Add FULL support for Ollama AI models

README.md

@@ -13,6 +13,15 @@ Let's make your `@Beans` intelligent!
 :warning:
 
 ### Breaking Changes
+
+December 20, 2023 Update
+
+Refactor the Ollama client and related classes and package names
+
+ - Replace the org.springframework.ai.ollama.client.OllamaClient by org.springframework.ai.ollama.OllamaChatClient.
+ - The OllamaChatClient method signatures have changed.
+ - Rename the org.springframework.ai.autoconfigure.ollama.OllamaProperties into org.springframework.ai.autoconfigure.ollama.OllamaChatProperties and change the suffix to: `spring.ai.ollama.chat`. Some of the properties have changed as well.
+
 December 19, 2023 Update
 
 Renaming of AiClient and related classes and packagenames
@@ -22,7 +31,7 @@ Renaming of AiClient and related classes and packagenames
 * Rename AiStreamClient to StreamingChatClient
 * Rename package org.sf.ai.client to org.sf.ai.chat
 
-Rename artifact ID of 
+Rename artifact ID of
 
 * `transformers-embedding` to `spring-ai-transformers`
 
@@ -144,7 +153,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-azure-vector-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -154,7 +163,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-chroma-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -163,7 +172,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-milvus-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -173,7 +182,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -182,7 +191,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-pinecone-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -191,7 +200,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-weaviate-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>
@@ -200,7 +209,7 @@ Following vector stores are supported:
 
 ```xml
     <dependency>
-        <groupId>org.springframework.ai</groupId> 
+        <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-neo4j-store-spring-boot-starter</artifactId>
         <version>0.8.0-SNAPSHOT</version>
     </dependency>

models/spring-ai-ollama/README.md

@@ -0,0 +1,120 @@
+# 1. Ollama Chat and Embedding
+
+## 1.1 OllamaApi
+
+[OllamaApi](./src/main/java/org/springframework/ai/ollama/api/OllamaApi.java) provides is lightweight Java client for [Ollama models](https://ollama.ai/).
+
+The OllamaApi provides the Chat completion as well as Embedding endpoints.
+
+Following class diagram illustrates the OllamaApi interface and building blocks for chat completion:
+
+![OllamaApi Class Diagram](./src/test/resources/doc/Ollama%20Chat%20API.jpg)
+
+The OllamaApi can supports all [Ollama Models](https://ollama.ai/library) providing synchronous chat completion, streaming chat completion and embedding:
+
+```java
+ChatResponse chat(ChatRequest chatRequest)
+
+Flux<ChatResponse> streamingChat(ChatRequest chatRequest)
+
+EmbeddingResponse embeddings(EmbeddingRequest embeddingRequest)
+```
+
+> NOTE: OllamaApi expose also the Ollama `generation` endpoint but later if inferior compared to the Ollama `chat` endpoint.
+
+The `OllamaApiOptions` is helper class used as type-safe option builder. It provides `toMap` to convert the content into `Map<String, Object>`.
+
+Here is a simple snippet how to use the OllamaApi programmatically:
+
+```java
+var request = ChatRequest.builder("orca-mini")
+	.withStream(false)
+	.withMessages(List.of(Message.builder(Role.user)
+		.withContent("What is the capital of Bulgaria and what is the size? " + "What it the national anthem?")
+		.build()))
+	.withOptions(Options.builder().withTemperature(0.9f).build())
+	.build();
+
+ChatResponse response = ollamaApi.chat(request);
+```
+
+```java
+var request = ChatRequest.builder("orca-mini")
+	.withStream(true)
+	.withMessages(List.of(Message.builder(Role.user)
+		.withContent("What is the capital of Bulgaria and what is the size? " + "What it the national anthem?")
+		.build()))
+	.withOptions(Options.builder().withTemperature(0.9f).build().toMap())
+	.build();
+
+Flux<ChatResponse> response = ollamaApi.streamingChat(request);
+
+List<ChatResponse> responses = response.collectList().block();
+```
+
+```java
+EmbeddingRequest request = new EmbeddingRequest("orca-mini", "I like to eat apples");
+
+EmbeddingResponse response = ollamaApi.embeddings(request);
+```
+
+## 1.2 OllamaChatClient and OllamaEmbeddingClient
+
+The [OllamaChatClient](./src/main/java/org/springframework/ai/ollama/OllamaChatClient.java) implements the Spring-Ai `ChatClient` and `StreamingChatClient` interfaces.
+
+The [OllamaEmbeddingClient](./src/main/java/org/springframework/ai/ollama/OllamaEmbeddingClient.java) implements the Spring AI `EmbeddingClient` interface.
+
+Both the OllamaChatClient and the OllamaEmbeddingClient leverage the `OllamaApi`.
+
+You can configure the clients like this:
+
+```java
+@Bean
+public OllamaApi ollamaApi() {
+	return new OllamaApi(baseUrl);
+}
+
+@Bean
+public OllamaChatClient ollamaChat(OllamaApi ollamaApi) {
+	return new OllamaChatClient(ollamaApi).withModel(MODEL)
+		.withOptions(OllamaApiOptions.Options.builder().withTemperature(0.9f).build());
+}
+
+@Bean
+public OllamaEmbeddingClient ollamaEmbedding(OllamaApi ollamaApi) {
+	return new OllamaEmbeddingClient(ollamaApi).withModel("orca-mini");
+}
+
+```
+
+or you can leverage the `spring-ai-ollama-spring-boot-starter` Spring Boot starter.
+For this add the following dependency:
+
+```xml
+<dependency>
+	<artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
+	<groupId>org.springframework.ai</groupId>
+    <version>0.8.0-SNAPSHOT</version>
+</dependency>
+```
+
+Use the `OllamaChatProperties` to configure the Ollama Chat client:
+
+| Property  | Description | Default |
+| ------------- | ------------- | ------------- |
+| spring.ai.ollama.chat.model  | Model to use.  | llama2 |
+| spring.ai.ollama.chat.base-url  | The base url of the Ollama server. | http://localhost:11434 |
+| spring.ai.ollama.chat.enabled  | Allows you to disable the Ollama Chat autoconfiguration.  | true  |
+| spring.ai.ollama.chat.temperature  | Controls the randomness of the output. Values can range over [0.0,1.0]  | 0.8 |
+| spring.ai.ollama.chat.topP  | The maximum cumulative probability of tokens to consider when sampling.  | - |
+| spring.ai.ollama.chat.topK  | Max number or responses to generate. | - |
+| spring.ai.options.chat.options  (WIP) | A Map<String,Object> used to configure the Chat client. | - |
+
+and `OllamaEmbeddingProperties` to configure the Ollama Embedding client:
+
+| Property  | Description | Default |
+| ------------- | ------------- | ------------- |
+| spring.ai.ollama.embedding.model  | Model to use.  | llama2 |
+| spring.ai.ollama.embedding.base-url  | The base url of the Ollama server. | http://localhost:11434 |
+| spring.ai.ollama.embedding.enabled  | Allows you to disable the Ollama embedding autoconfiguration.  | true  |
+| spring.ai.options.embedding.options  (WIP) | A Map<String,Object> used to configure the embedding client. | - |

models/spring-ai-ollama/pom.xml

@@ -1,7 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project xmlns="http://maven.apache.org/POM/4.0.0"
-         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>org.springframework.ai</groupId>
@@ -28,6 +27,23 @@
             <version>${project.parent.version}</version>
         </dependency>
 
+        <dependency>
+            <groupId>org.springframework</groupId>
+            <artifactId>spring-webflux</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>com.fasterxml.jackson.core</groupId>
+            <artifactId>jackson-databind</artifactId>
+            <version>${jackson.version}</version>
+        </dependency>
+
+        <dependency>
+            <groupId>com.fasterxml.jackson.datatype</groupId>
+            <artifactId>jackson-datatype-jsr310</artifactId>
+            <version>${jackson.version}</version>
+        </dependency>
+
         <dependency>
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-logging</artifactId>
@@ -39,5 +55,17 @@
             <artifactId>spring-boot-starter-test</artifactId>
             <scope>test</scope>
         </dependency>
+
+        <dependency>
+            <groupId>org.springframework.boot</groupId>
+            <artifactId>spring-boot-testcontainers</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.testcontainers</groupId>
+            <artifactId>junit-jupiter</artifactId>
+            <scope>test</scope>
+        </dependency>
     </dependencies>
 </project>