Ollama
8 operations0 webhooks
Local LLM runtime API for running open-source language models on your own infrastructure.
Supported operations
- ChatWrite
Tool to send a chat message with conversation history to Ollama. Use when you need to have a multi-turn conversation with an LLM model.
- GenerateWrite
Tool to generate text responses from Ollama models with optional raw mode. Use raw=true to bypass prompt templating when you need full control over the prompt for debugging or custom processing. Note that raw mode will not return a context.
FAQ
Install corsair and @corsair-dev/ollama, add the Ollama plugin, and connect with an API key or OAuth. Then call methods like corsair.ollama.api.chat.chat() from your app. Corsair stores tokens, and keeps each tenant isolated.
Yes. Ollama supports an API key or OAuth. Use credentials or OAuth scopes that match what you automate. Create them in the Ollama developer console, then paste into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit Ollama, GitHub, Notion, Stripe, and the rest. Trigger Ollama from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for local llm runtime api for running open-source language models on your own infrastructure. Common builds include sync jobs, admin tooling, and agents that call Ollama APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Ollama API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/ollama in the open repo. When Ollama ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Ollama data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Ollama data on your behalf.