Merge pull request #92 from ollama4j/90

Addresses issue where creation of model was failing

.github/workflows/label-issue-stale.yml

@@ -0,0 +1,24 @@
+name: Mark stale issues
+
+on:
+  workflow_dispatch: # for manual run
+  schedule:
+    - cron: '0 0 * * *'  # Runs every day at midnight
+
+permissions:
+  contents: write # only for delete-branch option
+  issues: write
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Mark stale issues
+        uses: actions/stale@v8
+        with:
+          repo-token: ${{ github.token }}
+          days-before-stale: 15
+          stale-issue-message: 'This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.'
+          days-before-close: 7
+          stale-issue-label: 'stale'
+          exempt-issue-labels: 'pinned,security'

.github/workflows/publish-docs.yml

@@ -63,12 +63,12 @@ jobs:
           working-directory: "."
 
       - name: Setup Pages
-        uses: actions/configure-pages@v3
+        uses: actions/configure-pages@v5
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v2
+        uses: actions/upload-pages-artifact@v3
         with:
           # Upload entire repository
           path: './docs/build/.'
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v2
+        uses: actions/deploy-pages@v4

.github/workflows/run-tests.yml

@@ -0,0 +1,29 @@
+name: Run Tests
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch name to run tests on'
+        required: true
+        default: 'main'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ github.event.inputs.branch }}
+
+      - name: Set up JDK 17
+        uses: actions/setup-java@v3
+        with:
+          java-version: '17'
+          distribution: 'temurin'
+          server-id: github
+          settings-path: ${{ github.workspace }}
+
+      - name: Run unit tests
+        run: mvn clean test -Punit-tests

README.md

@@ -153,7 +153,7 @@ In your Maven project, add this dependency:
 <dependency>
     <groupId>io.github.ollama4j</groupId>
     <artifactId>ollama4j</artifactId>
-    <version>1.0.89</version>
+    <version>1.0.93</version>
 </dependency>
 ```
 
@@ -209,7 +209,7 @@ In your Maven project, add this dependency:
 <dependency>
     <groupId>io.github.ollama4j</groupId>
     <artifactId>ollama4j</artifactId>
-    <version>1.0.89</version>
+    <version>1.0.93</version>
 </dependency>
 ```
 
@@ -219,7 +219,7 @@ In your Maven project, add this dependency:
 
 ```groovy
 dependencies {
-    implementation 'io.github.ollama4j:ollama4j:1.0.79'
+    implementation 'io.github.ollama4j:ollama4j:1.0.93'
 }
 ```
 
@@ -283,6 +283,8 @@ If you like or are using this project to build your own, please give us a star.
 | 7 | Katie Backend     | An open-source AI-based question-answering platform for accessing private domain knowledge                    | [GitHub](https://github.com/wyona/katie-backend)                                                                                               |
 | 8 | TeleLlama3 Bot    | A question-answering Telegram bot                                                                             | [Repo](https://git.hiast.edu.sy/mohamadbashar.disoki/telellama3-bot)                                                                           |
 | 9 | moqui-wechat      | A moqui-wechat component                                                                                      | [GitHub](https://github.com/heguangyong/moqui-wechat)                                                                                          |
+| 10 | B4X      | A set of simple and powerful RAD tool for Desktop and Server development                                              | [Website](https://www.b4x.com/android/forum/threads/ollama4j-library-pnd_ollama4j-your-local-offline-llm-like-chatgpt.165003/)     |                                                              
+
 
 ## Traction
 

docs/docs/apis-generate/generate-with-tools.md

@@ -521,6 +521,23 @@ public class MyOllamaService{
 }
 ```
 
+Or, if one needs to provide an object instance directly:
+```java
+public class MyOllamaService{
+    
+    public void chatWithAnnotatedTool(){
+        ollamaAPI.registerAnnotatedTools(new BackendService());
+        OllamaChatRequest requestModel = builder
+                .withMessage(OllamaChatMessageRole.USER,
+                        "Compute the most important constant in the world using 5 digits")
+                .build();
+
+        OllamaChatResult chatResult = ollamaAPI.chat(requestModel);
+    }
+    
+}
+```
+
 The request should be the following:
 
 ```json
@@ -622,4 +639,4 @@ public String getCurrentFuelPrice(String location, String fuelType) {
 }
 ```
 
-Updating async/chat APIs with support for tool-based generation. 
+Updating async/chat APIs with support for tool-based generation. 

docs/docs/apis-model-management/create-model.md

@@ -6,7 +6,7 @@ sidebar_position: 5
 
 This API lets you create a custom model on the Ollama server.
 
-### Create a model from an existing Modelfile in the Ollama server
+### Create a custom model from an existing model in the Ollama server
 
 ```java title="CreateModel.java"
 import io.github.ollama4j.OllamaAPI;
@@ -19,144 +19,220 @@ public class CreateModel {
 
         OllamaAPI ollamaAPI = new OllamaAPI(host);
 
-        ollamaAPI.createModelWithFilePath("mario", "/path/to/mario/modelfile/on/ollama-server");
-    }
-}
-```
-
-### 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.");
+        ollamaAPI.createModel(CustomModelRequest.builder().model("mario").from("llama3.2:latest").system("You are Mario from Super Mario Bros.").build());
     }
 }
 ```
 
 Once created, you can see it when you use [list models](./list-models) API.
 
-### Example of a `Modelfile`
+[Read more](https://github.com/ollama/ollama/blob/main/docs/api.md#create-a-model) about custom model creation and the parameters available for model creation.
 
-```
-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
+[//]: # ()
+[//]: # (### Example of a `Modelfile`)
 
-# 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`
+[//]: # (FROM llama2)
 
-```modelfile
-# comment
-INSTRUCTION arguments
-```
+[//]: # (# sets the temperature to 1 [higher is more creative, lower is more coherent])
 
-| 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 temperature 1)
 
-#### PARAMETER
+[//]: # (# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token)
 
-The `PARAMETER` instruction defines a parameter that can be set when the model is run.
+[//]: # (PARAMETER num_ctx 4096)
 
-| 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            |
+[//]: # ()
+[//]: # (# sets a custom system message to specify the behavior of the chat assistant)
 
-#### TEMPLATE
+[//]: # (SYSTEM You are Mario from super mario bros, acting as an assistant.)
 
-`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
+[//]: # ()
+[//]: # (### Format of the `Modelfile`)
 
-| 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)
 
-```modelfile
-TEMPLATE """
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
+[//]: # (# comment)
 
-### User:
-{{ .Prompt }}
+[//]: # (INSTRUCTION arguments)
 
-### Response:
-"""
+[//]: # (```)
 
-SYSTEM """<system message>"""
-```
+[//]: # ()
+[//]: # (| Instruction                         | Description                                                    |)
 
-### SYSTEM
+[//]: # (|-------------------------------------|----------------------------------------------------------------|)
 
-The `SYSTEM` instruction specifies the system message to be used in the template, if applicable.
+[//]: # (| [`FROM`]&#40;#from-required&#41; &#40;required&#41; | Defines the base model to use.                                 |)
 
-```modelfile
-SYSTEM """<system message>"""
-```
+[//]: # (| [`PARAMETER`]&#40;#parameter&#41;           | Sets the parameters for how Ollama will run the model.         |)
 
-### ADAPTER
+[//]: # (| [`TEMPLATE`]&#40;#template&#41;             | The full prompt template to be sent to the model.              |)
 
-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.
+[//]: # (| [`SYSTEM`]&#40;#system&#41;                 | Specifies the system message that will be set in the template. |)
 
-```modelfile
-ADAPTER ./ollama-lora.bin
-```
+[//]: # (| [`ADAPTER`]&#40;#adapter&#41;               | Defines the &#40;Q&#41;LoRA adapters to apply to the model.            |)
 
-### LICENSE
+[//]: # (| [`LICENSE`]&#40;#license&#41;               | Specifies the legal license.                                   |)
 
-The `LICENSE` instruction allows you to specify the legal license under which the model used with this Modelfile is
-shared or distributed.
+[//]: # ()
+[//]: # (#### PARAMETER)
 
-```modelfile
-LICENSE """
-<license text>
-"""
-```
+[//]: # ()
+[//]: # (The `PARAMETER` instruction defines a parameter that can be set when the model is run.)
 
-## Notes
+[//]: # ()
+[//]: # (| Parameter      | Description                                                                                                                                                                                                                                             | Value Type | Example Usage        |)
 
-- 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
+[//]: # (| mirostat       | Enable Mirostat sampling for controlling perplexity. &#40;default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0&#41;                                                                                                                                         | 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. &#40;Default: 0.1&#41;                        | 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. &#40;Default: 5.0&#41;                                                                                                         | float      | mirostat_tau 5.0     |)
+
+[//]: # (| num_ctx        | Sets the size of the context window used to generate the next token. &#40;Default: 2048&#41;                                                                                                                                                                    | 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&#40;s&#41;. 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 &#40;as opposed to the logical number of cores&#41;. | int        | num_thread 8         |)
+
+[//]: # (| repeat_last_n  | Sets how far back for the model to look back to prevent repetition. &#40;Default: 64, 0 = disabled, -1 = num_ctx&#41;                                                                                                                                           | int        | repeat_last_n 64     |)
+
+[//]: # (| repeat_penalty | Sets how strongly to penalize repetitions. A higher value &#40;e.g., 1.5&#41; will penalize repetitions more strongly, while a lower value &#40;e.g., 0.9&#41; will be more lenient. &#40;Default: 1.1&#41;                                                                     | float      | repeat_penalty 1.1   |)
+
+[//]: # (| temperature    | The temperature of the model. Increasing the temperature will make the model answer more creatively. &#40;Default: 0.8&#41;                                                                                                                                     | 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. &#40;Default: 0&#41;                                                                                       | 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 &#40;e.g., 2.0&#41; will reduce the impact more, while a value of 1.0 disables this setting. &#40;default: 1&#41;                                               | float      | tfs_z 1              |)
+
+[//]: # (| num_predict    | Maximum number of tokens to predict when generating text. &#40;Default: 128, -1 = infinite generation, -2 = fill context&#41;                                                                                                                                   | int        | num_predict 42       |)
+
+[//]: # (| top_k          | Reduces the probability of generating nonsense. A higher value &#40;e.g. 100&#41; will give more diverse answers, while a lower value &#40;e.g. 10&#41; will be more conservative. &#40;Default: 40&#41;                                                                        | int        | top_k 40             |)
+
+[//]: # (| top_p          | Works together with top-k. A higher value &#40;e.g., 0.95&#41; will lead to more diverse text, while a lower value &#40;e.g., 0.5&#41; will generate more focused and conservative text. &#40;Default: 0.9&#41;                                                                 | float      | top_p 0.9            |)
+
+[//]: # ()
+[//]: # (#### TEMPLATE)
+
+[//]: # ()
+[//]: # (`TEMPLATE` of the full prompt template to be passed into the model. It may include &#40;optionally&#41; 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)

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

@@ -11,6 +11,7 @@ import io.github.ollama4j.models.embeddings.OllamaEmbeddingsRequestModel;
 import io.github.ollama4j.models.embeddings.OllamaEmbedResponseModel;
 import io.github.ollama4j.models.generate.OllamaGenerateRequest;
 import io.github.ollama4j.models.generate.OllamaStreamHandler;
+import io.github.ollama4j.models.generate.OllamaTokenHandler;
 import io.github.ollama4j.models.ps.ModelsProcessResponse;
 import io.github.ollama4j.models.request.*;
 import io.github.ollama4j.models.response.*;
@@ -390,6 +391,7 @@ public class OllamaAPI {
      * @throws InterruptedException if the operation is interrupted
      * @throws URISyntaxException   if the URI for the request is malformed
      */
+    @Deprecated
     public void createModelWithFilePath(String modelName, String modelFilePath) throws IOException, InterruptedException, OllamaBaseException, URISyntaxException {
         String url = this.host + "/api/create";
         String jsonData = new CustomModelFilePathRequest(modelName, modelFilePath).toString();
@@ -422,6 +424,7 @@ public class OllamaAPI {
      * @throws InterruptedException if the operation is interrupted
      * @throws URISyntaxException   if the URI for the request is malformed
      */
+    @Deprecated
     public void createModelWithModelFileContents(String modelName, String modelFileContents) throws IOException, InterruptedException, OllamaBaseException, URISyntaxException {
         String url = this.host + "/api/create";
         String jsonData = new CustomModelFileContentsRequest(modelName, modelFileContents).toString();
@@ -441,6 +444,35 @@ public class OllamaAPI {
         }
     }
 
+    /**
+     * Create a custom model. Read more about custom model creation <a
+     * href="https://github.com/ollama/ollama/blob/main/docs/api.md#create-a-model">here</a>.
+     *
+     * @param customModelRequest custom model spec
+     * @throws OllamaBaseException  if the response indicates an error status
+     * @throws IOException          if an I/O error occurs during the HTTP request
+     * @throws InterruptedException if the operation is interrupted
+     * @throws URISyntaxException   if the URI for the request is malformed
+     */
+    public void createModel(CustomModelRequest customModelRequest) throws IOException, InterruptedException, OllamaBaseException, URISyntaxException {
+        String url = this.host + "/api/create";
+        String jsonData = customModelRequest.toString();
+        HttpRequest request = getRequestBuilderDefault(new URI(url)).header("Accept", "application/json").header("Content-Type", "application/json").POST(HttpRequest.BodyPublishers.ofString(jsonData, StandardCharsets.UTF_8)).build();
+        HttpClient client = HttpClient.newHttpClient();
+        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
+        int statusCode = response.statusCode();
+        String responseString = response.body();
+        if (statusCode != 200) {
+            throw new OllamaBaseException(statusCode + " - " + responseString);
+        }
+        if (responseString.contains("error")) {
+            throw new OllamaBaseException(responseString);
+        }
+        if (verbose) {
+            logger.info(responseString);
+        }
+    }
+
     /**
      * Delete a model from Ollama server.
      *
@@ -609,9 +641,9 @@ public class OllamaAPI {
         OllamaToolsResult toolResult = new OllamaToolsResult();
         Map<ToolFunctionCallSpec, Object> toolResults = new HashMap<>();
 
-        if(!prompt.startsWith("[AVAILABLE_TOOLS]")){
+        if (!prompt.startsWith("[AVAILABLE_TOOLS]")) {
             final Tools.PromptBuilder promptBuilder = new Tools.PromptBuilder();
-            for(Tools.ToolSpecification spec :  toolRegistry.getRegisteredSpecs()) {
+            for (Tools.ToolSpecification spec : toolRegistry.getRegisteredSpecs()) {
                 promptBuilder.withToolSpecification(spec);
             }
             promptBuilder.withPrompt(prompt);
@@ -785,15 +817,34 @@ public class OllamaAPI {
      * @throws InterruptedException if the operation is interrupted
      */
     public OllamaChatResult chat(OllamaChatRequest request, OllamaStreamHandler streamHandler) throws OllamaBaseException, IOException, InterruptedException {
+        return chatStreaming(request, new OllamaChatStreamObserver(streamHandler));
+    }
+
+    /**
+     * Ask a question to a model using an {@link OllamaChatRequest}. This can be constructed using an {@link OllamaChatRequestBuilder}.
+     * <p>
+     * Hint: the OllamaChatRequestModel#getStream() property is not implemented.
+     *
+     * @param request      request object to be sent to the server
+     * @param tokenHandler callback handler to handle the last token from stream (caution: all previous messages from stream will be concatenated)
+     * @return {@link OllamaChatResult}
+     * @throws OllamaBaseException  any response code than 200 has been returned
+     * @throws IOException          in case the responseStream can not be read
+     * @throws InterruptedException in case the server is not reachable or network issues happen
+     * @throws OllamaBaseException  if the response indicates an error status
+     * @throws IOException          if an I/O error occurs during the HTTP request
+     * @throws InterruptedException if the operation is interrupted
+     */
+    public OllamaChatResult chatStreaming(OllamaChatRequest request, OllamaTokenHandler tokenHandler) throws OllamaBaseException, IOException, InterruptedException {
         OllamaChatEndpointCaller requestCaller = new OllamaChatEndpointCaller(host, basicAuth, requestTimeoutSeconds, verbose);
         OllamaChatResult result;
 
         // add all registered tools to Request
         request.setTools(toolRegistry.getRegisteredSpecs().stream().map(Tools.ToolSpecification::getToolPrompt).collect(Collectors.toList()));
 
-        if (streamHandler != null) {
+        if (tokenHandler != null) {
             request.setStream(true);
-            result = requestCaller.call(request, streamHandler);
+            result = requestCaller.call(request, tokenHandler);
         } else {
             result = requestCaller.callSync(request);
         }
@@ -801,17 +852,17 @@ public class OllamaAPI {
         // check if toolCallIsWanted
         List<OllamaChatToolCalls> toolCalls = result.getResponseModel().getMessage().getToolCalls();
         int toolCallTries = 0;
-        while(toolCalls != null && !toolCalls.isEmpty() && toolCallTries < maxChatToolCallRetries){
-            for (OllamaChatToolCalls toolCall : toolCalls){
+        while (toolCalls != null && !toolCalls.isEmpty() && toolCallTries < maxChatToolCallRetries) {
+            for (OllamaChatToolCalls toolCall : toolCalls) {
                 String toolName = toolCall.getFunction().getName();
                 ToolFunction toolFunction = toolRegistry.getToolFunction(toolName);
                 Map<String, Object> arguments = toolCall.getFunction().getArguments();
                 Object res = toolFunction.apply(arguments);
-                request.getMessages().add(new OllamaChatMessage(OllamaChatMessageRole.TOOL,"[TOOL_RESULTS]" + toolName + "(" + arguments.keySet() +") : " + res + "[/TOOL_RESULTS]"));
+                request.getMessages().add(new OllamaChatMessage(OllamaChatMessageRole.TOOL, "[TOOL_RESULTS]" + toolName + "(" + arguments.keySet() + ") : " + res + "[/TOOL_RESULTS]"));
             }
 
-            if (streamHandler != null) {
-                result = requestCaller.call(request, streamHandler);
+            if (tokenHandler != null) {
+                result = requestCaller.call(request, tokenHandler);
             } else {
                 result = requestCaller.callSync(request);
             }
@@ -822,92 +873,101 @@ public class OllamaAPI {
         return result;
     }
 
+    /**
+     * Registers a single tool in the tool registry using the provided tool specification.
+     *
+     * @param toolSpecification the specification of the tool to register. It contains the
+     *                          tool's function name and other relevant information.
+     */
     public void registerTool(Tools.ToolSpecification toolSpecification) {
         toolRegistry.addTool(toolSpecification.getFunctionName(), toolSpecification);
     }
 
-    public void registerAnnotatedTools()  {
-        Class<?> callerClass = null;
+    /**
+     * Registers multiple tools in the tool registry using a list of tool specifications.
+     * Iterates over the list and adds each tool specification to the registry.
+     *
+     * @param toolSpecifications a list of tool specifications to register. Each specification
+     *                           contains information about a tool, such as its function name.
+     */
+    public void registerTools(List<Tools.ToolSpecification> toolSpecifications) {
+        for (Tools.ToolSpecification toolSpecification : toolSpecifications) {
+            toolRegistry.addTool(toolSpecification.getFunctionName(), toolSpecification);
+        }
+    }
+
+    /**
+     * Registers tools based on the annotations found on the methods of the caller's class and its providers.
+     * This method scans the caller's class for the {@link OllamaToolService} annotation and recursively registers
+     * annotated tools from all the providers specified in the annotation.
+     *
+     * @throws IllegalStateException if the caller's class is not annotated with {@link OllamaToolService}.
+     * @throws RuntimeException      if any reflection-based instantiation or invocation fails.
+     */
+    public void registerAnnotatedTools() {
         try {
-            callerClass = Class.forName(Thread.currentThread().getStackTrace()[2].getClassName());
-        } catch (ClassNotFoundException e) {
+            Class<?> callerClass = null;
+            try {
+                callerClass = Class.forName(Thread.currentThread().getStackTrace()[2].getClassName());
+            } catch (ClassNotFoundException e) {
+                throw new RuntimeException(e);
+            }
+
+            OllamaToolService ollamaToolServiceAnnotation = callerClass.getDeclaredAnnotation(OllamaToolService.class);
+            if (ollamaToolServiceAnnotation == null) {
+                throw new IllegalStateException(callerClass + " is not annotated as " + OllamaToolService.class);
+            }
+
+            Class<?>[] providers = ollamaToolServiceAnnotation.providers();
+            for (Class<?> provider : providers) {
+                registerAnnotatedTools(provider.getDeclaredConstructor().newInstance());
+            }
+        } catch (InstantiationException | NoSuchMethodException | IllegalAccessException |
+                 InvocationTargetException e) {
             throw new RuntimeException(e);
         }
+    }
 
-        OllamaToolService ollamaToolServiceAnnotation = callerClass.getDeclaredAnnotation(OllamaToolService.class);
-        if(ollamaToolServiceAnnotation == null) {
-            throw new IllegalStateException(callerClass + " is not annotated as " + OllamaToolService.class);
-        }
+    /**
+     * Registers tools based on the annotations found on the methods of the provided object.
+     * This method scans the methods of the given object and registers tools using the {@link ToolSpec} annotation
+     * and associated {@link ToolProperty} annotations. It constructs tool specifications and stores them in a tool registry.
+     *
+     * @param object the object whose methods are to be inspected for annotated tools.
+     * @throws RuntimeException if any reflection-based instantiation or invocation fails.
+     */
+    public void registerAnnotatedTools(Object object) {
+        Class<?> objectClass = object.getClass();
+        Method[] methods = objectClass.getMethods();
+        for (Method m : methods) {
+            ToolSpec toolSpec = m.getDeclaredAnnotation(ToolSpec.class);
+            if (toolSpec == null) {
+                continue;
+            }
+            String operationName = !toolSpec.name().isBlank() ? toolSpec.name() : m.getName();
+            String operationDesc = !toolSpec.desc().isBlank() ? toolSpec.desc() : operationName;
 
-        Class<?>[] providers = ollamaToolServiceAnnotation.providers();
-
-        for(Class<?> provider : providers){
-            Method[] methods = provider.getMethods();
-            for(Method m : methods) {
-                ToolSpec toolSpec = m.getDeclaredAnnotation(ToolSpec.class);
-                if(toolSpec == null){
+            final Tools.PropsBuilder propsBuilder = new Tools.PropsBuilder();
+            LinkedHashMap<String, String> methodParams = new LinkedHashMap<>();
+            for (Parameter parameter : m.getParameters()) {
+                final ToolProperty toolPropertyAnn = parameter.getDeclaredAnnotation(ToolProperty.class);
+                String propType = parameter.getType().getTypeName();
+                if (toolPropertyAnn == null) {
+                    methodParams.put(parameter.getName(), null);
                     continue;
                 }
-                String operationName = !toolSpec.name().isBlank() ? toolSpec.name() : m.getName();
-                String operationDesc = !toolSpec.desc().isBlank() ? toolSpec.desc() : operationName;
-
-                final Tools.PropsBuilder propsBuilder = new Tools.PropsBuilder();
-                LinkedHashMap<String,String> methodParams = new LinkedHashMap<>();
-                for (Parameter parameter : m.getParameters()) {
-                    final ToolProperty toolPropertyAnn = parameter.getDeclaredAnnotation(ToolProperty.class);
-                    String propType = parameter.getType().getTypeName();
-                    if(toolPropertyAnn == null) {
-                        methodParams.put(parameter.getName(),null);
-                        continue;
-                    }
-                    String propName = !toolPropertyAnn.name().isBlank() ? toolPropertyAnn.name() : parameter.getName();
-                    methodParams.put(propName,propType);
-                    propsBuilder.withProperty(propName,Tools.PromptFuncDefinition.Property.builder()
-                            .type(propType)
-                            .description(toolPropertyAnn.desc())
-                            .required(toolPropertyAnn.required())
-                            .build());
-                }
-                final Map<String, Tools.PromptFuncDefinition.Property> params = propsBuilder.build();
-                List<String> reqProps = params.entrySet().stream()
-                        .filter(e -> e.getValue().isRequired())
-                        .map(Map.Entry::getKey)
-                        .collect(Collectors.toList());
-
-                Tools.ToolSpecification toolSpecification = Tools.ToolSpecification.builder()
-                        .functionName(operationName)
-                        .functionDescription(operationDesc)
-                        .toolPrompt(
-                                Tools.PromptFuncDefinition.builder().type("function").function(
-                                        Tools.PromptFuncDefinition.PromptFuncSpec.builder()
-                                                .name(operationName)
-                                                .description(operationDesc)
-                                                .parameters(
-                                                        Tools.PromptFuncDefinition.Parameters.builder()
-                                                                .type("object")
-                                                                .properties(
-                                                                        params
-                                                                )
-                                                                .required(reqProps)
-                                                                .build()
-                                                ).build()
-                                ).build()
-                        )
-                        .build();
-
-                try {
-                    ReflectionalToolFunction reflectionalToolFunction =
-                            new ReflectionalToolFunction(provider.getDeclaredConstructor().newInstance()
-                                    ,m
-                                    ,methodParams);
-
-                    toolSpecification.setToolFunction(reflectionalToolFunction);
-                    toolRegistry.addTool(toolSpecification.getFunctionName(),toolSpecification);
-                } catch (InstantiationException | IllegalAccessException | InvocationTargetException |
-                         NoSuchMethodException e) {
-                    throw new RuntimeException(e);
-                }
+                String propName = !toolPropertyAnn.name().isBlank() ? toolPropertyAnn.name() : parameter.getName();
+                methodParams.put(propName, propType);
+                propsBuilder.withProperty(propName, Tools.PromptFuncDefinition.Property.builder().type(propType).description(toolPropertyAnn.desc()).required(toolPropertyAnn.required()).build());
             }
+            final Map<String, Tools.PromptFuncDefinition.Property> params = propsBuilder.build();
+            List<String> reqProps = params.entrySet().stream().filter(e -> e.getValue().isRequired()).map(Map.Entry::getKey).collect(Collectors.toList());
+
+            Tools.ToolSpecification toolSpecification = Tools.ToolSpecification.builder().functionName(operationName).functionDescription(operationDesc).toolPrompt(Tools.PromptFuncDefinition.builder().type("function").function(Tools.PromptFuncDefinition.PromptFuncSpec.builder().name(operationName).description(operationDesc).parameters(Tools.PromptFuncDefinition.Parameters.builder().type("object").properties(params).required(reqProps).build()).build()).build()).build();
+
+            ReflectionalToolFunction reflectionalToolFunction = new ReflectionalToolFunction(object, m, methodParams);
+            toolSpecification.setToolFunction(reflectionalToolFunction);
+            toolRegistry.addTool(toolSpecification.getFunctionName(), toolSpecification);
         }
 
     }
@@ -945,14 +1005,39 @@ public class OllamaAPI {
 
     // technical private methods //
 
+    /**
+     * Utility method to encode a file into a Base64 encoded string.
+     *
+     * @param file the file to be encoded into Base64.
+     * @return a Base64 encoded string representing the contents of the file.
+     * @throws IOException if an I/O error occurs during reading the file.
+     */
     private static String encodeFileToBase64(File file) throws IOException {
         return Base64.getEncoder().encodeToString(Files.readAllBytes(file.toPath()));
     }
 
+    /**
+     * Utility method to encode a byte array into a Base64 encoded string.
+     *
+     * @param bytes the byte array to be encoded into Base64.
+     * @return a Base64 encoded string representing the byte array.
+     */
     private static String encodeByteArrayToBase64(byte[] bytes) {
         return Base64.getEncoder().encodeToString(bytes);
     }
 
+    /**
+     * Generates a request for the Ollama API and returns the result.
+     * This method synchronously calls the Ollama API. If a stream handler is provided,
+     * the request will be streamed; otherwise, a regular synchronous request will be made.
+     *
+     * @param ollamaRequestModel the request model containing necessary parameters for the Ollama API request.
+     * @param streamHandler      the stream handler to process streaming responses, or null for non-streaming requests.
+     * @return the result of the Ollama API request.
+     * @throws OllamaBaseException  if the request fails due to an issue with the Ollama API.
+     * @throws IOException          if an I/O error occurs during the request process.
+     * @throws InterruptedException if the thread is interrupted during the request.
+     */
     private OllamaResult generateSyncForOllamaRequestModel(OllamaGenerateRequest ollamaRequestModel, OllamaStreamHandler streamHandler) throws OllamaBaseException, IOException, InterruptedException {
         OllamaGenerateEndpointCaller requestCaller = new OllamaGenerateEndpointCaller(host, basicAuth, requestTimeoutSeconds, verbose);
         OllamaResult result;
@@ -965,6 +1050,7 @@ public class OllamaAPI {
         return result;
     }
 
+
     /**
      * Get default request builder.
      *

src/main/java/io/github/ollama4j/models/chat/OllamaChatStreamObserver.java

@@ -1,31 +1,19 @@
 package io.github.ollama4j.models.chat;
 
 import io.github.ollama4j.models.generate.OllamaStreamHandler;
+import io.github.ollama4j.models.generate.OllamaTokenHandler;
+import lombok.RequiredArgsConstructor;
 
-import java.util.ArrayList;
-import java.util.List;
-
-public class OllamaChatStreamObserver {
-
-    private OllamaStreamHandler streamHandler;
-
-    private List<OllamaChatResponseModel> responseParts = new ArrayList<>();
-
+@RequiredArgsConstructor
+public class OllamaChatStreamObserver implements OllamaTokenHandler {
+    private final OllamaStreamHandler streamHandler;
     private String message = "";
 
-    public OllamaChatStreamObserver(OllamaStreamHandler streamHandler) {
-        this.streamHandler = streamHandler;
+    @Override
+    public void accept(OllamaChatResponseModel token) {
+        if (streamHandler != null) {
+            message += token.getMessage().getContent();
+            streamHandler.accept(message);
+        }
     }
-
-    public void notify(OllamaChatResponseModel currentResponsePart) {
-        responseParts.add(currentResponsePart);
-        handleCurrentResponsePart(currentResponsePart);
-    }
-
-    protected void handleCurrentResponsePart(OllamaChatResponseModel currentResponsePart) {
-        message = message + currentResponsePart.getMessage().getContent();
-        streamHandler.accept(message);
-    }
-
-
 }

src/main/java/io/github/ollama4j/models/embeddings/OllamaEmbedRequestBuilder.java

@@ -5,7 +5,7 @@ import io.github.ollama4j.utils.Options;
 import java.util.List;
 
 /**
- * Builderclass to easily create Requests for Embedding models using ollama.
+ * Builder class to easily create Requests for Embedding models using ollama.
  */
 public class OllamaEmbedRequestBuilder {
 

src/main/java/io/github/ollama4j/models/generate/OllamaTokenHandler.java

@@ -0,0 +1,8 @@
+package io.github.ollama4j.models.generate;
+
+import io.github.ollama4j.models.chat.OllamaChatResponseModel;
+
+import java.util.function.Consumer;
+
+public interface OllamaTokenHandler extends Consumer<OllamaChatResponseModel> {
+}

src/main/java/io/github/ollama4j/models/request/CustomModelRequest.java

@@ -0,0 +1,45 @@
+package io.github.ollama4j.models.request;
+
+import static io.github.ollama4j.utils.Utils.getObjectMapper;
+
+import com.fasterxml.jackson.core.JsonProcessingException;
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.Data;
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+
+import java.util.List;
+import java.util.Map;
+
+
+@Data
+@AllArgsConstructor
+@Builder
+public class CustomModelRequest {
+    private String model;
+    private String from;
+    private Map<String, String> files;
+    private Map<String, String> adapters;
+    private String template;
+    private Object license; // Using Object to handle both String and List<String>
+    private String system;
+    private Map<String, Object> parameters;
+    private List<Object> messages;
+    private Boolean stream;
+    private Boolean quantize;
+
+    public CustomModelRequest() {
+        this.stream = true;
+        this.quantize = false;
+    }
+
+    @Override
+    public String toString() {
+        try {
+            return getObjectMapper().writerWithDefaultPrettyPrinter().writeValueAsString(this);
+        } catch (JsonProcessingException e) {
+            throw new RuntimeException(e);
+        }
+    }
+}

src/main/java/io/github/ollama4j/models/request/OllamaChatEndpointCaller.java

@@ -4,9 +4,8 @@ import com.fasterxml.jackson.core.JsonProcessingException;
 import com.fasterxml.jackson.core.type.TypeReference;
 import io.github.ollama4j.exceptions.OllamaBaseException;
 import io.github.ollama4j.models.chat.*;
+import io.github.ollama4j.models.generate.OllamaTokenHandler;
 import io.github.ollama4j.models.response.OllamaErrorResponse;
-import io.github.ollama4j.models.generate.OllamaStreamHandler;
-import io.github.ollama4j.tools.Tools;
 import io.github.ollama4j.utils.Utils;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -29,7 +28,7 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
 
     private static final Logger LOG = LoggerFactory.getLogger(OllamaChatEndpointCaller.class);
 
-    private OllamaChatStreamObserver streamObserver;
+    private OllamaTokenHandler tokenHandler;
 
     public OllamaChatEndpointCaller(String host, BasicAuth basicAuth, long requestTimeoutSeconds, boolean verbose) {
         super(host, basicAuth, requestTimeoutSeconds, verbose);
@@ -60,8 +59,8 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
             OllamaChatMessage message = ollamaResponseModel.getMessage();
             if(message != null) {
                 responseBuffer.append(message.getContent());
-                if (streamObserver != null) {
-                    streamObserver.notify(ollamaResponseModel);
+                if (tokenHandler != null) {
+                    tokenHandler.accept(ollamaResponseModel);
                 }
             }
             return ollamaResponseModel.isDone();
@@ -71,9 +70,9 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
         }
     }
 
-    public OllamaChatResult call(OllamaChatRequest body, OllamaStreamHandler streamHandler)
+    public OllamaChatResult call(OllamaChatRequest body, OllamaTokenHandler tokenHandler)
             throws OllamaBaseException, IOException, InterruptedException {
-        streamObserver = new OllamaChatStreamObserver(streamHandler);
+        this.tokenHandler = tokenHandler;
         return callSync(body);
     }
 
@@ -86,7 +85,7 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
                         .POST(
                                 body.getBodyPublisher());
         HttpRequest request = requestBuilder.build();
-        if (isVerbose()) LOG.info("Asking model: " + body.toString());
+        if (isVerbose()) LOG.info("Asking model: " + body);
         HttpResponse<InputStream> response =
                 httpClient.send(request, HttpResponse.BodyHandlers.ofInputStream());
 

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

@@ -15,6 +15,7 @@ public class OllamaModelType {
     public static final String LLAMA3_1 = "llama3.1";
     public static final String MISTRAL = "mistral";
     public static final String MIXTRAL = "mixtral";
+    public static final String DEEPSEEK_R1 = "deepseek-r1";
     public static final String LLAVA = "llava";
     public static final String LLAVA_PHI3 = "llava-phi3";
     public static final String NEURAL_CHAT = "neural-chat";

src/test/java/io/github/ollama4j/integrationtests/TestRealAPIs.java

@@ -321,7 +321,7 @@ class TestRealAPIs {
             assertEquals(1, function.getArguments().size());
             Object noOfDigits = function.getArguments().get("noOfDigits");
             assertNotNull(noOfDigits);
-            assertEquals("5",noOfDigits);
+            assertEquals("5", noOfDigits.toString());
             assertTrue(chatResult.getChatHistory().size()>2);
             List<OllamaChatToolCalls> finalToolCalls = chatResult.getResponseModel().getMessage().getToolCalls();
             assertNull(finalToolCalls);
@@ -338,7 +338,7 @@ class TestRealAPIs {
             ollamaAPI.setVerbose(true);
             OllamaChatRequestBuilder builder = OllamaChatRequestBuilder.getInstance(config.getModel());
 
-            ollamaAPI.registerAnnotatedTools();
+            ollamaAPI.registerAnnotatedTools(new AnnotatedTool());
 
             OllamaChatRequest requestModel = builder
                     .withMessage(OllamaChatMessageRole.USER,

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

@@ -6,6 +6,7 @@ import io.github.ollama4j.exceptions.RoleNotFoundException;
 import io.github.ollama4j.models.chat.OllamaChatMessageRole;
 import io.github.ollama4j.models.embeddings.OllamaEmbedRequestModel;
 import io.github.ollama4j.models.embeddings.OllamaEmbedResponseModel;
+import io.github.ollama4j.models.request.CustomModelRequest;
 import io.github.ollama4j.models.response.ModelDetail;
 import io.github.ollama4j.models.response.OllamaAsyncResultStreamer;
 import io.github.ollama4j.models.response.OllamaResult;
@@ -52,12 +53,11 @@ class TestMockedAPIs {
     @Test
     void testCreateModel() {
         OllamaAPI ollamaAPI = Mockito.mock(OllamaAPI.class);
-        String model = OllamaModelType.LLAMA2;
-        String modelFilePath = "FROM llama2\nSYSTEM You are mario from Super Mario Bros.";
+        CustomModelRequest customModelRequest = CustomModelRequest.builder().model("mario").from("llama3.2:latest").system("You are Mario from Super Mario Bros.").build();
         try {
-            doNothing().when(ollamaAPI).createModelWithModelFileContents(model, modelFilePath);
-            ollamaAPI.createModelWithModelFileContents(model, modelFilePath);
-            verify(ollamaAPI, times(1)).createModelWithModelFileContents(model, modelFilePath);
+            doNothing().when(ollamaAPI).createModel(customModelRequest);
+            ollamaAPI.createModel(customModelRequest);
+            verify(ollamaAPI, times(1)).createModel(customModelRequest);
         } catch (IOException | OllamaBaseException | InterruptedException | URISyntaxException e) {
             throw new RuntimeException(e);
         }