Ollama
Ollama is a popular open-source platform for running and managing local large language models. It lets you chat, get completions, and generate embeddings using models hosted on your own machine or private environment. With straightforward model management (pull, list, create, copy, delete), Ollama is commonly used by teams that want flexibility, cost control, and stronger data privacy than sending prompts to third-party APIs.
Connecting Ollama gives BOBs a local “AI brain” you control. BOBs can answer users with chat completions, handle structured text generation, and produce embeddings that can feed search, matching, and personalization across your business data.
Instead of relying on remote model endpoints, BOBs can manage the model lifecycle in your environment: pulling models when needed, listing what’s available, creating or copying model variants, and deleting models to keep things tidy. This unlocks privacy-first automation, offline-friendly AI capabilities, and consistent model usage across multiple BOB jobs—such as AI drafting, customer support response generation, internal knowledge Q&A (when paired with your data systems), and semantic routing for business processes.
Available actions:
- Show Model Information
- Pull Model
- Push Model to Library
- Generate Embeddings
- Delete Model
- List Local Models
- Generate Completion
- Generate Chat Completion
- Copy Model
- Create Model
What can BOBs do with Ollama?
Perform actions
- Copy Model
- Create Model
- Delete Model
- Generate Chat Completion
- Generate Completion
- Generate Embeddings
- List Local Models
- Pull Model
- Push Model to Library
- Show Model Information