Release.ai Templates

Out-of-the box templates that get you started with Release.ai quickly

If there is a technology not listed that you'd like for Release.ai to support, please send an email to [e-mail] and we'll reach out and discuss getting you going.

RAG

RAG Templates are available under the "Server" execution type when creating an application from a template.

Docker GenAI

The GenAI Stack will get you started building your own GenAI application in no time

Docker GenAI with OpenAI

The GenAI Stack with OpenAI will get you started building your own GenAI application in no time

AnythingLLM

The all-in-one AI app you were looking for. Chat with your docs, use AI Agents, hyper-configurable, multi-user, & no frustrating set up required.

Docker GenAI-Chroma Release

The GenAI Stack with a Chroma vector datase will get you started building your own GenAI application in no time

Ragapp The easiest way to use Agentic RAG in any enterprise.

Inference

Inference Templates are available under the "Server" execution type when creating an application from a template.

Ollama

Ollama makes it easy to get up and running with large language models

Ollama Web UI

Ollama (Open) WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline

COG from Replicate

Easily run COG containers from Replicate in your cloud account

Nvidia NIM

Nvidia Nim Microservices and Inference

Fine Tuning

Fine Tuning Templates are available under the "Runnable" execution type when creating an application from a template.

Pytorch

Pytorch container with NVIDIA GPU drivers

Axolotl

PEFT Fine Tuning with Axolotl

Nvidia NeMo

PEFT Fine Tuning with NeMo

Image Generation

Image Generation Templates are available under the "Server" execution type when creating an application from a template.

Stable Diffusion

A web interface for Stable Diffusion By AUTOMATIC1111

Prompt Engineering

Prompt Engineering Templates are available under the "Server" execution type when creating an application from a template.

PromptFoo

A tool for testing and evaluating LLM output quality.

Vector Databases

Vector Databases are available under the "Server" execution type when creating an application from a template.

Vector Admin

The universal UI and tool suite for managing vector databases at scale

Notebooks

Notebooks are available under the "Server" execution type when creating an application from a template.

GPU Jupyter

Leverage Jupyter Notebooks with the power of your NVIDIA GPU via CUDA in Tensorflow and Pytorch.