[maven-release-plugin] prepare release v1.0.41

Makefile

@@ -10,4 +10,16 @@ it:
 list-releases:
 	curl 'https://central.sonatype.com/api/internal/browse/component/versions?sortField=normalizedVersion&sortDirection=asc&page=0&size=12&filter=namespace%3Aio.github.amithkoujalgi%2Cname%3Aollama4j' \
       --compressed \
-      --silent | jq '.components[].version'
+      --silent | jq '.components[].version'
+
+build-docs:
+	npm i --prefix docs && npm run build --prefix docs
+
+start-docs:
+	npm i --prefix docs && npm run start --prefix docs
+
+start-cpu:
+	docker run -it -v ~/ollama:/root/.ollama -p 11434:11434 ollama/ollama
+
+start-gpu:
+	docker run -it --gpus=all -v ~/ollama:/root/.ollama -p 11434:11434 ollama/ollama

docs/docs/apis-ask/ask-with-image-files.md

@@ -8,7 +8,7 @@ This API lets you ask questions along with the image files to the LLMs.
 These APIs correlate to
 the [completion](https://github.com/jmorganca/ollama/blob/main/docs/api.md#generate-a-completion) APIs.
 
-:::caution
+:::note
 
 Executing this on Ollama server running in CPU-mode will take longer to generate response. Hence, GPU-mode is
 recommended.

docs/docs/apis-ask/ask-with-image-urls.md

@@ -8,7 +8,7 @@ This API lets you ask questions along with the image files to the LLMs.
 These APIs correlate to
 the [completion](https://github.com/jmorganca/ollama/blob/main/docs/api.md#generate-a-completion) APIs.
 
-:::caution
+:::note
 
 Executing this on Ollama server running in CPU-mode will take longer to generate response. Hence, GPU-mode is
 recommended.

docs/docs/apis-ask/ask.md

@@ -8,6 +8,11 @@ This API lets you ask questions to the LLMs in a synchronous way.
 These APIs correlate to
 the [completion](https://github.com/jmorganca/ollama/blob/main/docs/api.md#generate-a-completion) APIs.
 
+Use the `OptionBuilder` to build the `Options` object
+with [extra parameters](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values).
+Refer
+to [this](/docs/apis-extras/options-builder).
+
 ## Try asking a question about the model.
 
 ```java
@@ -19,11 +24,13 @@ public class Main {
 
         OllamaAPI ollamaAPI = new OllamaAPI(host);
 
-        OllamaResult result = ollamaAPI.ask(OllamaModelType.LLAMA2, "Who are you?");
+        OllamaResult result =
+                ollamaAPI.ask(OllamaModelType.LLAMA2, "Who are you?", new OptionsBuilder().build());
 
         System.out.println(result.getResponse());
     }
 }
+
 ```
 
 You will get a response similar to:
@@ -47,11 +54,13 @@ public class Main {
 
         String prompt = "List all cricket world cup teams of 2019.";
 
-        OllamaResult result = ollamaAPI.ask(OllamaModelType.LLAMA2, prompt);
+        OllamaResult result =
+                ollamaAPI.ask(OllamaModelType.LLAMA2, prompt, new OptionsBuilder().build());
 
         System.out.println(result.getResponse());
     }
 }
+
 ```
 
 You'd then get a response from the model:
@@ -84,12 +93,15 @@ public class Main {
         String host = "http://localhost:11434/";
         OllamaAPI ollamaAPI = new OllamaAPI(host);
 
-        String prompt = SamplePrompts.getSampleDatabasePromptWithQuestion(
+        String prompt =
-                "List all customer names who have bought one or more products");
+                SamplePrompts.getSampleDatabasePromptWithQuestion(
-        OllamaResult result = ollamaAPI.ask(OllamaModelType.SQLCODER, prompt);
+                        "List all customer names who have bought one or more products");
+        OllamaResult result =
+                ollamaAPI.ask(OllamaModelType.SQLCODER, prompt, new OptionsBuilder().build());
         System.out.println(result.getResponse());
     }
 }
+
 ```
 
 _Note: Here I've used

docs/docs/apis-ask/generate-embeddings.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 5
+sidebar_position: 6
 ---
 
 # Generate Embeddings
@@ -30,17 +30,17 @@ public class Main {
 
 You will get a response similar to:
 
-```json
+```javascript
  [
-  0.5670403838157654,
+    0.5670403838157654,
-  0.009260174818336964,
+    0.009260174818336964,
-  0.23178744316101074,
+    0.23178744316101074,
-  -0.2916173040866852,
+    -0.2916173040866852,
-  -0.8924556970596313,
+    -0.8924556970596313,
-  0.8785552978515625,
+    0.8785552978515625,
-  -0.34576427936553955,
+    -0.34576427936553955,
-  0.5742510557174683,
+    0.5742510557174683,
-  -0.04222835972905159,
+    -0.04222835972905159,
-  -0.137906014919281
+    -0.137906014919281
 ]
 ```

docs/docs/apis-ask/prompt-builder.md

@@ -0,0 +1,73 @@
+---
+sidebar_position: 5
+---
+
+# Prompt Builder
+
+This is designed for prompt engineering. It allows you to easily build the prompt text for zero-shot, one-shot, few-shot
+inferences.
+
+```java
+
+import io.github.amithkoujalgi.ollama4j.core.OllamaAPI;
+import io.github.amithkoujalgi.ollama4j.core.models.OllamaResult;
+import io.github.amithkoujalgi.ollama4j.core.types.OllamaModelType;
+import io.github.amithkoujalgi.ollama4j.core.utils.PromptBuilder;
+
+public class AskPhi {
+    public static void main(String[] args) throws Exception {
+
+        String host = "http://localhost:11434/";
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+        ollamaAPI.setRequestTimeoutSeconds(10);
+
+        String model = OllamaModelType.PHI;
+
+        PromptBuilder promptBuilder =
+                new PromptBuilder()
+                        .addLine("You are an expert coder and understand different programming languages.")
+                        .addLine("Given a question, answer ONLY with code.")
+                        .addLine("Produce clean, formatted and indented code in markdown format.")
+                        .addLine(
+                                "DO NOT include ANY extra text apart from code. Follow this instruction very strictly!")
+                        .addLine("If there's any additional information you want to add, use comments within code.")
+                        .addLine("Answer only in the programming language that has been asked for.")
+                        .addSeparator()
+                        .addLine("Example: Sum 2 numbers in Python")
+                        .addLine("Answer:")
+                        .addLine("```python")
+                        .addLine("def sum(num1: int, num2: int) -> int:")
+                        .addLine("    return num1 + num2")
+                        .addLine("```")
+                        .addSeparator()
+                        .add("How do I read a file in Go and print its contents to stdout?");
+
+        OllamaResult response = ollamaAPI.ask(model, promptBuilder.build());
+        System.out.println(response.getResponse());
+    }
+}
+```
+
+You will get a response similar to:
+
+```go
+package main
+
+import (
+    "fmt"
+    "io/ioutil"
+)
+
+func readFile(fileName string) {
+    file, err := ioutil.ReadFile(fileName)
+    if err != nil {
+        fmt.Fprintln(os.Stderr, "Error reading file:", err.Error())
+        return
+    }
+
+    f, _ := ioutil.ReadFile("file.txt")
+    if f != nil {
+        fmt.Println(f.String())
+    }
+}
+```

docs/docs/apis-extras/options-builder.md

@@ -0,0 +1,53 @@
+---
+sidebar_position: 1
+---
+
+# Options Builder
+
+This lets you build options for the `ask()` API.
+Check out the supported
+options [here](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values).
+
+## Build an empty Options object
+
+```java
+import io.github.amithkoujalgi.ollama4j.core.utils.Options;
+import io.github.amithkoujalgi.ollama4j.core.utils.OptionsBuilder;
+
+public class Main {
+
+    public static void main(String[] args) {
+
+        String host = "http://localhost:11434/";
+
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+
+        Options options = new OptionsBuilder().build();
+    }
+}
+```
+
+## Build an empty Options object
+
+```java
+import io.github.amithkoujalgi.ollama4j.core.utils.Options;
+import io.github.amithkoujalgi.ollama4j.core.utils.OptionsBuilder;
+
+public class Main {
+
+    public static void main(String[] args) {
+
+        String host = "http://localhost:11434/";
+
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+
+        Options options =
+                new OptionsBuilder()
+                        .setMirostat(10)
+                        .setMirostatEta(0.5f)
+                        .setNumGpu(2)
+                        .setTemperature(1.5f)
+                        .build();
+    }
+}
+```

docs/docs/intro.md

@@ -2,10 +2,38 @@
 sidebar_position: 1
 ---
 
-# Intro
+# Introduction
 
 Let's get started with **Ollama4j**.
 
+## 🦙 What is Ollama?
+
+[Ollama](https://ollama.ai/) is an advanced AI tool that allows users to easily set up and run large language models
+locally (in CPU and GPU
+modes). With Ollama, users can leverage powerful language models such as Llama 2 and even customize and create their own
+models.
+
+## 👨‍💻 Why Ollama4j?
+
+Ollama4j was built for the simple purpose of integrating Ollama with Java applications.
+
+```mermaid
+  flowchart LR
+    o4j[Ollama4j]
+    o[Ollama Server]
+    o4j -->|Communicates with| o;
+    m[Models]
+    p[Your Java Project]
+    subgraph Your Java Environment
+        direction TB
+        p -->|Uses| o4j
+    end
+    subgraph Ollama Setup
+        direction TB
+        o -->|Manages| m
+    end
+```
+
 ## Getting Started
 
 ### What you'll need

docs/docusaurus.config.js

@@ -131,8 +131,13 @@ const config = {
             prism: {
                 theme: prismThemes.github,
                 darkTheme: prismThemes.dracula,
+                additionalLanguages: ['java'],
             },
         }),
+    markdown: {
+        mermaid: true,
+    },
+    themes: ['@docusaurus/theme-mermaid']
 };
 
 export default config;

docs/package.json

@@ -16,6 +16,7 @@
   "dependencies": {
     "@docusaurus/core": "3.0.1",
     "@docusaurus/preset-classic": "3.0.1",
+    "@docusaurus/theme-mermaid": "^3.0.1",
     "@mdx-js/react": "^3.0.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.3.0",

pom.xml

@@ -4,7 +4,7 @@
 
     <groupId>io.github.amithkoujalgi</groupId>
     <artifactId>ollama4j</artifactId>
-    <version>1.0.38</version>
+    <version>1.0.41</version>
 
   <name>Ollama4j</name>
   <description>Java library for interacting with Ollama API.</description>
@@ -39,7 +39,7 @@
     <connection>scm:git:git@github.com:amithkoujalgi/ollama4j.git</connection>
     <developerConnection>scm:git:https://github.com/amithkoujalgi/ollama4j.git</developerConnection>
     <url>https://github.com/amithkoujalgi/ollama4j</url>
-    <tag>v1.0.38</tag>
+    <tag>v1.0.41</tag>
   </scm>
 
   <build>

src/main/java/io/github/amithkoujalgi/ollama4j/core/OllamaAPI.java

@@ -6,6 +6,7 @@ import io.github.amithkoujalgi.ollama4j.core.models.request.CustomModelFileConte
 import io.github.amithkoujalgi.ollama4j.core.models.request.CustomModelFilePathRequest;
 import io.github.amithkoujalgi.ollama4j.core.models.request.ModelEmbeddingsRequest;
 import io.github.amithkoujalgi.ollama4j.core.models.request.ModelRequest;
+import io.github.amithkoujalgi.ollama4j.core.utils.Options;
 import io.github.amithkoujalgi.ollama4j.core.utils.Utils;
 import java.io.BufferedReader;
 import java.io.ByteArrayOutputStream;
@@ -332,11 +333,15 @@ public class OllamaAPI {
    *
    * @param model the ollama model to ask the question to
    * @param prompt the prompt/question text
+   * @param options the Options object - <a
+   *     href="https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values">More
+   *     details on the options</a>
    * @return OllamaResult that includes response text and time taken for response
    */
-  public OllamaResult ask(String model, String prompt)
+  public OllamaResult ask(String model, String prompt, Options options)
       throws OllamaBaseException, IOException, InterruptedException {
     OllamaRequestModel ollamaRequestModel = new OllamaRequestModel(model, prompt);
+    ollamaRequestModel.setOptions(options.getOptionsMap());
     return askSync(ollamaRequestModel);
   }
 

src/main/java/io/github/amithkoujalgi/ollama4j/core/models/OllamaRequestModel.java

@@ -1,10 +1,10 @@
 package io.github.amithkoujalgi.ollama4j.core.models;
 
-
 import static io.github.amithkoujalgi.ollama4j.core.utils.Utils.getObjectMapper;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
 import java.util.List;
+import java.util.Map;
 import lombok.Data;
 
 @Data
@@ -13,6 +13,7 @@ public class OllamaRequestModel {
   private String model;
   private String prompt;
   private List<String> images;
+  private Map<String, Object> options;
 
   public OllamaRequestModel(String model, String prompt) {
     this.model = model;

src/main/java/io/github/amithkoujalgi/ollama4j/core/types/OllamaModelType.java

@@ -21,6 +21,7 @@ public class OllamaModelType {
   public static final String VICUNA = "vicuna";
   public static final String WIZARD_VICUNA_UNCENSORED = "wizard-vicuna-uncensored";
   public static final String PHIND_CODELLAMA = "phind-codellama";
+  public static final String PHI = "phi";
   public static final String ZEPHYR = "zephyr";
   public static final String WIZARDCODER = "wizardcoder";
   public static final String MISTRAL_OPENORCA = "mistral-openorca";

src/main/java/io/github/amithkoujalgi/ollama4j/core/utils/Options.java

@@ -0,0 +1,11 @@
+package io.github.amithkoujalgi.ollama4j.core.utils;
+
+import java.util.Map;
+import lombok.Data;
+
+/** Class for options for Ollama model. */
+@Data
+public class Options {
+
+  private final Map<String, Object> optionsMap;
+}

src/main/java/io/github/amithkoujalgi/ollama4j/core/utils/OptionsBuilder.java

@@ -0,0 +1,218 @@
+package io.github.amithkoujalgi.ollama4j.core.utils;
+
+import java.util.HashMap;
+
+/** Builder class for creating options for Ollama model. */
+public class OptionsBuilder {
+
+  private final Options options;
+
+  /** Constructs a new OptionsBuilder with an empty options map. */
+  public OptionsBuilder() {
+    this.options = new Options(new HashMap<>());
+  }
+
+  /**
+   * Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2
+   * = Mirostat 2.0)
+   *
+   * @param value The value for the "mirostat" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setMirostat(int value) {
+    options.getOptionsMap().put("mirostat", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "mirostat_eta" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setMirostatEta(float value) {
+    options.getOptionsMap().put("mirostat_eta", value);
+    return this;
+  }
+
+  /**
+   * Controls the balance between coherence and diversity of the output. A lower value will result
+   * in more focused and coherent text. (Default: 5.0)
+   *
+   * @param value The value for the "mirostat_tau" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setMirostatTau(float value) {
+    options.getOptionsMap().put("mirostat_tau", value);
+    return this;
+  }
+
+  /**
+   * Sets the size of the context window used to generate the next token. (Default: 2048)
+   *
+   * @param value The value for the "num_ctx" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setNumCtx(int value) {
+    options.getOptionsMap().put("num_ctx", value);
+    return this;
+  }
+
+  /**
+   * The number of GQA groups in the transformer layer. Required for some models, for example, it is
+   * 8 for llama2:70b.
+   *
+   * @param value The value for the "num_gqa" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setNumGqa(int value) {
+    options.getOptionsMap().put("num_gqa", value);
+    return this;
+  }
+
+  /**
+   * The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support,
+   * 0 to disable.
+   *
+   * @param value The value for the "num_gpu" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setNumGpu(int value) {
+    options.getOptionsMap().put("num_gpu", value);
+    return this;
+  }
+
+  /**
+   * 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).
+   *
+   * @param value The value for the "num_thread" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setNumThread(int value) {
+    options.getOptionsMap().put("num_thread", value);
+    return this;
+  }
+
+  /**
+   * Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled,
+   * -1 = num_ctx)
+   *
+   * @param value The value for the "repeat_last_n" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setRepeatLastN(int value) {
+    options.getOptionsMap().put("repeat_last_n", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "repeat_penalty" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setRepeatPenalty(float value) {
+    options.getOptionsMap().put("repeat_penalty", value);
+    return this;
+  }
+
+  /**
+   * The temperature of the model. Increasing the temperature will make the model answer more
+   * creatively. (Default: 0.8)
+   *
+   * @param value The value for the "temperature" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setTemperature(float value) {
+    options.getOptionsMap().put("temperature", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "seed" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setSeed(int value) {
+    options.getOptionsMap().put("seed", value);
+    return this;
+  }
+
+  /**
+   * 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.
+   *
+   * @param value The value for the "stop" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setStop(String value) {
+    options.getOptionsMap().put("stop", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "tfs_z" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setTfsZ(float value) {
+    options.getOptionsMap().put("tfs_z", value);
+    return this;
+  }
+
+  /**
+   * Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite
+   * generation, -2 = fill context)
+   *
+   * @param value The value for the "num_predict" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setNumPredict(int value) {
+    options.getOptionsMap().put("num_predict", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "top_k" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setTopK(int value) {
+    options.getOptionsMap().put("top_k", value);
+    return this;
+  }
+
+  /**
+   * 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)
+   *
+   * @param value The value for the "top_p" parameter.
+   * @return The updated OptionsBuilder.
+   */
+  public OptionsBuilder setTopP(float value) {
+    options.getOptionsMap().put("top_p", value);
+    return this;
+  }
+
+  /**
+   * Builds the options map.
+   *
+   * @return The populated options map.
+   */
+  public Options build() {
+    return options;
+  }
+}

src/main/java/io/github/amithkoujalgi/ollama4j/core/utils/PromptBuilder.java

@@ -0,0 +1,69 @@
+package io.github.amithkoujalgi.ollama4j.core.utils;
+
+/**
+ * The {@code PromptBuilder} class is used to construct prompt texts for language models (LLMs). It
+ * provides methods for adding text, adding lines, adding separators, and building the final prompt.
+ *
+ * <p>Example usage:
+ *
+ * <pre>{@code
+ * PromptBuilder promptBuilder = new PromptBuilder();
+ * promptBuilder.add("This is a sample prompt for language models.")
+ *              .addLine("You can add lines to provide context.")
+ *              .addSeparator()
+ *              .add("Feel free to customize as needed.");
+ * String finalPrompt = promptBuilder.build();
+ * System.out.println(finalPrompt);
+ * }</pre>
+ */
+public class PromptBuilder {
+
+  private final StringBuilder prompt;
+
+  /** Constructs a new {@code PromptBuilder} with an empty prompt. */
+  public PromptBuilder() {
+    this.prompt = new StringBuilder();
+  }
+
+  /**
+   * Appends the specified text to the prompt.
+   *
+   * @param text the text to be added to the prompt
+   * @return a reference to this {@code PromptBuilder} instance for method chaining
+   */
+  public PromptBuilder add(String text) {
+    prompt.append(text);
+    return this;
+  }
+
+  /**
+   * Appends the specified text followed by a newline character to the prompt.
+   *
+   * @param text the text to be added as a line to the prompt
+   * @return a reference to this {@code PromptBuilder} instance for method chaining
+   */
+  public PromptBuilder addLine(String text) {
+    prompt.append(text).append("\n");
+    return this;
+  }
+
+  /**
+   * Appends a separator line to the prompt. The separator is a newline followed by a line of
+   * dashes.
+   *
+   * @return a reference to this {@code PromptBuilder} instance for method chaining
+   */
+  public PromptBuilder addSeparator() {
+    prompt.append("\n--------------------------------------------------\n");
+    return this;
+  }
+
+  /**
+   * Builds and returns the final prompt as a string.
+   *
+   * @return the final prompt as a string
+   */
+  public String build() {
+    return prompt.toString();
+  }
+}

src/test/java/io/github/amithkoujalgi/ollama4j/unittests/TestMockedAPIs.java

@@ -8,6 +8,7 @@ import io.github.amithkoujalgi.ollama4j.core.models.ModelDetail;
 import io.github.amithkoujalgi.ollama4j.core.models.OllamaAsyncResultCallback;
 import io.github.amithkoujalgi.ollama4j.core.models.OllamaResult;
 import io.github.amithkoujalgi.ollama4j.core.types.OllamaModelType;
+import io.github.amithkoujalgi.ollama4j.core.utils.OptionsBuilder;
 import java.io.IOException;
 import java.net.URISyntaxException;
 import java.util.ArrayList;
@@ -100,10 +101,12 @@ class TestMockedAPIs {
     OllamaAPI ollamaAPI = Mockito.mock(OllamaAPI.class);
     String model = OllamaModelType.LLAMA2;
     String prompt = "some prompt text";
+    OptionsBuilder optionsBuilder = new OptionsBuilder();
     try {
-      when(ollamaAPI.ask(model, prompt)).thenReturn(new OllamaResult("", 0, 200));
+      when(ollamaAPI.ask(model, prompt, optionsBuilder.build()))
-      ollamaAPI.ask(model, prompt);
+          .thenReturn(new OllamaResult("", 0, 200));
-      verify(ollamaAPI, times(1)).ask(model, prompt);
+      ollamaAPI.ask(model, prompt, optionsBuilder.build());
+      verify(ollamaAPI, times(1)).ask(model, prompt, optionsBuilder.build());
     } catch (IOException | OllamaBaseException | InterruptedException e) {
       throw new RuntimeException(e);
     }