wit VS checkov

wit.ai — NLP for developers.

Hello everyone, new to LLMs. I am working on my thesis project. The whole idea is to create a mixed reality voice assistant that can control some devices in a room and you can have with it a more intelligent conversation compared to other voice assistants(Alexa,Google, etc.). I thought initially to use wit.ai for the extraction of commands and if it's not a recognized command to send a request to a chatgpt API. Then I realized that wit.ai wasn't pretty accurate when I added multiple intents, for example distinguishing creating list from adding item to list or removing item from removing reminder etc, even though I added enough training data. Sometimes it identifies the entities correctly, but the intent is wrong even though there are no intents with these entities in the existing data. If user does not specify correctly a command I will have to handle a lot of scenarios like not specifying time or date or both and asking user to give them again and managing to extract the values correctly after. I thought that chatgpt could actually do both if I give some instructions with the formats of prompts and responses I want. I tried it in the web version and seemed to do what I want. Then I realized how expensive it is to use their API just to have context on a conversation. So my next thought was to use a local llm. So could someone recommend me a small model that can be used for such case or what adjustments should I do in order to work? In my university I can use a machine with 32GΒ Ram and Nvidia Α4000 GPU. Thank you :)

I can't find anything wrong with the code you posted. It is possible that wit.ai is expecting some default header that Unity is not sending (and that you are not setting)

Even though this was made for VR hopefully the scripts for wit.ai and GPT will be helpful to anyone who wants to explore this topic and doesn't know where to start.

Hey HN,

We're Alex, Martin and Laurent. We previously founded [Wit.ai](http://wit.ai/) (W14), which we sold to Facebook in 2015. Since 2019, we've been working on Nabla (https://www.nabla.com), an intelligent assistant for health practitioners.

When GPT-3 was released in 2020, we investigated it's usage in a medical context[0], to mixed results.

Since then we’ve kept exploring opportunities at the intersection of healthcare and AI, and noticed that doctors spend am awful lot of time on medical documentation (writing clinical notes, updating their EHR, etc.).

Today, we're releasing Nabla Copilot, a Chrome extension generating clinical notes from video consultations, to address this problem.

You can try it out, without installation nor sign up, on our demo page: [https://www.nabla.com/copilot-demo/](https://www.nabla.com/copilot-demo/)

Here’s how it works under the hood:

- When a doctor starts a video consultation, our Chrome extension auto-starts itself and listens to the active tab as well as the doctor’s microphone.

Thank you, that's helpful except that currently we're not running our own server. I'm currently using wit.ai for NLP which is a web API service provided by Meta. I'm trying to budget for what it would cost to roll out our own on a private cloud.

I have an NLP agent that uses wit.ai to "understand" input prompts. Now, wit.ai is just an API server that calculates the most probable intent of the prompt (out of the intents trained with) and also extracts the entities present in the prompt.

Wit AI : Natural Language for Developers

wit.ai — NLP for developers.

1. Checkov: https://github.com/bridgecrewio/checkov Checkov is a static code analysis tool that helps developers prevent cloud misconfigurations during the development phase by scanning Terraform, CloudFormation, Kubernetes, and more.

Checkov Owner/Maintainer: Prisma Cloud by Palo Alto Networks (acquired in 2021) Age: First released on GitHub on March 31st, 2021 License: Apache License 2.0

‍Checkov is another great tool that examines your Terraform files (.tf), parsing the configurations and evaluating them against a comprehensive set of predefined policies. It scans Terraform-managed infrastructure and detects misconfigurations that could lead to security issues or non-compliance with best practices and regulations.

Bridgecrew — Infrastructure as code (IaC) security powered by the open source tool - Checkov. The core Bridgecrew platform is free for up to 50 IaC resources.

Kustomize: It provides a solution to customize the Kubernetes resource base configuration and differential configuration without template and DSL. It does not solve the constraint problem itself, but needs to cooperate with a large number of additional tools to check constraints, such as Kube-linter, Checkov and kubescape.

Checkov is a versatile static code analysis tool designed for infrastructure as code (IaC) and software composition analysis (SCA). It supports a wide range of technologies, including Terraform, CloudFormation, Kubernetes, Docker, and others, to detect security and compliance issues through graph-based scanning. Checkov also performs SCA scans, identifying vulnerabilities in open source packages and images by checking for Common Vulnerabilities and Exposures (CVEs). Additionally, it is integrated into Prisma Cloud Application Security, a platform that helps developers secure cloud resources and infrastructure-as-code files, enabling the identification, rectification, and prevention of misconfigurations throughout the development lifecycle.

For your Dockerfiles, you can also scan them. There are lots of tools that can check your Dockerfiles. They will validate if Dockerfile is compliant with Docker best practices such as not using root user, making sure a health check exists, and not exposing the SSH port. You can use Snyk and Checkov.

You could try https://www.checkov.io/

We use https://www.checkov.io/ for this, it's very simple to get started with and works really well as PR quality gate

Once there is a CI pipeline for delivering infra changes you can add static code analysis tools (checkov) and even start testing changes (terratest)