Skip to content

feat(providers): add Ollama local provider (internal/providers/ollama) #5

Description

@Nithwin

Is your feature request related to a problem? Please describe.

Goal

Enable developers to run WindMist with zero API rate limits and zero cost by connecting to local models via Ollama.

Describe the solution you'd like

Requirements

  1. Create internal/providers/ollama/provider.go implementing ai.Provider (Generate, Stream).
  2. Connect to the local server endpoint (http://localhost:11434/v1).
  3. Support native tool calling schemas for open-source models like llama3.1 and qwen2.5.
  4. Register dynamically via ai.Register("ollama", New) inside init().

Describe alternatives you've considered

No response

Additional Context

No response

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions