Use Mistral as default model with Ollama

01-chat-models/chat-models-ollama/README.md

@@ -31,10 +31,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model. That's what we'll use in this example.
+Then, use Ollama to run the _mistral_ large language model. That's what we'll use in this example.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -45,15 +45,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to generate text based on a default prompt.
+You can now call the application that will use Ollama and _mistral_ to generate text based on a default prompt.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

01-chat-models/chat-models-ollama/src/main/java/com/thomasvitale/ai/spring/ChatController.java

@@ -33,7 +33,7 @@ String chatWithGenericOptions(@RequestParam(defaultValue = "What did Gandalf say
     @GetMapping("/chat/ollama-options")
     String chatWithOllamaOptions(@RequestParam(defaultValue = "What did Gandalf say to the Balrog?") String message) {
         return chatModel.call(new Prompt(message, OllamaOptions.create()
-                        .withModel("llama3")
+                        .withModel("mistral")
                         .withRepeatPenalty(1.5f)))
                 .getResult().getOutput().getContent();
     }

01-chat-models/chat-models-ollama/src/main/resources/application.yml

@@ -3,5 +3,5 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
           temperature: 0.7

01-chat-models/chat-models-ollama/src/test/java/com/thomasvitale/ai/spring/TestChatModelsOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestChatModelsOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

02-prompts/prompts-basics-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to generate an answer to your questions.
+You can now call the application that will use Ollama and _mistral_ to generate an answer to your questions.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

02-prompts/prompts-basics-ollama/src/main/resources/application.yml

@@ -3,5 +3,5 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
           temperature: 0.7

02-prompts/prompts-basics-ollama/src/test/java/com/thomasvitale/ai/spring/TestPromptBasicsOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestPromptBasicsOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

02-prompts/prompts-messages-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to generate an answer to your questions.
+You can now call the application that will use Ollama and _mistral_ to generate an answer to your questions.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

02-prompts/prompts-messages-ollama/src/main/resources/application.yml

@@ -3,5 +3,5 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
           temperature: 0.7

02-prompts/prompts-messages-ollama/src/test/java/com/thomasvitale/ai/spring/TestPromptsMessagesOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestPromptsMessagesOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

02-prompts/prompts-templates-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to generate an answer to your questions.
+You can now call the application that will use Ollama and _mistral_ to generate an answer to your questions.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

02-prompts/prompts-templates-ollama/src/main/resources/application.yml

@@ -3,5 +3,5 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
           temperature: 0.7

02-prompts/prompts-templates-ollama/src/test/java/com/thomasvitale/ai/spring/TestPromptsTemplatesOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestPromptsTemplatesOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

03-output-converters/output-converters-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to generate an answer to your questions.
+You can now call the application that will use Ollama and _mistral_ to generate an answer to your questions.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

03-output-converters/output-converters-ollama/src/main/resources/application.yml

@@ -3,5 +3,5 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
           temperature: 0.7

03-output-converters/output-converters-ollama/src/test/java/com/thomasvitale/ai/spring/TestOutputParsersOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestOutputParsersOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

04-embedding-models/embedding-models-ollama/README.md

@@ -32,10 +32,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -46,15 +46,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and llama3 to generate a vector representation (embeddings) of a default text.
+You can now call the application that will use Ollama and mistral to generate a vector representation (embeddings) of a default text.
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

04-embedding-models/embedding-models-ollama/src/main/java/com/thomasvitale/ai/spring/EmbeddingController.java

@@ -27,7 +27,7 @@ String embed(@RequestParam(defaultValue = "And Gandalf yelled: 'You shall not pa
     @GetMapping("/embed/ollama-options")
     String embedWithOllamaOptions(@RequestParam(defaultValue = "And Gandalf yelled: 'You shall not pass!'") String message) {
         var embeddings = embeddingModel.call(new EmbeddingRequest(List.of(message), OllamaOptions.create()
-                        .withModel("llama3")))
+                        .withModel("mistral")))
                 .getResult().getOutput();
         return "Size of the embedding vector: " + embeddings.size();
     }

04-embedding-models/embedding-models-ollama/src/main/resources/application.yml

@@ -3,4 +3,4 @@ spring:
     ollama:
       embedding:
         options:
-          model: llama3
+          model: mistral

04-embedding-models/embedding-models-ollama/src/test/java/com/thomasvitale/ai/spring/TestEmbeddingModelsOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestEmbeddingModelsOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

05-etl-pipeline/document-readers-json-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to load JSON documents as embeddings and generate an answer to your questions based on those documents (RAG pattern).
+You can now call the application that will use Ollama and _mistral_ to load JSON documents as embeddings and generate an answer to your questions based on those documents (RAG pattern).
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

05-etl-pipeline/document-readers-json-ollama/src/main/resources/application.yml

@@ -3,7 +3,7 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
       embedding:
         options:
-          model: llama3
+          model: mistral

05-etl-pipeline/document-readers-json-ollama/src/test/java/com/thomasvitale/ai/spring/TestDocumentReadersJsonOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestDocumentReadersJsonOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }
 

05-etl-pipeline/document-readers-pdf-ollama/README.md

@@ -9,10 +9,10 @@ The application relies on Ollama for providing LLMs. You can either run Ollama l
 ### Ollama as a native application
 
 First, make sure you have [Ollama](https://ollama.ai) installed on your laptop.
-Then, use Ollama to run the _llama3_ large language model.
+Then, use Ollama to run the _mistral_ large language model.
 
 ```shell
-ollama run llama3
+ollama run mistral
 ```
 
 Finally, run the Spring Boot application.
@@ -23,15 +23,15 @@ Finally, run the Spring Boot application.
 
 ### Ollama as a dev service with Testcontainers
 
-The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _llama3_ model at startup time.
+The application relies on the native Testcontainers support in Spring Boot to spin up an Ollama service with a _mistral_ model at startup time.
 
 ```shell
 ./gradlew bootTestRun
 ```
 
 ## Calling the application
 
-You can now call the application that will use Ollama and _llama3_ to load PDF documents as embeddings and generate an answer to your questions based on those documents (RAG pattern).
+You can now call the application that will use Ollama and _mistral_ to load PDF documents as embeddings and generate an answer to your questions based on those documents (RAG pattern).
 This example uses [httpie](https://httpie.io) to send HTTP requests.
 
 ```shell

05-etl-pipeline/document-readers-pdf-ollama/src/main/resources/application.yml

@@ -3,7 +3,7 @@ spring:
     ollama:
       chat:
         options:
-          model: llama3
+          model: mistral
       embedding:
         options:
-          model: llama3
+          model: mistral

05-etl-pipeline/document-readers-pdf-ollama/src/test/java/com/thomasvitale/ai/spring/TestDocumentReadersPdfOllamaApplication.java

@@ -15,7 +15,7 @@ public class TestDocumentReadersPdfOllamaApplication {
     @RestartScope
     @ServiceConnection
     OllamaContainer ollama() {
-        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-mistral")
                 .asCompatibleSubstituteFor("ollama/ollama"));
     }