feat(core): ai images

packages/frontend/core/src/components/blocksuite/block-suite-editor/ai/provider.ts

@@ -1,7 +1,7 @@
 import { assertExists } from '@blocksuite/global/utils';
 import { AIProvider } from '@blocksuite/presets';
 
-import { textToTextStream } from './request';
+import { imageToTextStream, textToTextStream } from './request';
 
 export function setupAIProvider() {
   AIProvider.provideAction('chat', options => {
@@ -118,4 +118,41 @@ export function setupAIProvider() {
       prompt,
     });
   });
+
+  AIProvider.provideAction('makeItReal', options => {
+    assertExists(options.stream);
+    const prompt = `You are an expert web developer who specializes in building working website prototypes from low-fidelity wireframes.
+Your job is to accept low-fidelity wireframes, then create a working prototype using HTML, CSS, and JavaScript, and finally send back the results.
+The results should be a single HTML file.
+Use tailwind to style the website.
+Put any additional CSS styles in a style tag and any JavaScript in a script tag.
+Use unpkg or skypack to import any required dependencies.
+Use Google fonts to pull in any open source fonts you require.
+If you have any images, load them from Unsplash or use solid colored rectangles.
+
+The wireframes may include flow charts, diagrams, labels, arrows, sticky notes, and other features that should inform your work.
+If there are screenshots or images, use them to inform the colors, fonts, and layout of your website.
+Use your best judgement to determine whether what you see should be part of the user interface, or else is just an annotation.
+
+Use what you know about applications and user experience to fill in any implicit business logic in the wireframes. Flesh it out, make it real!
+
+The user may also provide you with the html of a previous design that they want you to iterate from.
+In the wireframe, the previous design's html will appear as a white rectangle.
+Use their notes, together with the previous design, to inform your next result.
+
+Sometimes it's hard for you to read the writing in the wireframes.
+For this reason, all text from the wireframes will be provided to you as a list of strings, separated by newlines.
+Use the provided list of text from the wireframes as a reference if any text is hard to read.
+
+You love your designers and want them to be happy. Incorporating their feedback and notes and producing working websites makes them happy.
+
+When sent new wireframes, respond ONLY with the contents of the html file.`;
+    return imageToTextStream({
+      docId: options.docId,
+      workspaceId: options.workspaceId,
+      params: options.params,
+      attachments: options.atachments,
+      prompt,
+    });
+  });
 }

packages/frontend/core/src/components/blocksuite/block-suite-editor/ai/request.ts

@@ -25,3 +25,57 @@ export function textToTextStream({
     },
   };
 }
+
+// Image to text(html)
+export function imageToTextStream({
+  docId,
+  workspaceId,
+  ...options
+}: {
+  docId: string;
+  workspaceId: string;
+  prompt: string;
+  params?: string;
+  attachments?: string[];
+}) {
+  const client = new CopilotClient(getBaseUrl());
+  return {
+    [Symbol.asyncIterator]: async function* () {
+      const session = await client.createSession({
+        workspaceId,
+        docId,
+        promptName: 'Summary', // placeholder
+      });
+      const message = await client.createMessage(options);
+      const eventSource = client.textStream(message, session);
+      yield* toTextStream(eventSource, { timeout: TIMEOUT });
+    },
+  };
+}
+
+// Image to images
+export function imageToImagesStream({
+  docId,
+  workspaceId,
+  ...options
+}: {
+  docId: string;
+  workspaceId: string;
+  prompt: string;
+  params?: string;
+  attachments?: string[];
+}) {
+  const client = new CopilotClient(getBaseUrl());
+  return {
+    [Symbol.asyncIterator]: async function* () {
+      const session = await client.createSession({
+        workspaceId,
+        docId,
+        promptName: 'Summary', // placeholder
+      });
+      const message = await client.createMessage(options);
+      const eventSource = client.imagesStream(message, session);
+      yield* toTextStream(eventSource, { timeout: TIMEOUT });
+    },
+  };
+}