diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index eb7a2af..886efab 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -18,6 +18,7 @@ export class WebCrawler {
   private limit: number;
   private robotsTxtUrl: string;
   private robots: any;
+  private generateImgAltText: boolean;
 
   constructor({
     initialUrl,
@@ -25,12 +26,14 @@ export class WebCrawler {
     excludes,
     maxCrawledLinks,
     limit = 10000,
+    generateImgAltText = false,
   }: {
     initialUrl: string;
     includes?: string[];
     excludes?: string[];
     maxCrawledLinks?: number;
     limit?: number;
+    generateImgAltText?: boolean;
   }) {
     this.initialUrl = initialUrl;
     this.baseUrl = new URL(initialUrl).origin;
@@ -41,8 +44,10 @@ export class WebCrawler {
     this.robots = robotsParser(this.robotsTxtUrl, "");
     // Deprecated, use limit instead
     this.maxCrawledLinks = maxCrawledLinks ?? limit;
+    this.generateImgAltText = generateImgAltText ?? false;
   }
 
+
   private filterLinks(sitemapLinks: string[], limit: number): string[] {
     return sitemapLinks
       .filter((link) => {
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 6810ea2..b54d9e6 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -4,6 +4,7 @@ import { scrapSingleUrl } from "./single_url";
 import { SitemapEntry, fetchSitemapData, getLinksFromSitemap } from "./sitemap";
 import { WebCrawler } from "./crawler";
 import { getValue, setValue } from "../../services/redis";
+import { getImageDescription } from "./utils/gptVision";
 
 export type WebScraperOptions = {
   urls: string[];
@@ -14,7 +15,7 @@ export type WebScraperOptions = {
     excludes?: string[];
     maxCrawledLinks?: number;
     limit?: number;
-
+    generateImgAltText?: boolean;
   };
   concurrentRequests?: number;
 };
@@ -27,6 +28,7 @@ export class WebScraperDataProvider {
   private returnOnlyUrls: boolean;
   private limit: number = 10000;
   private concurrentRequests: number = 20;
+  private generateImgAltText: boolean = false;
 
   authorize(): void {
     throw new Error("Method not implemented.");
@@ -80,6 +82,7 @@ export class WebScraperDataProvider {
           excludes: this.excludes,
           maxCrawledLinks: this.maxCrawledLinks,
           limit: this.limit,
+          generateImgAltText: this.generateImgAltText,
         });
         const links = await crawler.start(inProgress, 5, this.limit);
         if (this.returnOnlyUrls) {
@@ -93,6 +96,9 @@ export class WebScraperDataProvider {
         let documents = await this.convertUrlsToDocuments(links, inProgress);
         documents = await this.getSitemapData(this.urls[0], documents);
         console.log("documents", documents)
+        if (this.generateImgAltText) {
+          documents = await this.generatesImgAltText(documents);
+        }
 
         // CACHING DOCUMENTS
         // - parent document
@@ -116,7 +122,9 @@ export class WebScraperDataProvider {
 
       if (this.mode === "single_urls") {
         let documents = await this.convertUrlsToDocuments(this.urls, inProgress);
-        
+        if (this.generateImgAltText) {
+          documents = await this.generatesImgAltText(documents);
+        }
         const baseUrl = new URL(this.urls[0]).origin;
         documents = await this.getSitemapData(baseUrl, documents);
         
@@ -130,6 +138,9 @@ export class WebScraperDataProvider {
         let documents = await this.convertUrlsToDocuments(links.slice(0, this.limit), inProgress);
 
         documents = await this.getSitemapData(this.urls[0], documents);
+        if (this.generateImgAltText) {
+          documents = await this.generatesImgAltText(documents);
+        }
         
         await this.setCachedDocuments(documents);
         documents = this.removeChildLinks(documents);
@@ -244,6 +255,7 @@ export class WebScraperDataProvider {
     this.maxCrawledLinks = options.crawlerOptions?.maxCrawledLinks ?? 1000;
     this.returnOnlyUrls = options.crawlerOptions?.returnOnlyUrls ?? false;
     this.limit = options.crawlerOptions?.limit ?? 10000;
+    this.generateImgAltText = options.crawlerOptions?.generateImgAltText ?? false;
 
 
     //! @nicolas, for some reason this was being injected and breakign everything. Don't have time to find source of the issue so adding this check
@@ -283,5 +295,31 @@ export class WebScraperDataProvider {
     }
     return documents;
   }
+  generatesImgAltText = async (documents: Document[]): Promise<Document[]> => {
+    await Promise.all(documents.map(async (document) => {
+      const baseUrl = new URL(document.metadata.sourceURL).origin;
+      const images = document.content.match(/!\[.*?\]\(((?:[^()]+|\((?:[^()]+|\([^()]*\))*\))*)\)/g) || [];
+
+      await Promise.all(images.map(async (image) => {
+        let imageUrl = image.match(/\(([^)]+)\)/)[1];
+        let altText = image.match(/\[(.*?)\]/)[1];
+        let newImageUrl = '';
+
+        if (!altText && !imageUrl.startsWith("data:image") && /\.(png|jpeg|gif|webp)$/.test(imageUrl)) {
+          newImageUrl = baseUrl + imageUrl;
+          const imageIndex = document.content.indexOf(image);
+          const contentLength = document.content.length;
+          let backText = document.content.substring(imageIndex + image.length, Math.min(imageIndex + image.length + 1000, contentLength));
+          let frontTextStartIndex = Math.max(imageIndex - 1000, 0);
+          let frontText = document.content.substring(frontTextStartIndex, imageIndex);
+          altText = await getImageDescription(newImageUrl, backText, frontText);
+        }
+
+        document.content = document.content.replace(image, `![${altText}](${newImageUrl})`);
+      }));
+    }));
+
+    return documents;
+  }
 }
 
diff --git a/apps/api/src/scraper/WebScraper/utils/gptVision.ts b/apps/api/src/scraper/WebScraper/utils/gptVision.ts
new file mode 100644
index 0000000..7458a56
--- /dev/null
+++ b/apps/api/src/scraper/WebScraper/utils/gptVision.ts
@@ -0,0 +1,41 @@
+export async function getImageDescription(
+  imageUrl: string,
+  backText: string,
+  frontText: string
+): Promise<string> {
+  const { OpenAI } = require("openai");
+  const openai = new OpenAI();
+
+  try {
+    const response = await openai.chat.completions.create({
+      model: "gpt-4-turbo",
+      messages: [
+        {
+          role: "user",
+          content: [
+            {
+              type: "text",
+              text:
+                "What's in the image? You need to answer with the content for the alt tag of the image. To help you with the context, the image is in the following text: " +
+                backText +
+                " and the following text: " +
+                frontText +
+                ". Be super concise.",
+            },
+            {
+              type: "image_url",
+              image_url: {
+                url: imageUrl,
+              },
+            },
+          ],
+        },
+      ],
+    });
+
+    return response.choices[0].message.content;
+  } catch (error) {
+    console.error("Error generating image alt text:", error?.message);
+    return "";
+  }
+}