Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
We would like to implement multi shot prompting. This involves running openadapt.replay on multiple actions simultaneously.
This also involves selecting relevant recordings, using user specified natural language descriptions. These can be prompted along with model generated natural language descriptions of recordings (ie RAG).
Feature request
We would like to implement multi shot prompting. This involves running openadapt.replay on multiple actions simultaneously.
This also involves selecting relevant recordings, using user specified natural language descriptions. These can be prompted along with model generated natural language descriptions of recordings (ie RAG).
Motivation
https://arxiv.org/abs/2406.03679