Skip to main content

Ollama

Prefer guided AI setup?

Instead of following these steps manually, you can use the AI Credential Assistant — describe what you want to connect and the AI will walk you through the setup step by step, tailored to your account.

Overview​

Ollama allows you to run large language models locally on your machine. It provides a simple way to download, run, and manage AI models like Llama, Mistral, and many others.

Authentication Type​

API Key (Optional) + Host URL

Setup Instructions​

Step 1: Install Ollama​

  1. Download from Ollama.com
  2. Follow the Quick Start guide
  3. Pull a model: ollama pull llama3.2

Step 2: Configure Access​

Local Setup:

  • Default URL: http://localhost:11434
  • No API key required for local access

Remote/Proxy Setup:

  • If using an authenticated proxy (like Open WebUI), you'll need an API key

Step 3: Add to Nirvai​

  1. In Nirvai, go to Credentials
  2. Select Ollama API
  3. Enter your:
    • Ollama URL (default: http://localhost:11434)
    • API Key (optional, for authenticated proxies)
  4. Save the credential

Common Use Cases​

  • Local AI chat applications
  • Private, offline AI inference
  • Development and testing of AI models
  • Embeddings generation

API Documentation​

Ollama API Documentation

Next Steps​

Got your credential? Connect it to an agent

Use the AI Tool Creator to turn this credential into agent-callable tools. Describe what your agent should be able to do and the AI investigates the API, configures the endpoints, and gives you a reviewable toolkit before saving anything.