# Rasa custom entity extractor
**URL:** https://forum.rasa.com/t/rasa-custom-entity-extractor/54359
**Category:** Rasa Open Source
**Created:** [July 18, 2022, 7:18am UTC](https://forum.rasa.com/t/rasa-custom-entity-extractor/54359 "2022-07-18T07:18:54Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@aliasad059](https://forum.rasa.com/u/aliasad059)
#### Post date: [July 18, 2022, 7:18am UTC](https://forum.rasa.com/t/rasa-custom-entity-extractor/54359/1 "2022-07-18T07:18:55Z")
hello everyone!
I’m trying to add a new component as an entity extractor for Persian names to the rasa pipeline. I found a fine-tuned Bert model for this and it works well.
The component successfully passes the rasa train but the problem is in the rasa shell section. It gives me the following error:
**rasa.core.agent - Could not load model due to Erro initializing graph component for node run\_components.name\_entity\_extractor.MyNameEntityExtractor4…**
config.yml and the custom class are as follows:
I also tried the following forum suggestions but none of them works for me.
> [@Could not load model due to Error initializing graph component for node](http://forum.rasa.com/t/could-not-load-model-due-to-error-initializing-graph-component-for-node/51841):
>
> I have updated an existing Rasa 2.0 project to Rasa 3.0 following the [migration guide](https://rasa.com/docs/rasa/migration-guide/#rasa-2x-to-30) and the [custom graph components guide](https://rasa.com/docs/rasa/custom-graph-components). My system set up is as follows: Rasa Version : 3.0.8 Minimum Compatible Version: 3.0.0 Rasa SDK Version : 3.0.4 Rasa X Version : None Python Version : 3.8.3 Operating System : Linux-5.4.0-1066-aws-x86\_64-with-glibc2.10 Python Path : /home/ubuntu/anaconda3/envs/vail-rasa-venv/bin/python I was able to succ…
> [@ERROR rasa.core.agent - Could not load model due to Error initializing graph component for node 'run\_classifiers.\[custom\_commponent\].\[CustomClass\]12](http://forum.rasa.com/t/error-rasa-core-agent-could-not-load-model-due-to-error-initializing-graph-component-for-node-run-classifiers-custom-commponent-customclass-12/50361):
>
> Not sure if this is a bug or something else is wrong, but when this worked in Rasa2 and has worked on and off in Rasa3. It appears that modifying config.yml requires retraining, not just restarting. Each time there is a retrain, a custom component gets cached, and that cached version gets placed in run\_classifiers module, and the name appended with an integer. However, the error occurred not only with custom component, but also with LanguageModelFeaturizer. I’ve erased the whole cache at .rasa …
Any help is really appreciated!
---
### Author:  [@aniketjain](https://forum.rasa.com/u/aniketjain)
#### Post date: [September 7, 2022, 11:08pm UTC](https://forum.rasa.com/t/rasa-custom-entity-extractor/54359/2 "2022-09-07T23:08:00Z")
What are the errors you are getting? Usually there is a specific one that causes failure in loading the graph component.
---
### Author:  [@Kaamer001](https://forum.rasa.com/u/Kaamer001)
#### Post date: [October 12, 2023, 10:41am UTC](https://forum.rasa.com/t/rasa-custom-entity-extractor/54359/3 "2023-10-12T10:41:48Z")
@aliasad059 similar to your application can we use some different entity extractor model for extracting the entities? I trained one custom spacy model for extracting the “SKILL” and i want to use that model in rasa chatbot how to use that can someone pls tell me?