# Chatbot for support model selection

**URL:** <https://discuss.huggingface.co/t/chatbot-for-support-model-selection/41776>\
**Category:** Beginners\
**Created:** [June 1, 2023, 1:28pm UTC](https://discuss.huggingface.co/t/chatbot-for-support-model-selection/41776 "2023-06-01T13:28:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tolkoton](https://avatars.discourse-cdn.com/v4/letter/t/3bc359/32.png) [@tolkoton](https://discuss.huggingface.co/u/tolkoton)\
**Post date:** [June 1, 2023, 1:28pm UTC](https://discuss.huggingface.co/t/chatbot-for-support-model-selection/41776/1 "2023-06-01T13:28:51Z")

</div>

I have many articles without labels and want to build a chatbot to answer questions based on that.  
Is it possible to make it on the fully open-source model? I have tested BERT with context - it’s a disaster. Viccuna that haven’t seen context performs much better than that.