Check whether the local Ollama service is reachable.

List all locally available Ollama models.

Get detailed information about a specific Ollama model.

Download / update an Ollama model from the Ollama registry. Returns streaming status lines summarising the download progress.

Delete a locally stored Ollama model to free disk space.

List models currently loaded in memory (running in Ollama).

Run the same prompt against multiple models and return all responses side-by-side for comparison.

Run text generation with an Ollama model. Returns the model's raw completion for a given prompt.

Send a multi-turn conversation to an Ollama model. Messages should follow the format [{'role': 'user'|'assistant'|'system', 'content': '...'}].

Use a local judge model to score an LLM response on relevance, coherence, correctness, and completeness (1-5 each).

Evaluate a multi-turn agent conversation on task completion, tool use, safety, and efficiency using a local judge model.

Create a named local vector index for RAG (Retrieval-Augmented Generation). Documents added to this index are embedded via Ollama.

List all local knowledge indexes.

Add a text document to a knowledge index. The text is embedded automatically using the index's embedding model.

Semantic search over a knowledge index. Returns the top-k most relevant documents for a natural language query.

Delete a knowledge index and all its documents.