feat: Integrate gpt-4o-mini into OdinRunes for image context support

- Added support for gpt-4o-mini in the latest version of OdinRunes. - Enabled the functionality to supply images within the context for enhanced capabilities.
leonid20000 · Jul 20, 2024 · 7f1a8af · 7f1a8af
1 parent d6d2df7
commit 7f1a8af
Show file tree

Hide file tree

Showing 6 changed files with 81 additions and 192 deletions.
diff --git a/pom.xml b/pom.xml
@@ -7,7 +7,7 @@
 
     <groupId>com.odinware</groupId>
     <artifactId>OdinRunes</artifactId>
-    <version>1.3-SNAPSHOT</version>
+    <version>1.5-SNAPSHOT</version>
 
 
     <dependencies>
@@ -20,7 +20,7 @@
         <dependency>
             <groupId>net.sourceforge.tess4j</groupId>
             <artifactId>tess4j</artifactId>
-            <version>5.10.0</version> <!-- Replace with the latest version -->
+            <version>5.12.0</version> <!-- Replace with the latest version -->
         </dependency>
         <dependency>
             <groupId>org.slf4j</groupId>
@@ -30,12 +30,12 @@
         <dependency>
             <groupId>ch.qos.logback</groupId>
             <artifactId>logback-classic</artifactId>
-            <version>1.4.14</version> <!-- Use the latest version -->
+            <version>1.5.6</version> <!-- Use the latest version -->
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-text</artifactId>
-            <version>1.11.0</version> <!-- Replace with the latest version -->
+            <version>1.12.0</version> <!-- Replace with the latest version -->
         </dependency>
         <dependency>
             <groupId>org.apache.httpcomponents</groupId>
@@ -45,30 +45,31 @@
         <dependency>
             <groupId>org.json</groupId>
             <artifactId>json</artifactId>
-            <version>20231013</version> <!-- Use the latest version available -->
+            <version>20240303</version> <!-- Use the latest version available -->
         </dependency>
         <dependency>
             <groupId>com.squareup.okhttp3</groupId>
             <artifactId>okhttp</artifactId>
-            <version>5.0.0-alpha.12</version> <!-- Use the latest version available -->
+            <version>5.0.0-alpha.14</version> <!-- Use the latest version available -->
         </dependency>
 
         <!-- Jackson for JSON parsing -->
         <dependency>
             <groupId>com.fasterxml.jackson.core</groupId>
             <artifactId>jackson-core</artifactId>
-            <version>2.16.1</version> <!-- Use the latest version available -->
+            <version>2.17.2</version> <!-- Use the latest version available -->
         </dependency>
 
         <dependency>
             <groupId>com.fasterxml.jackson.core</groupId>
             <artifactId>jackson-databind</artifactId>
-            <version>2.16.1</version> <!-- Replace with the latest version -->
+            <version>2.17.2</version> <!-- Replace with the latest version -->
         </dependency>
 
 
 
 
+
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
@@ -84,32 +85,32 @@
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter</artifactId>
-            <version>5.10.1</version>
+            <version>5.11.0-M2</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter</artifactId>
-            <version>5.10.1</version>
+            <version>5.11.0-M2</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter</artifactId>
-            <version>5.10.1</version>
+            <version>5.11.0-M2</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.mockito</groupId>
             <artifactId>mockito-core</artifactId>
-            <version>5.8.0</version> <!-- Use the latest version available -->
+            <version>5.12.0</version> <!-- Use the latest version available -->
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter-api</artifactId>
-            <version>5.10.1</version>
+            <version>5.11.0-M2</version>
             <scope>test</scope>
         </dependency>
 

diff --git a/pom.xml.versionsBackup b/pom.xml.versionsBackup
diff --git a/src/main/java/org/odinware/odinrunes/Context.java b/src/main/java/org/odinware/odinrunes/Context.java
@@ -3,7 +3,11 @@
 import java.util.ArrayList;
 import java.util.List;
 import java.io.Serializable;
-
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.nio.file.Files;
+import java.util.Base64;
 /**
  * The Context class represents the context in which the GPT request is made.
  * It contains captured data and user options that will be used to construct the request.
@@ -79,12 +83,28 @@ public CapturedData(String capturedText, String captureMethod) {
             this.captureMethod = captureMethod;
         }
 
+        public String getRawCapturedText(){
+            return capturedText;
+        }
         public String getCapturedText() {
             if(getCaptureMethod().equals("File (Live)")){
                String fileContent=TextHelper.readIntoString(capturedText);
                if(fileContent == null){
                    return "ERROR READING FROM FILE";
                } else return fileContent;
+            } else if(getCaptureMethod().equals("Image File (Live)")){
+                try{
+                    File file = new File(capturedText);
+                    // Read the file into a byte array
+                    byte[] fileContent = Files.readAllBytes(file.toPath());
+
+                    // Encode the byte array into a Base64 string
+                    String encodedString = Base64.getEncoder().encodeToString(fileContent);
+                    return encodedString;
+                } catch (IOException e) {
+                        e.printStackTrace();
+                        return "";
+                    }
             } else return capturedText;
 
         }

diff --git a/src/main/java/org/odinware/odinrunes/GptOpsHelper.java b/src/main/java/org/odinware/odinrunes/GptOpsHelper.java
@@ -54,6 +54,11 @@ public static void streamResponse(TextHelper odinSays, Context context, JSONObje
 
         // Switch case based on gptProvider value
         switch (gptProvider) {
+            case "OpenAI (gpt-4o-mini)":
+                // Code to handle OpenAI (gpt-4o-mini) provider
+                customWellsOfWisdom = new OpenAIWellsOfWisdom();
+                logger.info("Using OpenAI (gpt-4o-mini)");
+                break;
             case "OpenAI (gpt-3.5-turbo)":
                 // Code to handle OpenAI (gpt-3.5-turbo) provider
                 customWellsOfWisdom = new OpenAIWellsOfWisdom();

diff --git a/src/main/java/org/odinware/odinrunes/Main.java b/src/main/java/org/odinware/odinrunes/Main.java
@@ -19,7 +19,7 @@ public class Main {
     private static final Logger logger = Logger.getLogger(GraphicalInteractionsHelper.class.getName());
 
     private static Context context = new Context();
-    private static JSONObject gptSettingsJsonObject = new JSONObject("{\"temperature\":0.8,\"gptProvider\":\"OpenAI (gpt-3.5-turbo)\"}");
+    private static JSONObject gptSettingsJsonObject = new JSONObject("{\"temperature\":0.8,\"gptProvider\":\"OpenAI (gpt-4o-mini)\"}");
     private static JFrame frame;
     private static JPanel mainPanel;
     private static JPanel settingsPanel;
@@ -114,7 +114,7 @@ private static void createAndShowGUI() {
         mainComponentsPanel.setLayout(new FlowLayout());
 
         // Create the first dropdown menu
-        String[] options = {"Clipboard", "Regionshot (OCR)", "Scrollshot (OCR)", "File (Live)","Photo (Coming Soon)"};
+        String[] options = {"Clipboard", "Regionshot (OCR)", "Scrollshot (OCR)", "Text File (Live)","Image File (Live)"};
         final JComboBox<String> firstDropdown = new JComboBox<>(options);
         firstDropdown.setBackground(new Color(189, 219, 225)); // RGB values for a blue-grey shade
 
@@ -156,7 +156,7 @@ public void run() {
                                 logger.info(selectedArgument);
                                 toggleSettingsPanelVisibility();
                                 if(!settingsVisible) toggleSettingsPanelVisibility();
-                            } else if (selectedFunction.equals("File (Live)")) {
+                            } else if (selectedFunction.equals("Text File (Live)")) {
                                 JFileChooser fileChooser = new JFileChooser();
                                 int returnValue = fileChooser.showOpenDialog(null);
                                 if (returnValue == JFileChooser.APPROVE_OPTION) {
@@ -169,6 +169,19 @@ public void run() {
                                         context.addCapturedData(tempFile.getAbsolutePath(), "File (Live)");
                                     }
                                 }
+                            } else if (selectedFunction.equals("Image File (Live)")) {
+                                JFileChooser fileChooser = new JFileChooser();
+                                int returnValue = fileChooser.showOpenDialog(null);
+                                if (returnValue == JFileChooser.APPROVE_OPTION) {
+                                    File tempFile = fileChooser.getSelectedFile();
+                                    if(!tempFile.exists()) {
+                                        // Do something with the selected file, e.g., display its path
+                                        JOptionPane.showMessageDialog(frame, "ERROR: Something is wrong with the selected file: " + tempFile.getAbsolutePath());
+                                    }else{
+                                        JOptionPane.showMessageDialog(frame, "OK: I will pass the latest content of the selected image source as part of the context to your specified GPT provider. (Only multimodal GPT providers) \nThis means that any changes to the file will also be automatically reflected in the context. \nThe selected file: " + tempFile.getAbsolutePath());
+                                        context.addCapturedData(tempFile.getAbsolutePath(), "Image File (Live)");
+                                    }
+                                }
                             }
 
                             // Add logic to handle the result or display a message.
@@ -305,7 +318,7 @@ private static void toggleSettingsPanelVisibility() {
 
 
             // Create an array of options for the dropdown
-            String[] options = {"OpenAI (gpt-3.5-turbo)", "Google's VertexAI (chat-bison)", "Google's VertexAI (gemini-pro)", "Ollama"};
+            String[] options = {"OpenAI (gpt-4o-mini)", "OpenAI (gpt-3.5-turbo)", "Google's VertexAI (chat-bison)", "Google's VertexAI (gemini-pro)", "Ollama"};
 
             // Create a JComboBox with the options array
             final JComboBox<String> dropdown = new JComboBox<>(options);