Ollama4j
A Java library (wrapper/binding) for Ollama server.
Loading...
Searching...
No Matches
io.github.ollama4j.utils.OptionsBuilder Class Reference

Public Member Functions

 OptionsBuilder ()
 
OptionsBuilder setMirostat (int value)
 
OptionsBuilder setMirostatEta (float value)
 
OptionsBuilder setMirostatTau (float value)
 
OptionsBuilder setNumCtx (int value)
 
OptionsBuilder setNumGqa (int value)
 
OptionsBuilder setNumGpu (int value)
 
OptionsBuilder setNumThread (int value)
 
OptionsBuilder setRepeatLastN (int value)
 
OptionsBuilder setRepeatPenalty (float value)
 
OptionsBuilder setTemperature (float value)
 
OptionsBuilder setSeed (int value)
 
OptionsBuilder setStop (String value)
 
OptionsBuilder setTfsZ (float value)
 
OptionsBuilder setNumPredict (int value)
 
OptionsBuilder setTopK (int value)
 
OptionsBuilder setTopP (float value)
 
OptionsBuilder setMinP (float value)
 
OptionsBuilder setCustomOption (String name, Object value) throws IllegalArgumentException
 
Options build ()
 

Detailed Description

Builder class for creating options for Ollama model.

Definition at line 7 of file OptionsBuilder.java.

Constructor & Destructor Documentation

◆ OptionsBuilder()

io.github.ollama4j.utils.OptionsBuilder.OptionsBuilder ( )

Constructs a new OptionsBuilder with an empty options map.

Definition at line 12 of file OptionsBuilder.java.

Member Function Documentation

◆ build()

Options io.github.ollama4j.utils.OptionsBuilder.build ( )

Builds the options map.

Returns
The populated options map.

Definition at line 244 of file OptionsBuilder.java.

◆ setCustomOption()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setCustomOption ( String name,
Object value ) throws IllegalArgumentException

Allows passing an option not formally supported by the library

Parameters
nameThe option name for the parameter.
valueThe value for the "{name}" parameter.
Returns
The updated OptionsBuilder.
Exceptions
IllegalArgumentExceptionif parameter has an unsupported type

Definition at line 229 of file OptionsBuilder.java.

◆ setMinP()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setMinP ( float value)

Alternative to the top_p, and aims to ensure a balance of qualityand variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)

Definition at line 217 of file OptionsBuilder.java.

◆ setMirostat()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setMirostat ( int value)

Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)

Parameters
valueThe value for the "mirostat" parameter.
Returns
The updated OptionsBuilder.

Definition at line 23 of file OptionsBuilder.java.

◆ setMirostatEta()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setMirostatEta ( float value)

Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)

Parameters
valueThe value for the "mirostat_eta" parameter.
Returns
The updated OptionsBuilder.

Definition at line 36 of file OptionsBuilder.java.

◆ setMirostatTau()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setMirostatTau ( float value)

Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)

Parameters
valueThe value for the "mirostat_tau" parameter.
Returns
The updated OptionsBuilder.

Definition at line 48 of file OptionsBuilder.java.

◆ setNumCtx()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setNumCtx ( int value)

Sets the size of the context window used to generate the next token. (Default: 2048)

Parameters
valueThe value for the "num_ctx" parameter.
Returns
The updated OptionsBuilder.

Definition at line 59 of file OptionsBuilder.java.

◆ setNumGpu()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setNumGpu ( int value)

The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.

Parameters
valueThe value for the "num_gpu" parameter.
Returns
The updated OptionsBuilder.

Definition at line 83 of file OptionsBuilder.java.

◆ setNumGqa()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setNumGqa ( int value)

The number of GQA groups in the transformer layer. Required for some models, for example, it is 8 for llama2:70b.

Parameters
valueThe value for the "num_gqa" parameter.
Returns
The updated OptionsBuilder.

Definition at line 71 of file OptionsBuilder.java.

◆ setNumPredict()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setNumPredict ( int value)

Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)

Parameters
valueThe value for the "num_predict" parameter.
Returns
The updated OptionsBuilder.

Definition at line 182 of file OptionsBuilder.java.

◆ setNumThread()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setNumThread ( int value)

Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores).

Parameters
valueThe value for the "num_thread" parameter.
Returns
The updated OptionsBuilder.

Definition at line 96 of file OptionsBuilder.java.

◆ setRepeatLastN()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setRepeatLastN ( int value)

Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)

Parameters
valueThe value for the "repeat_last_n" parameter.
Returns
The updated OptionsBuilder.

Definition at line 108 of file OptionsBuilder.java.

◆ setRepeatPenalty()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setRepeatPenalty ( float value)

Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)

Parameters
valueThe value for the "repeat_penalty" parameter.
Returns
The updated OptionsBuilder.

Definition at line 120 of file OptionsBuilder.java.

◆ setSeed()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setSeed ( int value)

Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)

Parameters
valueThe value for the "seed" parameter.
Returns
The updated OptionsBuilder.

Definition at line 144 of file OptionsBuilder.java.

◆ setStop()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setStop ( String value)

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile.

Parameters
valueThe value for the "stop" parameter.
Returns
The updated OptionsBuilder.

Definition at line 157 of file OptionsBuilder.java.

◆ setTemperature()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setTemperature ( float value)

The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)

Parameters
valueThe value for the "temperature" parameter.
Returns
The updated OptionsBuilder.

Definition at line 132 of file OptionsBuilder.java.

◆ setTfsZ()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setTfsZ ( float value)

Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)

Parameters
valueThe value for the "tfs_z" parameter.
Returns
The updated OptionsBuilder.

Definition at line 170 of file OptionsBuilder.java.

◆ setTopK()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setTopK ( int value)

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)

Parameters
valueThe value for the "top_k" parameter.
Returns
The updated OptionsBuilder.

Definition at line 194 of file OptionsBuilder.java.

◆ setTopP()

OptionsBuilder io.github.ollama4j.utils.OptionsBuilder.setTopP ( float value)

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)

Parameters
valueThe value for the "top_p" parameter.
Returns
The updated OptionsBuilder.

Definition at line 206 of file OptionsBuilder.java.


The documentation for this class was generated from the following file: