Ollama integration
Get up and running with large language models.
What your agents can do with Ollama
10 pre-built Ollama tool steps, ready to drop into any agent. Anything they do not cover, an agent can reach with an authenticated API call.
Actions (10)
Show Model Information
Show information about a model including details, modelfile, template, parameters, license, and system prompt.
Push Model to Library
Upload a model to a model library. Requires registering for ollama.ai and adding a public key first.
Pull Model
Download a model from the ollama library. Cancelled pulls are resumed from where they left off, and multiple calls will share the same download progress.
List Local Models
List models that are available locally.
Generate Embeddings
Generate embeddings from a model.
Generate Completion
Generates a response for a given prompt with a provided model.
Generate Chat Completion
Generates the next message in a chat with a provided model.
Delete Model
Delete a model and its data.
Create Model
Create a model from a modelfile.
Copy Model
Copies a model, creating a model with another name from an existing model.
Set up Ollama in Relevance AI
Do this once. Every agent in your workspace can then use the connection.
Create a Relevance AI account
Sign in, or create a free account. You do not need to be a developer to set this up.
Connect your Ollama account
In Relevance AI, open Integrations and add Ollama, then paste your URL and API Key. You will find it in your Ollama account settings.
Use Ollama in an agent
Create a tool, add a Ollama tool step, and connect it to an agent. The agent fills in the step's inputs each time it runs.
Put Ollama to work in your agents
Connect Ollama alongside 1,800+ other integrations and let your agents run the busywork.