diff --git a/docs/blog/2025-03-08-blog/index.md b/docs/blog/2025-03-08-blog/index.md
index b702f39..347ed86 100644
--- a/docs/blog/2025-03-08-blog/index.md
+++ b/docs/blog/2025-03-08-blog/index.md
@@ -337,7 +337,7 @@ import com.couchbase.client.java.Scope;
 import com.couchbase.client.java.json.JsonObject;
 import com.couchbase.client.java.query.QueryResult;
 import io.github.ollama4j.OllamaAPI;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.exceptions.ToolInvocationException;
 import io.github.ollama4j.tools.OllamaToolsResult;
 import io.github.ollama4j.tools.ToolFunction;
@@ -356,7 +356,7 @@ import java.util.Map;
 
 public class CouchbaseToolCallingExample {
 
-    public static void main(String[] args) throws IOException, ToolInvocationException, OllamaBaseException, InterruptedException {
+    public static void main(String[] args) throws IOException, ToolInvocationException, OllamaException, InterruptedException {
         String connectionString = Utilities.getFromEnvVar("CB_CLUSTER_URL");
         String username = Utilities.getFromEnvVar("CB_CLUSTER_USERNAME");
         String password = Utilities.getFromEnvVar("CB_CLUSTER_PASSWORD");
diff --git a/docs/docs/apis-extras/ps.md b/docs/docs/apis-extras/ps.md
index faea1c3..b4822f2 100644
--- a/docs/docs/apis-extras/ps.md
+++ b/docs/docs/apis-extras/ps.md
@@ -12,11 +12,8 @@ This API corresponds to the [PS](https://github.com/ollama/ollama/blob/main/docs
 package io.github.ollama4j.localtests;
 
 import io.github.ollama4j.OllamaAPI;
-import io.github.ollama4j.exceptions.OllamaBaseException;
 import io.github.ollama4j.models.ps.ModelsProcessResponse;
 
-import java.io.IOException;
-
 public class Main {
     public static void main(String[] args) {
 
diff --git a/src/main/java/io/github/ollama4j/OllamaAPI.java b/src/main/java/io/github/ollama4j/OllamaAPI.java
index ef0b843..7347844 100644
--- a/src/main/java/io/github/ollama4j/OllamaAPI.java
+++ b/src/main/java/io/github/ollama4j/OllamaAPI.java
@@ -9,7 +9,7 @@
 package io.github.ollama4j;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.exceptions.RoleNotFoundException;
 import io.github.ollama4j.exceptions.ToolInvocationException;
 import io.github.ollama4j.metrics.MetricsRecorder;
@@ -150,9 +150,9 @@ public class OllamaAPI {
      * Checks the reachability of the Ollama server.
      *
      * @return true if the server is reachable, false otherwise
-     * @throws OllamaBaseException if the ping fails
+     * @throws OllamaException if the ping fails
      */
-    public boolean ping() throws OllamaBaseException {
+    public boolean ping() throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/tags";
         int statusCode = -1;
@@ -175,7 +175,7 @@ public class OllamaAPI {
             statusCode = response.statusCode();
             return statusCode == 200;
         } catch (Exception e) {
-            throw new OllamaBaseException("Ping failed", e);
+            throw new OllamaException("Ping failed", e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -186,9 +186,9 @@ public class OllamaAPI {
      * Provides a list of running models and details about each model currently loaded into memory.
      *
      * @return ModelsProcessResponse containing details about the running models
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public ModelsProcessResponse ps() throws OllamaBaseException {
+    public ModelsProcessResponse ps() throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/ps";
         int statusCode = -1;
@@ -208,7 +208,7 @@ public class OllamaAPI {
                                 .GET()
                                 .build();
             } catch (URISyntaxException e) {
-                throw new OllamaBaseException(e.getMessage(), e);
+                throw new OllamaException(e.getMessage(), e);
             }
             HttpResponse<String> response = null;
             response = httpClient.send(httpRequest, HttpResponse.BodyHandlers.ofString());
@@ -218,10 +218,10 @@ public class OllamaAPI {
                 return Utils.getObjectMapper()
                         .readValue(responseString, ModelsProcessResponse.class);
             } else {
-                throw new OllamaBaseException(statusCode + " - " + responseString);
+                throw new OllamaException(statusCode + " - " + responseString);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException("ps failed", e);
+            throw new OllamaException("ps failed", e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -232,9 +232,9 @@ public class OllamaAPI {
      * Lists available models from the Ollama server.
      *
      * @return a list of models available on the server
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public List<Model> listModels() throws OllamaBaseException {
+    public List<Model> listModels() throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/tags";
         int statusCode = -1;
@@ -260,10 +260,10 @@ public class OllamaAPI {
                         .readValue(responseString, ListModelsResponse.class)
                         .getModels();
             } else {
-                throw new OllamaBaseException(statusCode + " - " + responseString);
+                throw new OllamaException(statusCode + " - " + responseString);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -309,9 +309,9 @@ public class OllamaAPI {
      * Internal method to pull a model from the Ollama server.
      *
      * @param modelName the name of the model to pull
-     * @throws OllamaBaseException if the pull fails
+     * @throws OllamaException if the pull fails
      */
-    private void doPullModel(String modelName) throws OllamaBaseException {
+    private void doPullModel(String modelName) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/pull";
         int statusCode = -1;
@@ -348,13 +348,13 @@ public class OllamaAPI {
             }
             if (!success) {
                 LOG.error("Model pull failed or returned invalid status.");
-                throw new OllamaBaseException("Model pull failed or returned invalid status.");
+                throw new OllamaException("Model pull failed or returned invalid status.");
             }
             if (statusCode != 200) {
-                throw new OllamaBaseException(statusCode + " - " + responseString);
+                throw new OllamaException(statusCode + " - " + responseString);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -368,18 +368,18 @@ public class OllamaAPI {
      * @param modelPullResponse the response from the model pull
      * @param modelName the name of the model
      * @return true if the pull was successful, false otherwise
-     * @throws OllamaBaseException if the response contains an error
+     * @throws OllamaException if the response contains an error
      */
     @SuppressWarnings("RedundantIfStatement")
     private boolean processModelPullResponse(ModelPullResponse modelPullResponse, String modelName)
-            throws OllamaBaseException {
+            throws OllamaException {
         if (modelPullResponse == null) {
             LOG.error("Received null response for model pull.");
             return false;
         }
         String error = modelPullResponse.getError();
         if (error != null && !error.trim().isEmpty()) {
-            throw new OllamaBaseException("Model pull failed: " + error);
+            throw new OllamaException("Model pull failed: " + error);
         }
         String status = modelPullResponse.getStatus();
         if (status != null) {
@@ -395,9 +395,9 @@ public class OllamaAPI {
      * Gets the Ollama server version.
      *
      * @return the version string
-     * @throws OllamaBaseException if the request fails
+     * @throws OllamaException if the request fails
      */
-    public String getVersion() throws OllamaBaseException {
+    public String getVersion() throws OllamaException {
         String url = "/api/version";
         long startTime = System.currentTimeMillis();
         int statusCode = -1;
@@ -423,10 +423,10 @@ public class OllamaAPI {
                         .readValue(responseString, OllamaVersion.class)
                         .getVersion();
             } else {
-                throw new OllamaBaseException(statusCode + " - " + responseString);
+                throw new OllamaException(statusCode + " - " + responseString);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -439,9 +439,9 @@ public class OllamaAPI {
      * in the format "name:tag" to pull the corresponding model.
      *
      * @param modelName the name/tag of the model to be pulled. Ex: llama3:latest
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public void pullModel(String modelName) throws OllamaBaseException {
+    public void pullModel(String modelName) throws OllamaException {
         try {
             if (numberOfRetriesForModelPull == 0) {
                 this.doPullModel(modelName);
@@ -453,7 +453,7 @@ public class OllamaAPI {
                 try {
                     this.doPullModel(modelName);
                     return;
-                } catch (OllamaBaseException e) {
+                } catch (OllamaException e) {
                     handlePullRetry(
                             modelName,
                             numberOfRetries,
@@ -462,14 +462,14 @@ public class OllamaAPI {
                     numberOfRetries++;
                 }
             }
-            throw new OllamaBaseException(
+            throw new OllamaException(
                     "Failed to pull model "
                             + modelName
                             + " after "
                             + numberOfRetriesForModelPull
                             + " retries");
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         }
     }
 
@@ -478,9 +478,9 @@ public class OllamaAPI {
      *
      * @param modelName the model name
      * @return the model details
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public ModelDetail getModelDetails(String modelName) throws OllamaBaseException {
+    public ModelDetail getModelDetails(String modelName) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/show";
         int statusCode = -1;
@@ -505,10 +505,10 @@ public class OllamaAPI {
             if (statusCode == 200) {
                 return Utils.getObjectMapper().readValue(responseBody, ModelDetail.class);
             } else {
-                throw new OllamaBaseException(statusCode + " - " + responseBody);
+                throw new OllamaException(statusCode + " - " + responseBody);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -520,9 +520,9 @@ public class OllamaAPI {
      * <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 OllamaException if the response indicates an error status
      */
-    public void createModel(CustomModelRequest customModelRequest) throws OllamaBaseException {
+    public void createModel(CustomModelRequest customModelRequest) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/create";
         int statusCode = -1;
@@ -549,7 +549,7 @@ public class OllamaAPI {
                 String errorBody =
                         new String(response.body().readAllBytes(), StandardCharsets.UTF_8);
                 out = errorBody;
-                throw new OllamaBaseException(statusCode + " - " + errorBody);
+                throw new OllamaException(statusCode + " - " + errorBody);
             }
             try (BufferedReader reader =
                     new BufferedReader(
@@ -563,13 +563,13 @@ public class OllamaAPI {
                     LOG.debug(res.getStatus());
                     if (res.getError() != null) {
                         out = res.getError();
-                        throw new OllamaBaseException(res.getError());
+                        throw new OllamaException(res.getError());
                     }
                 }
                 out = lines;
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -581,10 +581,9 @@ public class OllamaAPI {
      *
      * @param modelName the name of the model to be deleted
      * @param ignoreIfNotPresent ignore errors if the specified model is not present on the Ollama server
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public void deleteModel(String modelName, boolean ignoreIfNotPresent)
-            throws OllamaBaseException {
+    public void deleteModel(String modelName, boolean ignoreIfNotPresent) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/delete";
         int statusCode = -1;
@@ -616,10 +615,10 @@ public class OllamaAPI {
                 return;
             }
             if (statusCode != 200) {
-                throw new OllamaBaseException(statusCode + " - " + responseBody);
+                throw new OllamaException(statusCode + " - " + responseBody);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(statusCode + " - " + out, e);
+            throw new OllamaException(statusCode + " - " + out, e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -633,9 +632,9 @@ public class OllamaAPI {
      * unloaded from memory.
      *
      * @param modelName the name of the model to unload
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
-    public void unloadModel(String modelName) throws OllamaBaseException {
+    public void unloadModel(String modelName) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/generate";
         int statusCode = -1;
@@ -673,11 +672,11 @@ public class OllamaAPI {
             }
             if (statusCode != 200) {
                 LOG.debug("Unload response: {} - {}", statusCode, responseBody);
-                throw new OllamaBaseException(statusCode + " - " + responseBody);
+                throw new OllamaException(statusCode + " - " + responseBody);
             }
         } catch (Exception e) {
             LOG.debug("Unload failed: {} - {}", statusCode, out);
-            throw new OllamaBaseException(statusCode + " - " + out, e);
+            throw new OllamaException(statusCode + " - " + out, e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -689,10 +688,10 @@ public class OllamaAPI {
      *
      * @param modelRequest request for '/api/embed' endpoint
      * @return embeddings
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
     public OllamaEmbedResponseModel embed(OllamaEmbedRequestModel modelRequest)
-            throws OllamaBaseException {
+            throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/embed";
         int statusCode = -1;
@@ -715,10 +714,10 @@ public class OllamaAPI {
                 return Utils.getObjectMapper()
                         .readValue(responseBody, OllamaEmbedResponseModel.class);
             } else {
-                throw new OllamaBaseException(statusCode + " - " + responseBody);
+                throw new OllamaException(statusCode + " - " + responseBody);
             }
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, "", false, false, false, null, null, startTime, statusCode, out);
@@ -732,11 +731,11 @@ public class OllamaAPI {
      * @param request the generation request
      * @param streamObserver the stream observer for streaming responses, or null for synchronous
      * @return the result of the generation
-     * @throws OllamaBaseException if the request fails
+     * @throws OllamaException if the request fails
      */
     public OllamaResult generate(
             OllamaGenerateRequest request, OllamaGenerateStreamObserver streamObserver)
-            throws OllamaBaseException {
+            throws OllamaException {
         try {
             if (request.isUseTools()) {
                 return generateWithToolsInternal(request, streamObserver);
@@ -755,14 +754,14 @@ public class OllamaAPI {
             }
             return generateSyncForOllamaRequestModel(request, null, null);
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         }
     }
 
     // (No javadoc for private helper, as is standard)
     private OllamaResult generateWithToolsInternal(
             OllamaGenerateRequest request, OllamaGenerateStreamObserver streamObserver)
-            throws OllamaBaseException {
+            throws OllamaException {
         ArrayList<OllamaChatMessage> msgs = new ArrayList<>();
         OllamaChatRequest chatRequest = new OllamaChatRequest();
         chatRequest.setModel(request.getModel());
@@ -799,10 +798,10 @@ public class OllamaAPI {
      * @param raw whether to use raw mode
      * @param think whether to use "think" mode
      * @return an OllamaAsyncResultStreamer for streaming results
-     * @throws OllamaBaseException if the request fails
+     * @throws OllamaException if the request fails
      */
     public OllamaAsyncResultStreamer generateAsync(
-            String model, String prompt, boolean raw, boolean think) throws OllamaBaseException {
+            String model, String prompt, boolean raw, boolean think) throws OllamaException {
         long startTime = System.currentTimeMillis();
         String url = "/api/generate";
         int statusCode = -1;
@@ -819,7 +818,7 @@ public class OllamaAPI {
             statusCode = ollamaAsyncResultStreamer.getHttpStatusCode();
             return ollamaAsyncResultStreamer;
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     url, model, raw, think, true, null, null, startTime, statusCode, null);
@@ -836,10 +835,10 @@ public class OllamaAPI {
      * @param tokenHandler callback handler to handle the last token from stream (caution: the
      *     previous tokens from stream will not be concatenated)
      * @return {@link OllamaChatResult}
-     * @throws OllamaBaseException if the response indicates an error status
+     * @throws OllamaException if the response indicates an error status
      */
     public OllamaChatResult chat(OllamaChatRequest request, OllamaChatTokenHandler tokenHandler)
-            throws OllamaBaseException {
+            throws OllamaException {
         try {
             OllamaChatEndpointCaller requestCaller =
                     new OllamaChatEndpointCaller(host, auth, requestTimeoutSeconds);
@@ -909,7 +908,7 @@ public class OllamaAPI {
             }
             return result;
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         }
     }
 
@@ -947,17 +946,17 @@ public class OllamaAPI {
      * 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 OllamaBaseException if the caller's class is not annotated with {@link
+     * @throws OllamaException if the caller's class is not annotated with {@link
      *     OllamaToolService} or if reflection-based instantiation or invocation fails
      */
-    public void registerAnnotatedTools() throws OllamaBaseException {
+    public void registerAnnotatedTools() throws OllamaException {
         try {
             Class<?> callerClass = null;
             try {
                 callerClass =
                         Class.forName(Thread.currentThread().getStackTrace()[2].getClassName());
             } catch (ClassNotFoundException e) {
-                throw new OllamaBaseException(e.getMessage(), e);
+                throw new OllamaException(e.getMessage(), e);
             }
 
             OllamaToolService ollamaToolServiceAnnotation =
@@ -975,7 +974,7 @@ public class OllamaAPI {
                 | NoSuchMethodException
                 | IllegalAccessException
                 | InvocationTargetException e) {
-            throw new OllamaBaseException(e.getMessage());
+            throw new OllamaException(e.getMessage());
         }
     }
 
@@ -1100,13 +1099,13 @@ public class OllamaAPI {
      * @param thinkingStreamHandler the stream handler for "thinking" tokens, or null if not used
      * @param responseStreamHandler 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 OllamaException if the request fails due to an issue with the Ollama API
      */
     private OllamaResult generateSyncForOllamaRequestModel(
             OllamaGenerateRequest ollamaRequestModel,
             OllamaGenerateTokenHandler thinkingStreamHandler,
             OllamaGenerateTokenHandler responseStreamHandler)
-            throws OllamaBaseException {
+            throws OllamaException {
         long startTime = System.currentTimeMillis();
         int statusCode = -1;
         Object out = null;
@@ -1126,7 +1125,7 @@ public class OllamaAPI {
             out = result;
             return result;
         } catch (Exception e) {
-            throw new OllamaBaseException(e.getMessage(), e);
+            throw new OllamaException(e.getMessage(), e);
         } finally {
             MetricsRecorder.record(
                     OllamaGenerateEndpointCaller.endpoint,
diff --git a/src/main/java/io/github/ollama4j/exceptions/OllamaBaseException.java b/src/main/java/io/github/ollama4j/exceptions/OllamaException.java
similarity index 67%
rename from src/main/java/io/github/ollama4j/exceptions/OllamaBaseException.java
rename to src/main/java/io/github/ollama4j/exceptions/OllamaException.java
index d6f312e..7570c10 100644
--- a/src/main/java/io/github/ollama4j/exceptions/OllamaBaseException.java
+++ b/src/main/java/io/github/ollama4j/exceptions/OllamaException.java
@@ -8,13 +8,13 @@
 */
 package io.github.ollama4j.exceptions;
 
-public class OllamaBaseException extends Exception {
+public class OllamaException extends Exception {
 
-    public OllamaBaseException(String message) {
+    public OllamaException(String message) {
         super(message);
     }
 
-    public OllamaBaseException(String message, Exception exception) {
+    public OllamaException(String message, Exception exception) {
         super(message, exception);
     }
 }
diff --git a/src/main/java/io/github/ollama4j/models/request/OllamaChatEndpointCaller.java b/src/main/java/io/github/ollama4j/models/request/OllamaChatEndpointCaller.java
index 952e094..a08cd18 100644
--- a/src/main/java/io/github/ollama4j/models/request/OllamaChatEndpointCaller.java
+++ b/src/main/java/io/github/ollama4j/models/request/OllamaChatEndpointCaller.java
@@ -10,7 +10,7 @@ package io.github.ollama4j.models.request;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
 import com.fasterxml.jackson.core.type.TypeReference;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.metrics.MetricsRecorder;
 import io.github.ollama4j.models.chat.*;
 import io.github.ollama4j.models.chat.OllamaChatTokenHandler;
@@ -82,13 +82,13 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
     }
 
     public OllamaChatResult call(OllamaChatRequest body, OllamaChatTokenHandler tokenHandler)
-            throws OllamaBaseException, IOException, InterruptedException {
+            throws OllamaException, IOException, InterruptedException {
         this.tokenHandler = tokenHandler;
         return callSync(body);
     }
 
     public OllamaChatResult callSync(OllamaChatRequest body)
-            throws OllamaBaseException, IOException, InterruptedException {
+            throws OllamaException, IOException, InterruptedException {
         long startTime = System.currentTimeMillis();
         HttpClient httpClient = HttpClient.newHttpClient();
         URI uri = URI.create(getHost() + endpoint);
@@ -143,7 +143,7 @@ public class OllamaChatEndpointCaller extends OllamaEndpointCaller {
         if (statusCode != 200) {
             LOG.error("Status code: {}", statusCode);
             System.out.println(responseBuffer);
-            throw new OllamaBaseException(responseBuffer.toString());
+            throw new OllamaException(responseBuffer.toString());
         }
         if (wantedToolsForStream != null && ollamaChatResponseModel != null) {
             ollamaChatResponseModel.getMessage().setToolCalls(wantedToolsForStream);
diff --git a/src/main/java/io/github/ollama4j/models/request/OllamaGenerateEndpointCaller.java b/src/main/java/io/github/ollama4j/models/request/OllamaGenerateEndpointCaller.java
index 253a20e..fcd16fc 100644
--- a/src/main/java/io/github/ollama4j/models/request/OllamaGenerateEndpointCaller.java
+++ b/src/main/java/io/github/ollama4j/models/request/OllamaGenerateEndpointCaller.java
@@ -9,7 +9,7 @@
 package io.github.ollama4j.models.request;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.models.generate.OllamaGenerateResponseModel;
 import io.github.ollama4j.models.generate.OllamaGenerateStreamObserver;
 import io.github.ollama4j.models.generate.OllamaGenerateTokenHandler;
@@ -67,7 +67,7 @@ public class OllamaGenerateEndpointCaller extends OllamaEndpointCaller {
             OllamaRequestBody body,
             OllamaGenerateTokenHandler thinkingStreamHandler,
             OllamaGenerateTokenHandler responseStreamHandler)
-            throws OllamaBaseException, IOException, InterruptedException {
+            throws OllamaException, IOException, InterruptedException {
         responseStreamObserver =
                 new OllamaGenerateStreamObserver(thinkingStreamHandler, responseStreamHandler);
         return callSync(body);
@@ -79,13 +79,13 @@ public class OllamaGenerateEndpointCaller extends OllamaEndpointCaller {
      *
      * @param body POST body payload
      * @return result answer given by the assistant
-     * @throws OllamaBaseException any response code than 200 has been returned
+     * @throws OllamaException 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
      */
     @SuppressWarnings("DuplicatedCode")
     public OllamaResult callSync(OllamaRequestBody body)
-            throws OllamaBaseException, IOException, InterruptedException {
+            throws OllamaException, IOException, InterruptedException {
         long startTime = System.currentTimeMillis();
         HttpClient httpClient = HttpClient.newHttpClient();
         URI uri = URI.create(getHost() + endpoint);
@@ -127,7 +127,7 @@ public class OllamaGenerateEndpointCaller extends OllamaEndpointCaller {
         if (statusCode != 200) {
             LOG.error("Status code: {}", statusCode);
             LOG.error("Response: {}", responseBuffer);
-            throw new OllamaBaseException(responseBuffer.toString());
+            throw new OllamaException(responseBuffer.toString());
         } else {
             long endTime = System.currentTimeMillis();
             OllamaResult ollamaResult =
diff --git a/src/main/java/io/github/ollama4j/models/response/OllamaAsyncResultStreamer.java b/src/main/java/io/github/ollama4j/models/response/OllamaAsyncResultStreamer.java
index 07df702..4929c81 100644
--- a/src/main/java/io/github/ollama4j/models/response/OllamaAsyncResultStreamer.java
+++ b/src/main/java/io/github/ollama4j/models/response/OllamaAsyncResultStreamer.java
@@ -8,7 +8,7 @@
 */
 package io.github.ollama4j.models.response;
 
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.models.generate.OllamaGenerateRequest;
 import io.github.ollama4j.models.generate.OllamaGenerateResponseModel;
 import io.github.ollama4j.utils.Constants;
@@ -146,9 +146,9 @@ public class OllamaAsyncResultStreamer extends Thread {
                 }
             }
             if (statusCode != 200) {
-                throw new OllamaBaseException(this.completeResponse);
+                throw new OllamaException(this.completeResponse);
             }
-        } catch (IOException | InterruptedException | OllamaBaseException e) {
+        } catch (IOException | InterruptedException | OllamaException e) {
             this.succeeded = false;
             this.completeResponse = "[FAILED] " + e.getMessage();
         }
diff --git a/src/main/java/io/github/ollama4j/tools/Tools.java b/src/main/java/io/github/ollama4j/tools/Tools.java
index a82a717..79fa8e6 100644
--- a/src/main/java/io/github/ollama4j/tools/Tools.java
+++ b/src/main/java/io/github/ollama4j/tools/Tools.java
@@ -31,7 +31,7 @@ public class Tools {
         @JsonProperty("function")
         private ToolSpec toolSpec;
 
-        private String type = "function";
+        @Builder.Default private String type = "function";
         @JsonIgnore private ToolFunction toolFunction;
     }
 
diff --git a/src/test/java/io/github/ollama4j/integrationtests/OllamaAPIIntegrationTest.java b/src/test/java/io/github/ollama4j/integrationtests/OllamaAPIIntegrationTest.java
index 741956b..16cc6e1 100644
--- a/src/test/java/io/github/ollama4j/integrationtests/OllamaAPIIntegrationTest.java
+++ b/src/test/java/io/github/ollama4j/integrationtests/OllamaAPIIntegrationTest.java
@@ -11,7 +11,7 @@ package io.github.ollama4j.integrationtests;
 import static org.junit.jupiter.api.Assertions.*;
 
 import io.github.ollama4j.OllamaAPI;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.impl.ConsoleOutputChatTokenHandler;
 import io.github.ollama4j.impl.ConsoleOutputGenerateTokenHandler;
 import io.github.ollama4j.models.chat.*;
@@ -144,7 +144,7 @@ class OllamaAPIIntegrationTest {
     @Order(1)
     void shouldThrowConnectExceptionForWrongEndpoint() {
         OllamaAPI ollamaAPI = new OllamaAPI("http://wrong-host:11434");
-        assertThrows(OllamaBaseException.class, ollamaAPI::listModels);
+        assertThrows(OllamaException.class, ollamaAPI::listModels);
     }
 
     /**
@@ -155,7 +155,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(1)
-    void shouldReturnVersionFromVersionAPI() throws OllamaBaseException {
+    void shouldReturnVersionFromVersionAPI() throws OllamaException {
         String version = api.getVersion();
         assertNotNull(version);
     }
@@ -167,7 +167,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(1)
-    void shouldPingSuccessfully() throws OllamaBaseException {
+    void shouldPingSuccessfully() throws OllamaException {
         boolean pingResponse = api.ping();
         assertTrue(pingResponse, "Ping should return true");
     }
@@ -179,7 +179,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(2)
-    void shouldListModels() throws OllamaBaseException {
+    void shouldListModels() throws OllamaException {
         List<Model> models = api.listModels();
         assertNotNull(models, "Models should not be null");
         assertTrue(models.size() >= 0, "Models list can be empty or contain elements");
@@ -200,7 +200,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(3)
-    void shouldPullModelAndListModels() throws OllamaBaseException {
+    void shouldPullModelAndListModels() throws OllamaException {
         api.pullModel(EMBEDDING_MODEL);
         List<Model> models = api.listModels();
         assertNotNull(models, "Models should not be null");
@@ -215,7 +215,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(4)
-    void shouldGetModelDetails() throws OllamaBaseException {
+    void shouldGetModelDetails() throws OllamaException {
         api.pullModel(EMBEDDING_MODEL);
         ModelDetail modelDetails = api.getModelDetails(EMBEDDING_MODEL);
         assertNotNull(modelDetails);
@@ -247,7 +247,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(6)
-    void shouldGenerateWithStructuredOutput() throws OllamaBaseException {
+    void shouldGenerateWithStructuredOutput() throws OllamaException {
         api.pullModel(TOOLS_MODEL);
 
         String prompt =
@@ -294,7 +294,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(6)
-    void shouldGenerateWithDefaultOptions() throws OllamaBaseException {
+    void shouldGenerateWithDefaultOptions() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         boolean raw = false;
         boolean thinking = false;
@@ -323,7 +323,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(7)
-    void shouldGenerateWithDefaultOptionsStreamed() throws OllamaBaseException {
+    void shouldGenerateWithDefaultOptionsStreamed() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         boolean raw = false;
         OllamaGenerateRequest request =
@@ -355,7 +355,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(8)
-    void shouldGenerateWithCustomOptions() throws OllamaBaseException {
+    void shouldGenerateWithCustomOptions() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         OllamaChatRequestBuilder builder =
@@ -386,7 +386,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(9)
-    void shouldChatWithSystemPrompt() throws OllamaBaseException {
+    void shouldChatWithSystemPrompt() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         String expectedResponse = "Bhai";
@@ -479,7 +479,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(11)
-    void shouldChatWithExplicitTool() throws OllamaBaseException {
+    void shouldChatWithExplicitTool() throws OllamaException {
         String theToolModel = TOOLS_MODEL;
         api.pullModel(theToolModel);
         OllamaChatRequestBuilder builder =
@@ -532,7 +532,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(13)
-    void shouldChatWithExplicitToolAndUseTools() throws OllamaBaseException {
+    void shouldChatWithExplicitToolAndUseTools() throws OllamaException {
         String theToolModel = TOOLS_MODEL;
         api.pullModel(theToolModel);
         OllamaChatRequestBuilder builder =
@@ -576,7 +576,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(14)
-    void shouldChatWithToolsAndStream() throws OllamaBaseException {
+    void shouldChatWithToolsAndStream() throws OllamaException {
         String theToolModel = TOOLS_MODEL;
         api.pullModel(theToolModel);
 
@@ -631,7 +631,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(12)
-    void shouldChatWithAnnotatedToolSingleParam() throws OllamaBaseException {
+    void shouldChatWithAnnotatedToolSingleParam() throws OllamaException {
         String theToolModel = TOOLS_MODEL;
         api.pullModel(theToolModel);
         OllamaChatRequestBuilder builder =
@@ -678,7 +678,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(13)
-    void shouldChatWithAnnotatedToolMultipleParams() throws OllamaBaseException {
+    void shouldChatWithAnnotatedToolMultipleParams() throws OllamaException {
         String theToolModel = TOOLS_MODEL;
         api.pullModel(theToolModel);
         OllamaChatRequestBuilder builder =
@@ -710,7 +710,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(15)
-    void shouldChatWithStream() throws OllamaBaseException {
+    void shouldChatWithStream() throws OllamaException {
         api.deregisterTools();
         api.pullModel(GENERAL_PURPOSE_MODEL);
         OllamaChatRequestBuilder builder =
@@ -738,7 +738,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(15)
-    void shouldChatWithThinkingAndStream() throws OllamaBaseException {
+    void shouldChatWithThinkingAndStream() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL_2);
         OllamaChatRequestBuilder builder =
                 OllamaChatRequestBuilder.builder().withModel(THINKING_TOOL_MODEL_2);
@@ -767,8 +767,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(10)
-    void shouldChatWithImageFromURL()
-            throws OllamaBaseException, IOException, InterruptedException {
+    void shouldChatWithImageFromURL() throws OllamaException, IOException, InterruptedException {
         api.pullModel(VISION_MODEL);
 
         OllamaChatRequestBuilder builder =
@@ -795,7 +794,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(10)
-    void shouldChatWithImageFromFileAndHistory() throws OllamaBaseException {
+    void shouldChatWithImageFromFileAndHistory() throws OllamaException {
         api.pullModel(VISION_MODEL);
         OllamaChatRequestBuilder builder =
                 OllamaChatRequestBuilder.builder().withModel(VISION_MODEL);
@@ -857,7 +856,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(18)
-    void shouldGenerateWithImageFiles() throws OllamaBaseException {
+    void shouldGenerateWithImageFiles() throws OllamaException {
         api.pullModel(VISION_MODEL);
         try {
             OllamaGenerateRequest request =
@@ -876,7 +875,7 @@ class OllamaAPIIntegrationTest {
             assertNotNull(result);
             assertNotNull(result.getResponse());
             assertFalse(result.getResponse().isEmpty());
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             fail(e);
         } catch (IOException e) {
             throw new RuntimeException(e);
@@ -891,7 +890,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(20)
-    void shouldGenerateWithImageFilesAndResponseStreamed() throws OllamaBaseException, IOException {
+    void shouldGenerateWithImageFilesAndResponseStreamed() throws OllamaException, IOException {
         api.pullModel(VISION_MODEL);
         OllamaGenerateRequest request =
                 OllamaGenerateRequestBuilder.builder()
@@ -922,7 +921,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(20)
-    void shouldGenerateWithThinking() throws OllamaBaseException {
+    void shouldGenerateWithThinking() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL);
 
         boolean raw = false;
@@ -954,7 +953,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(20)
-    void shouldGenerateWithThinkingAndStreamHandler() throws OllamaBaseException {
+    void shouldGenerateWithThinkingAndStreamHandler() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL);
         boolean raw = false;
         OllamaGenerateRequest request =
@@ -990,7 +989,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(21)
-    void shouldGenerateWithRawMode() throws OllamaBaseException {
+    void shouldGenerateWithRawMode() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         api.unloadModel(GENERAL_PURPOSE_MODEL);
         boolean raw = true;
@@ -1020,7 +1019,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(22)
-    void shouldGenerateWithRawModeAndStreaming() throws OllamaBaseException {
+    void shouldGenerateWithRawModeAndStreaming() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         boolean raw = true;
         OllamaGenerateRequest request =
@@ -1082,7 +1081,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(24)
-    void shouldGenerateWithAllParametersEnabled() throws OllamaBaseException {
+    void shouldGenerateWithAllParametersEnabled() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL);
         // Settinng raw here instructs to keep the response raw. Even if the model generates
         // 'thinking' tokens, they will not be received as separate tokens and will be mised with
@@ -1102,8 +1101,8 @@ class OllamaAPIIntegrationTest {
                         .build();
         OllamaGenerateStreamObserver handler =
                 new OllamaGenerateStreamObserver(
-                        thinkingToken -> LOG.info("THINKING: {}", thinkingToken),
-                        responseToken -> LOG.info("RESPONSE: {}", responseToken));
+                        thinkingToken -> LOG.info("Thinking token: {}", thinkingToken),
+                        responseToken -> LOG.info("Response token: {}", responseToken));
         OllamaResult result = api.generate(request, handler);
         assertNotNull(result);
         assertNotNull(result.getResponse());
@@ -1118,7 +1117,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(25)
-    void shouldGenerateWithComplexStructuredOutput() throws OllamaBaseException {
+    void shouldGenerateWithComplexStructuredOutput() throws OllamaException {
         api.pullModel(TOOLS_MODEL);
 
         String prompt =
@@ -1178,7 +1177,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(26)
-    void shouldChatWithThinkingNoStream() throws OllamaBaseException {
+    void shouldChatWithThinkingNoStream() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL);
         OllamaChatRequestBuilder builder =
                 OllamaChatRequestBuilder.builder().withModel(THINKING_TOOL_MODEL);
@@ -1207,7 +1206,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(27)
-    void shouldChatWithCustomOptionsAndStreaming() throws OllamaBaseException {
+    void shouldChatWithCustomOptionsAndStreaming() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         OllamaChatRequestBuilder builder =
@@ -1240,7 +1239,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(28)
-    void shouldChatWithToolsThinkingAndStreaming() throws OllamaBaseException {
+    void shouldChatWithToolsThinkingAndStreaming() throws OllamaException {
         api.pullModel(THINKING_TOOL_MODEL_2);
 
         api.registerTool(EmployeeFinderToolSpec.getSpecification());
@@ -1272,7 +1271,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(31)
-    void shouldChatWithMultipleImages() throws OllamaBaseException {
+    void shouldChatWithMultipleImages() throws OllamaException {
         api.pullModel(VISION_MODEL);
 
         List<OllamaChatToolCalls> tools = Collections.emptyList();
@@ -1318,7 +1317,7 @@ class OllamaAPIIntegrationTest {
                         .build();
         OllamaGenerateStreamObserver handler = new OllamaGenerateStreamObserver(null, null);
         assertThrows(
-                OllamaBaseException.class,
+                OllamaException.class,
                 () -> {
                     api.generate(request, handler);
                 });
@@ -1331,7 +1330,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(33)
-    void shouldHandleEmptyMessage() throws OllamaBaseException {
+    void shouldHandleEmptyMessage() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         List<OllamaChatToolCalls> tools = Collections.emptyList();
@@ -1356,7 +1355,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(34)
-    void shouldGenerateWithExtremeParameters() throws OllamaBaseException {
+    void shouldGenerateWithExtremeParameters() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         OllamaGenerateRequest request =
                 OllamaGenerateRequestBuilder.builder()
@@ -1409,7 +1408,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(36)
-    void shouldChatWithKeepAlive() throws OllamaBaseException {
+    void shouldChatWithKeepAlive() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         OllamaChatRequestBuilder builder =
@@ -1434,7 +1433,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(37)
-    void shouldGenerateWithAdvancedOptions() throws OllamaBaseException {
+    void shouldGenerateWithAdvancedOptions() throws OllamaException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
         OllamaGenerateRequest request =
                 OllamaGenerateRequestBuilder.builder()
@@ -1468,7 +1467,7 @@ class OllamaAPIIntegrationTest {
      */
     @Test
     @Order(38)
-    void shouldHandleConcurrentChatRequests() throws OllamaBaseException, InterruptedException {
+    void shouldHandleConcurrentChatRequests() throws OllamaException, InterruptedException {
         api.pullModel(GENERAL_PURPOSE_MODEL);
 
         int numThreads = 3;
@@ -1570,8 +1569,13 @@ class EmployeeFinderToolSpec {
                                 .build())
                 .toolFunction(
                         arguments -> {
-                            String employeeName = arguments.get("employee-name").toString();
                             String address = null;
+                            String employeeName = null;
+                            try {
+                                employeeName = arguments.get("employee-name").toString();
+                            } catch (Exception e) {
+                                employeeName = "Mr. LLoyd Llama";
+                            }
                             try {
                                 address = arguments.get("employee-address").toString();
                             } catch (Exception e) {
diff --git a/src/test/java/io/github/ollama4j/integrationtests/WithAuth.java b/src/test/java/io/github/ollama4j/integrationtests/WithAuth.java
index 6fe314d..e4a5fee 100644
--- a/src/test/java/io/github/ollama4j/integrationtests/WithAuth.java
+++ b/src/test/java/io/github/ollama4j/integrationtests/WithAuth.java
@@ -11,7 +11,7 @@ package io.github.ollama4j.integrationtests;
 import static org.junit.jupiter.api.Assertions.*;
 
 import io.github.ollama4j.OllamaAPI;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.models.generate.OllamaGenerateRequest;
 import io.github.ollama4j.models.generate.OllamaGenerateRequestBuilder;
 import io.github.ollama4j.models.generate.OllamaGenerateStreamObserver;
@@ -181,7 +181,7 @@ public class WithAuth {
     @Test
     @Order(2)
     void testAskModelWithStructuredOutput()
-            throws OllamaBaseException, IOException, InterruptedException, URISyntaxException {
+            throws OllamaException, IOException, InterruptedException, URISyntaxException {
         api.setBearerAuth(BEARER_AUTH_TOKEN);
         String model = GENERAL_PURPOSE_MODEL;
         api.pullModel(model);
diff --git a/src/test/java/io/github/ollama4j/unittests/TestMockedAPIs.java b/src/test/java/io/github/ollama4j/unittests/TestMockedAPIs.java
index 176d662..abe6a60 100644
--- a/src/test/java/io/github/ollama4j/unittests/TestMockedAPIs.java
+++ b/src/test/java/io/github/ollama4j/unittests/TestMockedAPIs.java
@@ -13,7 +13,7 @@ import static org.junit.jupiter.api.Assertions.fail;
 import static org.mockito.Mockito.*;
 
 import io.github.ollama4j.OllamaAPI;
-import io.github.ollama4j.exceptions.OllamaBaseException;
+import io.github.ollama4j.exceptions.OllamaException;
 import io.github.ollama4j.exceptions.RoleNotFoundException;
 import io.github.ollama4j.models.chat.OllamaChatMessageRole;
 import io.github.ollama4j.models.embed.OllamaEmbedRequestModel;
@@ -42,7 +42,7 @@ class TestMockedAPIs {
             doNothing().when(ollamaAPI).pullModel(model);
             ollamaAPI.pullModel(model);
             verify(ollamaAPI, times(1)).pullModel(model);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -54,7 +54,7 @@ class TestMockedAPIs {
             when(ollamaAPI.listModels()).thenReturn(new ArrayList<>());
             ollamaAPI.listModels();
             verify(ollamaAPI, times(1)).listModels();
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -72,7 +72,7 @@ class TestMockedAPIs {
             doNothing().when(ollamaAPI).createModel(customModelRequest);
             ollamaAPI.createModel(customModelRequest);
             verify(ollamaAPI, times(1)).createModel(customModelRequest);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -85,7 +85,7 @@ class TestMockedAPIs {
             doNothing().when(ollamaAPI).deleteModel(model, true);
             ollamaAPI.deleteModel(model, true);
             verify(ollamaAPI, times(1)).deleteModel(model, true);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -112,7 +112,7 @@ class TestMockedAPIs {
             when(ollamaAPI.getModelDetails(model)).thenReturn(new ModelDetail());
             ollamaAPI.getModelDetails(model);
             verify(ollamaAPI, times(1)).getModelDetails(model);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -129,7 +129,7 @@ class TestMockedAPIs {
             when(ollamaAPI.embed(m)).thenReturn(new OllamaEmbedResponseModel());
             ollamaAPI.embed(m);
             verify(ollamaAPI, times(1)).embed(m);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -144,7 +144,7 @@ class TestMockedAPIs {
             when(ollamaAPI.embed(m)).thenReturn(new OllamaEmbedResponseModel());
             ollamaAPI.embed(m);
             verify(ollamaAPI, times(1)).embed(m);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -159,7 +159,7 @@ class TestMockedAPIs {
                     .thenReturn(new OllamaEmbedResponseModel());
             ollamaAPI.embed(new OllamaEmbedRequestModel(model, inputs));
             verify(ollamaAPI, times(1)).embed(new OllamaEmbedRequestModel(model, inputs));
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -184,7 +184,7 @@ class TestMockedAPIs {
                     .thenReturn(new OllamaResult("", "", 0, 200));
             ollamaAPI.generate(request, observer);
             verify(ollamaAPI, times(1)).generate(request, observer);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         }
     }
@@ -236,7 +236,7 @@ class TestMockedAPIs {
             when(ollamaAPI.generate(request, handler)).thenReturn(new OllamaResult("", "", 0, 200));
             ollamaAPI.generate(request, handler);
             verify(ollamaAPI, times(1)).generate(request, handler);
-        } catch (OllamaBaseException e) {
+        } catch (OllamaException e) {
             throw new RuntimeException(e);
         } catch (IOException e) {
             throw new RuntimeException(e);
@@ -244,7 +244,7 @@ class TestMockedAPIs {
     }
 
     @Test
-    void testAskAsync() throws OllamaBaseException {
+    void testAskAsync() throws OllamaException {
         OllamaAPI ollamaAPI = Mockito.mock(OllamaAPI.class);
         String model = "llama2";
         String prompt = "some prompt text";