WebInfer

🦙

Ollama

Local models via Ollama

Free
Local & Self-Hosted
Local

Configure Ollama

Enable Ollama in Settings

Go to Settings
Capabilities
chat
local
openai-compatible
Configuration Schema
Required and optional fields for configuring this provider
FieldTypeRequired
host
text
Optional
port
number
Optional
CLI Usage
For users running the daemon server locally or a self-hosted gateway

Add provider:

npx webinfer provider add ollama

Test connection:

npx webinfer provider test ollama
Programmatic Usage
Use Ollama in your code with WebInfer

Basic usage:

import { generateText } from "webinfer"

// WebInfer automatically routes to the best available provider
const result = await generateText({
  prompt: "Write a haiku about programming"
})

console.log(result.text)

Specify Ollama explicitly:

import { generateText } from "webinfer"

const result = await generateText({
  prompt: "Write a haiku about programming",
  provider: "ollama"
})

console.log(result.text)
console.log("Provider:", result.provider)
console.log("Model:", result.model)

Streaming:

import { streamText } from "webinfer"

const { textStream } = await streamText({
  prompt: "Write a story about AI",
  provider: "ollama"
})

for await (const chunk of textStream) {
  process.stdout.write(chunk)
}