
Enabling LLM-Powered Applications with Harrison Chase of LangChain
Gradient Dissent: Conversations on AI
The Complexity of Prompt Construction
The main thing is kind of the chaining of multiple things together? Is that fair? Yeah. I think there's a lot of the utils we also have are around, I would just say more complex things. So like even if you're making a simple call to the language model at the end of the day, like in the document question answering thing, you're doing a lot of work to carefully construct that prompt basically. And so we have a number of different pieces and then constructing them in a standard way. All these tools will be more useful over time as other models become more viable.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.