From 874736eb162c490058d945a83a14b2fd7a2171c6 Mon Sep 17 00:00:00 2001
From: Markus Klenke <markusklenke86@gmail.com>
Date: Sat, 10 Feb 2024 22:58:50 +0000
Subject: [PATCH] adds documentation for chat API

---
 docs/docs/apis-ask/chat.md | 98 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 98 insertions(+)
 create mode 100644 docs/docs/apis-ask/chat.md

diff --git a/docs/docs/apis-ask/chat.md b/docs/docs/apis-ask/chat.md
new file mode 100644
index 0000000..751aba2
--- /dev/null
+++ b/docs/docs/apis-ask/chat.md
@@ -0,0 +1,98 @@
+---
+sidebar_position: 5
+---
+
+# Chat
+
+This API lets you create a conversation with LLMs. Using this API enables you to ask questions to the model including 
+information using the history of already asked questions and the respective answers.
+
+## Create a new conversation and use chat history to augment follow up questions
+
+```java
+public class Main {
+
+    public static void main(String[] args) {
+
+        String host = "http://localhost:11434/";
+
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+        OllamaChatRequestBuilder builder = OllamaChatRequestBuilder.getInstance(OllamaModelType.LLAMA2);
+
+        // create first user question
+        OllamaChatRequestModel requestModel = builder.withMessage(OllamaChatMessageRole.USER,"What is the capital of France?")
+             .build();
+
+        // start conversation with model
+        OllamaChatResult chatResult = ollamaAPI.chat(requestModel);
+
+        System.out.println("First answer: " + chatResult.getResponse());
+
+        // create next userQuestion
+        requestModel = builder.withMessages(chatResult.getChatHistory()).withMessage(OllamaChatMessageRole.USER,"And what is the second largest city?").build();
+
+        // "continue" conversation with model
+        chatResult = ollamaAPI.chat(requestModel);
+
+        System.out.println("Second answer: " + chatResult.getResponse());
+
+        System.out.println("Chat History: " + chatResult.getChatHistory());
+    }
+}
+
+```
+You will get a response similar to:
+
+> First answer: Should be Paris!
+> 
+> Second answer: Marseille.
+> 
+> Chat History:
+
+```json
+[ {
+    "role" : "user",
+    "content" : "What is the capital of France?",
+    "images" : [ ]
+  }, {
+    "role" : "assistant",
+    "content" : "Should be Paris!",
+    "images" : [ ]
+  }, {
+    "role" : "user",
+    "content" : "And what is the second largest city?",
+    "images" : [ ]
+  }, {
+    "role" : "assistant",
+    "content" : "Marseille.",
+    "images" : [ ]
+  } ]
+```
+
+## Create a new conversation with individual system prompt
+```java
+public class Main {
+
+    public static void main(String[] args) {
+
+        String host = "http://localhost:11434/";
+
+        OllamaAPI ollamaAPI = new OllamaAPI(host);
+        OllamaChatRequestBuilder builder = OllamaChatRequestBuilder.getInstance(OllamaModelType.LLAMA2);
+
+        // create request with system-prompt (overriding the model defaults) and user question
+        OllamaChatRequestModel requestModel = builder.withMessage(OllamaChatMessageRole.SYSTEM, "You are a silent bot that only says 'NI'. Do not say anything else under any circumstances!")
+             .withMessage(OllamaChatMessageRole.USER,"What is the capital of France? And what's France's connection with Mona Lisa?")
+             .build();
+
+        // start conversation with model
+        OllamaChatResult chatResult = ollamaAPI.chat(requestModel);
+
+        System.out.println(chatResult.getResponse());
+    }
+}
+
+```
+You will get a response similar to:
+
+> NI.
\ No newline at end of file