Bundle
Ollama local LLM client. Runs models (Llama, Mistral, Phi, etc.) locally via the Ollama server. Supports chat sessions, embeddings, and model management. Every request completes before returning -- responses are not streamed, so a long generation produces nothing until it finishes. Compile with -lib ollama.
Tool
Tool definition for function calling in chat.
Example
params := JsonParser->TextToElement("{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\"}}}");
tool := Tool->New("get_weather", "Get the weather for a location", params);Operations
New # constructor
Constructor
New(name:String, description:String, parameters:JsonElement)Parameters
| Name | Type | Description |
|---|---|---|
| name | String | function name |
| description | String | function description |
| parameters | JsonElement | JSON schema for parameters |
ToJson #
Converts tool to JSON for the request.
method : public : ToJson() ~ JsonElementReturn
| Type | Description |
|---|---|
| JsonElement | JSON element |