Security

At a glance

The post is about the community member looking for the best open-source security architecture to use with Llamaindex. The comments provide some suggestions:

One community member recommends using open-source language models and embedding models, as this keeps the data on the user's side. They also suggest using the nemo-guardrails tool to verify user input and mask sensitive information when using closed-source language models like OpenAI or Azure.

Another community member, Riccardo, the Co-Founder of Glaider, suggests that their platform could be a valuable asset. Glaider is designed to safeguard applications from prompt injection attacks, data leakage, and toxic language, and can be integrated with any language model through their API.

Useful resources

mmemorIA

OpenSource like Llamaindex vs Azure... clients always asks about security... I'm trying to find the best opensource security architecture with Llamaindex.

3 comments

WWhiteFang_Jr

I think using open-source llms and embed models improves and make your data stay at your side which is a big PLUS.

Apart from this you can use nemo-gaurdrails to verify user input , mask any important details like card numbers etc in case going with closed llms like openai or azure.

https://github.com/NVIDIA/NeMo-Guardrails

Llamaindex implementation: https://medium.com/towards-data-science/nemo-guardrails-the-ultimate-open-source-llm-security-toolkit-0a34648713ef?sk=836ead39623dab0015420de2740eccc2

mmemorIA

I didn't know about this. Going to take a look. Thnks for sharing!

rriccardomorotti

Hello @memorIA , I'm Riccardo, Co-Founder of Glaider. I believe Glaider could be a valuable asset for your needs. Our platform is purpose-built to safeguard your applications from:

Prompt Injection attacks: shields against direct and indirect attacks that can manipulate your prompts.
Data leakage: ensures the safety of sensitive data when connecting to critical resources.
Toxic language: keeps outputs aligned with ethical standards and company policies.

Integration is a breeze! With our API, you can secure any LLM with just a few steps.

Want to give it a try? DM me or reach out at riccardo@glaider.it for a trial, we’re just starting and would love some solid feedback!

Add a reply

Find answers from the community

Security