[maven-release-plugin] prepare release v1.0.40

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/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,
-  0.009260174818336964,
-  0.23178744316101074,
-  -0.2916173040866852,
-  -0.8924556970596313,
-  0.8785552978515625,
-  -0.34576427936553955,
-  0.5742510557174683,
-  -0.04222835972905159,
-  -0.137906014919281
+    0.5670403838157654,
+    0.009260174818336964,
+    0.23178744316101074,
+    -0.2916173040866852,
+    -0.8924556970596313,
+    0.8785552978515625,
+    -0.34576427936553955,
+    0.5742510557174683,
+    -0.04222835972905159,
+    -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-model-management/create-model.md

@@ -6,6 +6,8 @@ sidebar_position: 4
 
 This API lets you create a custom model on the Ollama server.
 
+### Create a model from an existing Modelfile in the Ollama server
+
 ```java title="CreateModel.java"
 public class CreateModel {
 
@@ -15,9 +17,144 @@ public class CreateModel {
 
         OllamaAPI ollamaAPI = new OllamaAPI(host);
 
-        ollamaAPI.createModel("mycustommodel", "/path/to/modelfile/on/ollama-server");
+        ollamaAPI.createModelWithFilePath("mario", "/path/to/mario/modelfile/on/ollama-server");
     }
 }
 ```
 
-Once created, you can see it when you use [list models](./list-models) API.
+### Create a model by passing the contents of Modelfile
+
+```java title="CreateModel.java"
+public class CreateModel {
+
+    public static void main(String[] args) {
+
+        String host = "http://localhost:11434/";
+
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+
+        ollamaAPI.createModelWithModelFileContents("mario", "FROM llama2\nSYSTEM You are mario from Super Mario Bros.");
+    }
+}
+```
+
+Once created, you can see it when you use [list models](./list-models) API.
+
+### Example of a `Modelfile`
+
+```
+FROM llama2
+# sets the temperature to 1 [higher is more creative, lower is more coherent]
+PARAMETER temperature 1
+# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
+PARAMETER num_ctx 4096
+
+# sets a custom system message to specify the behavior of the chat assistant
+SYSTEM You are Mario from super mario bros, acting as an assistant.
+```
+
+### Format of the `Modelfile`
+
+```modelfile
+# comment
+INSTRUCTION arguments
+```
+
+| Instruction                         | Description                                                    |
+|-------------------------------------|----------------------------------------------------------------|
+| [`FROM`](#from-required) (required) | Defines the base model to use.                                 |
+| [`PARAMETER`](#parameter)           | Sets the parameters for how Ollama will run the model.         |
+| [`TEMPLATE`](#template)             | The full prompt template to be sent to the model.              |
+| [`SYSTEM`](#system)                 | Specifies the system message that will be set in the template. |
+| [`ADAPTER`](#adapter)               | Defines the (Q)LoRA adapters to apply to the model.            |
+| [`LICENSE`](#license)               | Specifies the legal license.                                   |
+
+#### PARAMETER
+
+The `PARAMETER` instruction defines a parameter that can be set when the model is run.
+
+| Parameter      | Description                                                                                                                                                                                                                                             | Value Type | Example Usage        |
+|----------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------|----------------------|
+| mirostat       | Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)                                                                                                                                         | int        | mirostat 0           |
+| mirostat_eta   | 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)                        | float      | mirostat_eta 0.1     |
+| mirostat_tau   | Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)                                                                                                         | float      | mirostat_tau 5.0     |
+| num_ctx        | Sets the size of the context window used to generate the next token. (Default: 2048)                                                                                                                                                                    | int        | num_ctx 4096         |
+| num_gqa        | The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b                                                                                                                                         | int        | num_gqa 1            |
+| num_gpu        | The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.                                                                                                                                            | int        | num_gpu 50           |
+| num_thread     | 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). | int        | num_thread 8         |
+| repeat_last_n  | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)                                                                                                                                           | int        | repeat_last_n 64     |
+| repeat_penalty | 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)                                                                     | float      | repeat_penalty 1.1   |
+| temperature    | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)                                                                                                                                     | float      | temperature 0.7      |
+| seed           | 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)                                                                                       | int        | seed 42              |
+| stop           | 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.                                      | string     | stop "AI assistant:" |
+| tfs_z          | 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)                                               | float      | tfs_z 1              |
+| num_predict    | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)                                                                                                                                   | int        | num_predict 42       |
+| top_k          | 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)                                                                        | int        | top_k 40             |
+| top_p          | 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)                                                                 | float      | top_p 0.9            |
+
+#### TEMPLATE
+
+`TEMPLATE` of the full prompt template to be passed into the model. It may include (optionally) a system message and a
+user's prompt. This is used to create a full custom prompt, and syntax may be model specific. You can usually find the
+template for a given model in the readme for that model.
+
+#### Template Variables
+
+| Variable        | Description                                                                                                   |
+|-----------------|---------------------------------------------------------------------------------------------------------------|
+| `{{ .System }}` | The system message used to specify custom behavior, this must also be set in the Modelfile as an instruction. |
+| `{{ .Prompt }}` | The incoming prompt, this is not specified in the model file and will be set based on input.                  |
+| `{{ .First }}`  | A boolean value used to render specific template information for the first generation of a session.           |
+
+```modelfile
+TEMPLATE """
+{{- if .First }}
+### System:
+{{ .System }}
+{{- end }}
+
+### User:
+{{ .Prompt }}
+
+### Response:
+"""
+
+SYSTEM """<system message>"""
+```
+
+### SYSTEM
+
+The `SYSTEM` instruction specifies the system message to be used in the template, if applicable.
+
+```modelfile
+SYSTEM """<system message>"""
+```
+
+### ADAPTER
+
+The `ADAPTER` instruction specifies the LoRA adapter to apply to the base model. The value of this instruction should be
+an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be
+tuned from the base model otherwise the behaviour is undefined.
+
+```modelfile
+ADAPTER ./ollama-lora.bin
+```
+
+### LICENSE
+
+The `LICENSE` instruction allows you to specify the legal license under which the model used with this Modelfile is
+shared or distributed.
+
+```modelfile
+LICENSE """
+<license text>
+"""
+```
+
+## Notes
+
+- the **`Modelfile` is not case sensitive**. In the examples, uppercase instructions are used to make it easier to
+  distinguish it from arguments.
+- Instructions can be in any order. In the examples, the `FROM` instruction is first to keep it easily readable.
+
+Read more about Modelfile: https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md

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>1.0.36</version>
+    <version>1.0.40</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>v1.0.36</tag>
+    <tag>v1.0.40</tag>
   </scm>
 
   <build>

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

@@ -123,9 +123,9 @@ public class OllamaAsyncResultCallback extends Thread {
   }
 
   /**
-   * Returns the final response when the execution completes. Does not return intermediate results.
+   * Returns the final completion/response when the execution completes. Does not return intermediate results.
    *
-   * @return String - response text
+   * @return String completion/response text
    */
   public String getResponse() {
     return result;

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

@@ -13,9 +13,9 @@ import lombok.Getter;
 public class OllamaResult {
   /**
    * -- GETTER --
-   *  Get the response text
+   *  Get the completion/response text
    *
-   * @return String - response text
+   * @return String completion/response text
    */
   private final String response;
 

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/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();
+  }
+}