Using LLMs in your Product

What if your LLM could call your application's code? Learn how function calling connects models to proprietary data and transforms them into intelligent agents.

#1about 2 minutes

Three pillars for integrating LLMs in products

The talk will cover three key areas for product integration: using the API, mastering prompt engineering, and implementing function calls for external data.

#2about 3 minutes

Making your first OpenAI API chat completion call

This section covers the basic code structure for making a chat completion request, including the different message roles and the stateless nature of the API.

#3about 3 minutes

Choosing the right LLM for your use case

Key factors for selecting a model include its training dataset cutoff date, context length measured in tokens, and the number of model parameters.

#4about 5 minutes

Best practices for effective prompt engineering

Improve LLM outputs by writing clear instructions, providing context with personas and references, and breaking down complex tasks into smaller steps.

#5about 4 minutes

Understanding and defending against prompt injection

Prevent users from bypassing system instructions by reinforcing the original rules with a post-prompt at the end of the message history.

#6about 4 minutes

Giving LLMs new abilities with function calling

Function calling allows the LLM to request help from your own code to access external data or perform actions like searching a database.

#7about 2 minutes

Summary and resources for further learning

The talk concludes with a recap of core concepts and provides resources for advanced prompting techniques and retrieval-augmented generation (RAG).

#8about 7 minutes

Audience Q&A on practical LLM implementation

The Q&A covers practical concerns like managing context length, prompt testing costs, implementing function call logic, and ensuring reliable JSON output.