10-18, 12:10–12:40 (Europe/Lisbon), Auditorium
Over the last year, there has been a lot of focus on making applications intelligent using the power of AI with the help of large language models (LLMs). This talk covers how to add intelligence to existing applications with an overview of different techniques starting from prompt engineering, using vector stores to improve the results, and building intelligent agents to figure out how to solve a problem.
This talk will showcase the techniques with demos using open-source frameworks to build LLM-powered applications like LangChain & LlamaIndex.
The talk also covers some practical considerations to consider while deploying these applications to production.
Large Language Models(LLMs) are good at reasoning based on their knowledge. This talk explores how you can use the power of LLMs to add intelligence like coding assistants, text-to-sequel, etc to existing applications.
One of the simplest ways to start adding intelligence is by using an LLM with fine-tuned prompts. You can find the answers to questions like: - What are some of the things that you need to consider while prompt engineering? - What are the limits of prompt engineering?
After finding out the limits of prompt engineering, let us understand how to augment the knowledge of the LLM using vector databases. You can learn things like: - Ingesting the data into the vector databases. - Considerations in data ingestion to improve the LLM performance.
We will also cover the concept of AI agents that given a set of capabilities or tools can figure out how to use them where relevant in an intelligent fashion. You can learn - How do agents work? - Where are they useful?
After this talk, you will learn how to add intelligence to existing applications with the help of the ever-popular LLMs using open-source frameworks.
Beginner
What are the main topics of your talk? –LLM, AI, RAG, Agents
Nithish Raghunandanan is a Developer Advocate at Couchbase who loves to build products that solve real-world problems in short spans of time. He has experienced different areas of the industry having worked in diverse companies in Germany and India. Apart from work, he likes to travel and interact and engage with the tech community through Meetups & Hackathons. In his free time, he likes to try stuff out by hacking things together.