# Function Node and complete Flow for the (filtered) GPT4All AI Text Generator Model

**URL:** <https://discourse.nodered.org/t/function-node-and-complete-flow-for-the-filtered-gpt4all-ai-text-generator-model/77769>\
**Category:** Share Your Projects\
**Created:** [21 April 2023 03:54 UTC](https://discourse.nodered.org/t/function-node-and-complete-flow-for-the-filtered-gpt4all-ai-text-generator-model/77769 "2023-04-21T03:54:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rozek](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/rozek/32/48594_2.png) [@rozek](https://discourse.nodered.org/u/rozek)\
**Post date:** [21 April 2023 03:54 UTC](https://discourse.nodered.org/t/function-node-and-complete-flow-for-the-filtered-gpt4all-ai-text-generator-model/77769/1 "2023-04-21T03:54:42Z")

</div>

As promised yesterday: the function node for the (filtered) GPT4All AI text generator model is fully available now. **Please note: inference runs on the CPU (without requiring any special hardware) but still completes within a few seconds.**

Having GPT4All inference as a self-contained Node-RED node gives you the possibility to create your own user interface or even build autonomous agents.

The distribution comes with a flow both for the basic function node and a complete HTTP endpoint which responds to incoming requests. Also attached is a trivial web page which can be used as a user interface for the AI model.

See the related [GitHub repository](https://github.com/rozek/node-red-flow-gpt4all-filtered) for instructions on how to install and use it.