SideNote Pro

Use Ollama with SideNote Pro for local AI

Ollama runs language models on your own hardware and exposes an OpenAI-compatible interface. Point SideNote Pro at it and your prompts go to localhost rather than to a hosted provider.

What Ollama is, and what it is not

Ollama is separate software that downloads and runs language models locally. SideNote Pro does not bundle it, does not install it, and does not supply the models. What SideNote Pro provides is a client that can talk to it.

Ollama exposes an OpenAI-compatible API alongside its own, which is what makes this work. SideNote Pro treats it as any other compatible endpoint: GET /models to test and discover, POST /chat/completions to generate.

Setting it up

  1. Install Ollama and pull a modelFollow Ollama's own documentation. You need at least one model downloaded before anything will answer, and the model name you pulled is the model ID you will use.
  2. Make sure the Ollama server is runningThe client and the server are separate. If the connection test fails, this is the first thing to check.
  3. Add an Ollama profile in SideNote ProSettings, AI providers, add from the Ollama preset. It fills in the local base URL for you.
  4. Leave the API key emptyA default local Ollama install does not require authentication. If you have put it behind a gateway that does, enter that gateway's key.
  5. Test, then pick your modelThe connection test lists the models you have pulled. Choose one, or type its name.
Ollama profile fields
FieldValue
Provider nameOllama
Base URLhttp://localhost:11434/v1
ModelThe model you pulled, by its Ollama name
API keyEmpty for a default local install
Reasoning effortProvider default

The /v1 suffix matters. http://localhost:11434 is Ollama's own API root; http://localhost:11434/v1 is the OpenAI-compatible one, and that is what SideNote Pro needs. If Ollama is on another machine or a non-default port, substitute accordingly.

What actually changes when you go local

The good part

Requests go to localhost. Inference happens on your hardware. There is no per-token bill, no rate limit, and nothing sent to a hosted provider, subject to how you have configured Ollama.

The cost

Speed and capability now depend on your machine. Local models that run comfortably on a laptop are generally smaller and less capable than the best hosted models, and long prompts are noticeably slower without a capable GPU.

SideNote Pro cannot make guarantees about third-party software. What it controls is the destination of the request. Whether that destination keeps everything on your machine depends on how you configured Ollama, and Ollama's own documentation is the authority on that.

Setting expectations for local models

  • Image input is uncommon. Most small local models are text-only. If images seem to be ignored, the model is the reason. See screenshots and images.
  • `reasoning_effort` may be ignored. Leave it on *Provider default* unless the specific model documents support.
  • Usage metadata may be absent. SideNote Pro falls back to local token estimates, which is fine given there is no bill to reconcile.
  • Long context is expensive in time. A long conversation, a large attached document or a folder-retrieval request means a lot of tokens to process locally. Lowering the context budget helps.
  • Context compaction still calls the model. It is local, so it costs no money, but it does cost time.

A practical arrangement many people settle on: keep a hosted profile for hard work and a local profile for anything confidential, and switch between them in the composer. Using local models for private workflows goes into that pattern.

Keep reading