Fix Gemini Image Input Functionality (#678)

# PR Checklist
- [ ] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [x] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [x] Did you added a type def?

# Description
This PR fixes the image input functionality for the Gemini model.

### Issue with Existing Code
The previous implementation attempted to process images in the following
way:
1. In the `OpenAIChat` type, if the `memo` field started with
`inlayImage`, the `content` field's value was copied into a variable
called `pendingImage`.
2. Later, if the `chat` role was `'user'` and `pendingImage` was not an
empty string, the code processed the image.

However, it does not seem to work as expected in the current state.

### Update
I updated the image input handling to align with the method used in
RisuAI for handling GPT’s image input. Specifically, the changes
include:

1. In `image.ts`, I explicitly specified the `gemini-exp` model.
2. If the `chat` object has a `multimodals` field and the `role` is
`user`:
- I created an array called `geminiParts` to store `GeminiPart` objects.
- The `chat.content` value is set as the `text` field of the
`GeminiPart` object in the array.
- I then iterated over `chat.multimodals` and created an object for each
`image` type, formatting it to match the Gemini structure, and added it
to the `geminiParts` array.
- After the iteration, the `geminiParts` array is assigned to the
`parts` field of `reformatedChat`.


### Notes
- I removed the previous non-functional code entirely. If this causes
any inconvenience or violates any conventions, I sincerely apologize.
- As the final name of the next-generation Gemini model is currently
unknown, I restricted the functionality to the **gemini-exp** model in
the `image.ts` file for now. This can be updated later when the official
name is confirmed.

The Gemini model is currently very widely used, so I kindly request you
to review the updated code. If you have any feedback or if the changes
are not acceptable, I completely understand if this PR is rejected.

Thank you for your time and consideration! Let me know if there's
anything I can improve or clarify.

src/ts/process/files/image.ts

@@ -84,7 +84,7 @@ export async function getInlayImage(id: string){
 
 export function supportsInlayImage(){
     const db = getDatabase()
-    return db.aiModel.startsWith('gptv') || db.aiModel === 'gemini-pro-vision' || db.aiModel.startsWith('claude-3') || db.aiModel.startsWith('gpt4_turbo') || db.aiModel.startsWith('gpt5') || db.aiModel.startsWith('gpt4o') ||
+    return db.aiModel.startsWith('gptv') || db.aiModel === 'gemini-pro-vision' || db.aiModel.startsWith('gemini-exp') || db.aiModel.startsWith('claude-3') || db.aiModel.startsWith('gpt4_turbo') || db.aiModel.startsWith('gpt5') || db.aiModel.startsWith('gpt4o') ||
         (db.aiModel === 'reverse_proxy' && (
             db.proxyRequestModel?.startsWith('gptv') || db.proxyRequestModel === 'gemini-pro-vision' || db.proxyRequestModel?.startsWith('claude-3') || db.proxyRequestModel.startsWith('gpt4_turbo') ||
             db.proxyRequestModel?.startsWith('gpt5') || db.proxyRequestModel?.startsWith('gpt4o') ||

src/ts/process/request.ts

@@ -1364,7 +1364,6 @@ async function requestGoogleCloudVertex(arg:RequestDataArgumentExtended):Promise
 
 
     let reformatedChat:GeminiChat[] = []
-    let pendingImage = ''
     let systemPrompt = ''
 
     if(formated[0].role === 'system'){
@@ -1374,10 +1373,7 @@ async function requestGoogleCloudVertex(arg:RequestDataArgumentExtended):Promise
 
     for(let i=0;i<formated.length;i++){
         const chat = formated[i]
-        if(chat.memo && chat.memo.startsWith('inlayImage')){
+  
-            pendingImage = chat.content
-            continue
-        }
         if(i === 0){
             if(chat.role === 'user' || chat.role === 'assistant'){
                 reformatedChat.push({
@@ -1403,7 +1399,34 @@ async function requestGoogleCloudVertex(arg:RequestDataArgumentExtended):Promise
                 chat.role === 'assistant' ? 'MODEL' :
                 chat.role
 
-            if(prevChat.role === qRole){
+            if (chat.multimodals && chat.multimodals.length > 0 && chat.role === "user") {
+                let geminiParts: GeminiPart[] = [];
+                
+                geminiParts.push({
+                    text: chat.content,
+                });
+                
+                for (const modal of chat.multimodals) {
+                    if (modal.type === "image") {
+                        const dataurl = modal.base64;
+                        const base64 = dataurl.split(",")[1];
+                        const mediaType = dataurl.split(";")[0].split(":")[1];
+            
+                        geminiParts.push({
+                            inlineData: {
+                                mimeType: mediaType,
+                                data: base64,
+                            }
+                        });
+                    }
+                }
+        
+                reformatedChat.push({
+                    role: "USER",
+                    parts: geminiParts,
+                });
+        
+            } else if (prevChat.role === qRole) {
                 reformatedChat[reformatedChat.length-1].parts[0].text += '\n' + chat.content
                 continue
             }
@@ -1420,36 +1443,7 @@ async function requestGoogleCloudVertex(arg:RequestDataArgumentExtended):Promise
                     })
                 }
             }
-            else if(chat.role === 'user' && pendingImage !== ''){
-                //conver image to jpeg so it can be inlined
-                const canv = document.createElement('canvas')
-                const img = new Image()
-                img.src = pendingImage  
-                await img.decode()
-                canv.width = img.width
-                canv.height = img.height
-                const ctx = canv.getContext('2d')
-                ctx.drawImage(img, 0, 0)
-                const base64 = canv.toDataURL('image/jpeg').replace(/^data:image\/jpeg;base64,/, "")
-                const mimeType = 'image/jpeg'
-                pendingImage = ''
-                canv.remove()
-                img.remove()
 
-                reformatedChat.push({
-                    role: "USER",
-                    parts: [
-                    {
-                        text: chat.content,
-                    },
-                    {
-                        inlineData: {
-                            mimeType: mimeType,
-                            data: base64
-                        }
-                    }]
-                })
-            }
             else if(chat.role === 'assistant' || chat.role === 'user'){
                 reformatedChat.push({
                     role: chat.role === 'user' ? 'USER' : 'MODEL',