This is awesome, Luis! 🚀 Love seeing MiniCPM-OCR integrated into Hermes Agent. Thanks for building this and sharing it with the community! 💙
OpenBMB praises Luis Poveda's MiniCPM-OCR plugin for Hermes Agent
AIOpenBMB welcomes Luis Poveda's MiniCPM-OCR plugin for Hermes Agent, which lets agents call the MiniCPM-OCR model for document parsing. Poveda built the plugin after finding general LLMs weak at complex documents such as physician prescriptions, and shared code on GitHub with a pull request to Nous Research's Hermes Agent repository.
@OpenBMB
Introducing the MiniCPM-OCR plugin for Hermes Agent. This is a problem I have experienced myself: LLMs by themselves are not always very good at OCR; sometimes I have needed another model specialized in it to solve complex document parsing. For example, recently I have had difficulties understanding some physician recipes and other manuscripts. This is where MiniCPM-OCR comes in. You can use the model and harness you already have to utilize a best-in-class OCR model by @OpenBMB. @Teknium @NousResearch Code: https://github.com/PovedaAqui/minicpm-ocr-hermes PR: https://github.com/NousResearch/hermes-agent/pull/150268
Source details
OpenBMB · x.comPublished · added here
Original title: This is awesome, Luis! 🚀 Love seeing MiniCPM-OCR integrated into Hermes Agent. Thanks for building this and sharing it with the communit...