OpenTypeless

Ollama (Local)

Ollama is a local LLM provider for text polishing; it is not an STT provider. Verify the configured host, model dependencies, update traffic, and network behavior because local deployment is not an automatic privacy guarantee.

Official Documentation

Ollama API

Core API endpoints and model lifecycle commands.

https://github.com/ollama/ollama/blob/main/docs/api.md

Ollama OpenAI Compatibility

OpenAI-compatible endpoint behavior.

https://github.com/ollama/ollama/blob/main/docs/openai.md

Prepare Local Runtime

  1. Install Ollama and confirm daemon is running.
  2. Pull at least one local model, for example: ollama pull llama3.2.
  3. Verify local endpoint is reachable before OpenTypeless test.

Configure in OpenTypeless

  1. Settings > AI Polish > Provider: Ollama.
  2. Base URL: http://localhost:11434/v1.
  3. Model: llama3.2 (or your local model).
  4. If API key field must be non-empty for test button, use a placeholder such as ollama-local.
  5. Run Test.

Recommended Configuration

OpenTypeless calls Ollama via OpenAI-compatible endpoint path.

Provider: ollama
Base URL: http://localhost:11434/v1
Endpoint: /chat/completions
Default model: llama3.2

Important

⚠️
Most failures are local runtime issues (daemon down or model missing), not prompt quality problems.