---
title: "Discussion on \"Cutting costs on developing RAG chatbots\" | Hashnode"
description: "Discussion on \"Cutting costs on developing RAG chatbots\". Testing a hybrid approach on local and hosted LLM models"
url: "https://hashnode.com/posts/cutting-costs-on-developing-rag-chatbots/67d0b90e9e91bf73728a2805"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Cutting costs on developing RAG chatbots](https://tech.teomoura.com/cutting-costs-on-developing-rag-chatbots?utm_source=hashnode&utm_medium=feed)

Testing a hybrid approach on local and hosted LLM models

Mar 11, 2025 · 6 min read · tech.teomoura.com  
Updated Apr 3, 2025  
Read the article

-   [#rag](https://hashnode.com/tag/rag)
-   [#chatbot](https://hashnode.com/tag/chatbot)
-   [#supabase](https://hashnode.com/tag/supabase)
-   [#llm](https://hashnode.com/tag/llm)
-   [#javascript](https://hashnode.com/tag/javascript)

## Written by

[Teogenes Moura](https://hashnode.com/@teomoura)

@teomoura

  
[View profile](https://hashnode.com/@teomoura)

Software engineer interested in AI

Software engineer transitioning into ML/AI Engineering

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
