ToZt--/f_auto/v1724209435/public/daily.dev%20-%20open%20graph --- # Best of Towards Data Science — May 2024 1. 1 [](https://daily.dev/posts/using-llms-to-learn-from-youtube-pzx8gpobn "Using LLMs to Learn From YouTube") Article Towards Data Science · 2y Using LLMs to Learn From YouTube Learn how to build a chatbot using LangChain, Pinecone, Flask, and React that allows users to ask questions about YouTube videos. The chatbot uses the RAG framework to generate answers that take the conversation history into account. 96 2. 2 [](https://daily.dev/posts/a-complete-guide-to-bert-with-code-odukuaay8 "A Complete Guide to BERT with Code") Article Towards Data Science · 2y A Complete Guide to BERT with Code The post provides a complete guide to BERT, including its history, architecture, pre-training objectives, and fine-tuning for sentiment analysis. It discusses the key features of BERT, such as its encoder-only architecture, pre-training approach, model fine-tuning, and use of bidirectional context. The post also covers the tokenization process, creating train and validation data loaders, instantiating a BERT model, and setting up an optimizer, loss function, and scheduler for fine-tuning. The fine-tuning loop is explained, highlighting the steps taken for each epoch and within each batch. 24 3. 3 [](https://daily.dev/posts/from-prompt-engineering-to-agent-engineering-rhb16mguf "From Prompt Engineering to Agent Engineering") Article Towards Data Science · 2y From Prompt Engineering to Agent Engineering The post introduces the concept of transitioning from prompt engineering to agent engineering, exploring the key ideas and precepts of agent engineering. It outlines the Agent Engineering Framework, which includes sections on Agent Capabilities Requirements and Agent Engineering & Design. The framework focuses on defining the jobs and actions of AI agents, identifying the required capabilities and proficiency levels, and mapping the required proficiencies to technologies and techniques. The post concludes by emphasizing the importance of a strong and flexible foundation for agent design and engineering. 23 3 4. 4 [](https://daily.dev/posts/build-your-own-chatgpt-like-chatbot-with-java-and-python-telz61nee "Build Your Own ChatGPT-like Chatbot with Java and Python") Article Towards Data Science · 2y Build Your Own ChatGPT-like Chatbot with Java and Python This article explains how to build a chatbot similar to ChatGPT using Java and Python. It covers topics such as creating a custom LLM inference infrastructure, architecture design, web client implementation, LDAP server setup, model performance, and a Kotlin mobile client. The system is scalable and can provide a decent service to a limited number of users. 10 [See all Towards Data Science archives](/sources/tds/best-of) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@graph":[{"@type":"CollectionPage","@id":"https://daily.dev/sources/tds/best-of/2024/05#page","url":"https://daily.dev/sources/tds/best-of/2024/05","name":"Best Towards Data Science Posts — May 2024","description":"The most upvoted Towards Data Science posts from May 2024, curated by the daily.dev community.","isPartOf":{"@type":"WebSite","url":"https://daily.dev"}},{"@type":"ItemList","@id":"https://daily.dev/sources/tds/best-of/2024/05#items","numberOfItems":4,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/posts/using-llms-to-learn-from-youtube-pzx8gpobn","name":"Using LLMs to Learn From YouTube"},{"@type":"ListItem","position":2,"url":"https://daily.dev/posts/a-complete-guide-to-bert-with-code-odukuaay8","name":"A Complete Guide to BERT with Code"},{"@type":"ListItem","position":3,"url":"https://daily.dev/posts/from-prompt-engineering-to-agent-engineering-rhb16mguf","name":"From Prompt Engineering to Agent Engineering"},{"@type":"ListItem","position":4,"url":"https://daily.dev/posts/build-your-own-chatgpt-like-chatbot-with-java-and-python-telz61nee","name":"Build Your Own ChatGPT-like Chatbot with Java and Python"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Sources","item":"https://daily.dev/sources"},{"@type":"ListItem","position":3,"name":"Towards Data Science","item":"https://daily.dev/sources/tds"},{"@type":"ListItem","position":4,"name":"Best of","item":"https://daily.dev/sources/tds/best-of"},{"@type":"ListItem","position":5,"name":"May 2024"}]}]} ```