Building a Generative UI App With LangChain.js

preview_player
Показать описание


Рекомендации по теме
Комментарии
Автор

This was great. Thanks for taking the time to share this pattern.

colinmcnamara
Автор

For anyone looking to save time: Not even cloning the repository makes this work. It only functions in a development environment. Any attempt to run the build fails with the error [EmptyChannelError]. Langchain seems more focused on releasing videos and new features than on ensuring functionality, and doesn't even have the courtesy to respond to those trying to resolve the issue.

rossanovinicius
Автор

Exactly right timing. Today I spoke with my teammate to see how its done in Langchain

MrBadGenius
Автор

Awesome, thanks for using JS langchain

mtin
Автор

Excellent, thanks for sharing the knowledge. Not sure if this was explained, but is there a way to persist streamed component's user input into the agent executor state? The example only explains the `toolResult` which is the JSX element / error string. How do we capture inputs from JSX back into the chat?

There is a little explanation that I heard during DynamicStructuredTool explanation about stream.append / .update instead .done? But, that seems to be for intermediate update like progress bar updates rather than capture user input etc.

sanskritclub
Автор

Is there a way to use custom fine tuned models with langchain.js?

akimodeli
Автор

Hi, can we integrate this inside of messenger or whatsapp or something else ?

Stefan
Автор

Good video. But how could I save the messages and access them again? Since the messages are displayed in {elements} without any map, how could I access them again?

AdvogaIA
Автор

Please make a video on LangGraph Typescript, AI SDK and RAG pgVector

— edit, you covered enough for my above request 🎉

StephenRayner
Автор

Hi
please has anyone here ever worked on building a chat bot that respond to people like a particular person?, i.e chat bot that respond or generate replies like trump or barack

tolorunlekedanieljesutoni
Автор

common pattern in all videos by Langchain: author assumes the audience has the same knowledge level as them

datasciencetoday