Ollama

           Coming Soon

Ragfish is designed with a modular AI provider architecture, allowing applications to work with different AI model providers through the same Core Framework.

Ollama support is planned for a future release.

Planned Integration

The planned Ollama integration will allow Ragfish applications to work with locally hosted AI models.

The integration is expected to follow the same provider architecture used by the existing OpenAI integration.

@ragfish/core
     │
     ▼
  Settings
     │
     ▼
Ollama Provider
     │
     ├── Language Model
     └── Embeddings

Local AI Architecture

Ollama is intended to support local model deployments.

A future Ragfish application could follow this architecture:

Ragfish Application
       │
       ▼
  @ragfish/core
       │
       ▼
    Settings
       │
       ▼
     Ollama
       │
       ▼
Local AI Model

This can provide an alternative to cloud-based AI providers for applications that require locally hosted model infrastructure.

Provider Independence

The Ragfish provider architecture keeps AI-provider-specific implementation separate from the Core Framework.

Application
   │
   ▼
@ragfish/core
   │
   ▼
Provider Interface
   │
   ▼
Ollama

This allows the rest of the Ragfish RAG pipeline to remain independent of the underlying model provider.

Status

     Status : Coming Soon

Ollama support is not currently available in the documented Ragfish release.

Installation instructions, supported models, configuration options, and API examples will be added when the integration is released.

For currently available AI provider functionality, see OpenAI