1 files changed, 43 insertions, 2 deletions
diff --git a/src/client/apis/gpt/GPT.ts b/src/client/apis/gpt/GPT.ts
index a780596fa..ee8d5e9b2 100644
--- a/src/client/apis/gpt/GPT.ts
+++ b/src/client/apis/gpt/GPT.ts
@@ -13,6 +13,7 @@ enum GPTCallType {
     MERMAID = 'mermaid',
     DATA = 'data',
     DRAW = 'draw',
+    COLOR = 'color',
 }
 
 type GPTCallOpts = {
@@ -57,9 +58,15 @@ const callTypeMap: { [type: string]: GPTCallOpts } = {
     draw: {
         model: 'gpt-4o',
         maxTokens: 1024,
-        temp: 0.5,
+        temp: 0.8,
         prompt: 'Given an item, a level of complexity from 1-10, and a size in pixels, generate a detailed and colored line drawing representation of it. Make sure every element has the stroke field filled out. More complex drawings will have much more detail and strokes. The drawing should be in SVG format with no additional text or comments. For path coordinates, make sure you format with a comma between numbers, like M100,200 C150,250 etc. The only supported commands are line, ellipse, circle, rect, polygon, and path with M, Q, C, and L so only use those.',
     },
+    color: {
+        model: 'gpt-4o',
+        maxTokens: 1024,
+        temp: 0.5,
+        prompt: 'You will be coloring drawings. You will be given what the drawing is, then a list of descriptions for parts of the drawing. Based on each description, respond with the stroke and fill color that it should be. Follow the rules: 1. Avoid using black for stroke color 2. Make the stroke color 1-3 shades darker than the fill color 3. Use the same colors when possible. Format as {#abcdef #abcdef}, making sure theres a color for each description, and do not include any additional text.',
+    },
 };
 
 let lastCall = '';
@@ -187,4 +194,38 @@ const gptHandwriting = async (src: string): Promise<string> => {
     }
 };
 
-export { gptAPICall, gptImageCall, GPTCallType, gptImageLabel, gptGetEmbedding, gptHandwriting };
+const gptDrawingColor = async (image: string, coords: string[]): Promise<string> => {
+    try {
+        const response = await openai.chat.completions.create({
+            model: 'gpt-4o',
+            temperature: 0,
+            messages: [
+                {
+                    role: 'user',
+                    content: [
+                        {
+                            type: 'text',
+                            text: `Identify what the drawing in the image represents in 1-5 words. Then, given a list of a list of coordinates, where each list is the coordinates for one stroke of the drawing, determine which part of the drawing it is. Return just what the item it is, followed by ~~~ then only your descriptions in a list like [description, description, ...]. Here are the coordinates: ${coords}`,
+                        },
+                        {
+                            type: 'image_url',
+                            image_url: {
+                                url: `${image}`,
+                                detail: 'low',
+                            },
+                        },
+                    ],
+                },
+            ],
+        });
+        if (response.choices[0].message.content) {
+            return response.choices[0].message.content;
+        }
+        return 'Missing labels';
+    } catch (err) {
+        console.log(err);
+        return 'Error connecting with API';
+    }
+};
+
+export { gptAPICall, gptImageCall, GPTCallType, gptImageLabel, gptGetEmbedding, gptHandwriting, gptDrawingColor };