Docker Inc. Dives Into AI Application Development

At its DockerCon event, Docker, Inc. today launched a framework to make it simpler to build applications infused with artificial intelligence (AI) using containers.

In addition, Docker Inc. revealed it has partnered with Neo4j, LangChain and Ollama to create a GenAI Stack designed to help developers start building generative AI applications in minutes.

Step 1 of 7

14%

Which of the following best describes how you currently monitor and manage systems across your hybrid cloud environment?(Required)

Multiple separate tools for different environments

Multiple separate tools for different monitoring and management functions

Single consolidated dashboard

Custom built monitoring and management solution

No full monitoring and management solution

Don’t know

How valuable would it be for your monitoring and management solution to incorporate predictive analytics to help you identify and address system issues that are critical and not waste time or effort working through all the data and “noise” that is not critical?(Required)

Extremely valuable

Moderately valuable

Somewhat valuable

Slightly valuable

Not valuable

How do you most typically address potential system issues BEFORE they impact your operations?(Required)

Automated workflows and playbooks to remediate potential issues as soon as they are detected

An orchestrated response process that leverages automation, AI, and human expertise to rapidly respond to potential issues

Advanced monitoring tools such as predictive analytics and anomaly detection to proactively identify and address potential issues

Respond to issues as they arise, using manual processes and troubleshooting techniques

A combination of automated remediation, orchestrated response, and/or proactive monitoring to address potential system issues

Don’t know

Other

What methods does your organization use to control and monitor cloud/IT spending?(Required)

Centralized procurement processes

Pre-approved budget thresholds

Automated cost monitoring tools

Department-level spending controls

Regular cost audits and reviews

Cloud cost optimization platform

Approval workflows for resource provisioning

Native financial operations tools provided by the cloud provider

No formal controls in place

Don’t know

Other

Please specify:

Which methods do you rely on most to detect security vulnerabilities in your systems?(Required)

Automated scanning tools

Manual assessments

Vendor notifications

Threat modeling (for early detection)

None of these

Don’t know

Other

Please specify:

What are the TWO most common ways you prioritize vulnerabilities to address within your environment?(Required)

Based on potential impact

Based on exploitability

Regulatory compliance requirements

Based on CVSS scores

Risk-based analysis of multiple factors

First-in-first-out approach

No formal prioritization process

Don’t know

How do you typically handle system updates and security patches?(Required)

Automated updates and patches

Manually review and apply updates and patches on a regular schedule

A combination of automation and manual review

Apply updates and patches on an as-needed basis.

Outsourced update and patch management

No defined process

Don’t know

Other

Δ

Docker, Inc. CEO Scott Johnston said Docker AI is designed to help developers define and troubleshoot all aspects of an application development involving AI models. Specifically, developers will be able to take advantage of a framework that surfaces automated guidance, for example, to spin up resources such as databases using Docker files and images, he added.

The GenAI Stack complements that effort by making available pre-configured large language models (LLMs) from Ollama, vector and graph databases from Neo4j, and the open source LangChain framework. Components include open source LLMs such as Llama 2, Code Llama, Mistral and private models such as OpenAI’s GPT-3.5 and GPT-4, along with tools and templates to, for example, simplify data loading and vector index population.

Developers can take advantage of knowledge graphs to enhance querying and enrich results using summarization and retrieval tools. In addition, developers can compare results achieved between LLMs on their own, LLMs with vector and LLMs with vector and knowledge graph integration.

Building applications infused with AI is now a team sport involving data scientists, data engineers, software engineers and traditional developers. Over time, Docker is betting that as AI models become more commonly infused with AI capabilities, developers will be able to more easily invoke models they constructed themselves or those created by a data science team. Of course, data science teams have their own distinct cultures based on machine learning operations (MLOps) platforms, so the biggest challenge ahead in terms of creating more holistic teams will be bridging the cultural divides that exist between the different classes of engineers and developers involved.

In the meantime, the race to embed AI models is on. While it’s still early days with regard to determining the best use cases for AI, many organizations are now experimenting with AI models. The challenge many initially face is simply figuring out how to train AI models using reliable data. However, once a model is constructed, it then needs to be integrated into an application via an application programming interface (API).

Of course, AI models are also subject to drift, so there will be a need for observability, governance and DevOps frameworks to monitor performance, bias and hallucinations in addition to updating and rolling back AI models based on the feedback loops an organization creates.

Finally, each AI model will need to be secured to ensure that the data used to create it has not been poisoned by cybercriminals trying to deliberately force a hallucination to occur.

Most organizations are going to need time to completely address every aspect of the AI life cycle, but, as always, the desire to innovate now is pushing the limitations of the frameworks many organizations have relied on for decades to build applications.