Add YouTube video caption tool and related stories/tests

packages/tools/package.json

@@ -17,6 +17,10 @@
     "./tavily": {
       "import": "./dist/tavily/index.esm.js",
       "require": "./dist/tavily/index.cjs.js"
+    },
+    "./youtube": {
+      "import": "./dist/youtube/index.esm.js",
+      "require": "./dist/youtube/index.cjs.js"
     }
   },
   "files": [
@@ -62,6 +66,7 @@
   "dependencies": {
     "@langchain/core": "0.2.16",
     "ky": "^1.7.2",
+    "youtube-captions-scraper": "^2.0.3",
     "zod": "^3.23.8"
   },
   "devDependencies": {

packages/tools/rollup.config.mjs

@@ -6,7 +6,7 @@ import json from '@rollup/plugin-json';
 import nodePolyfills from 'rollup-plugin-node-polyfills'; // Correct plugin name
 
 // Array of tool folder names
-const toolFolders = ['firecrawl', 'tavily']; // Add more folder names as needed
+const toolFolders = ['firecrawl', 'tavily','youtube-video-caption']; // Add more folder names as needed
 
 const toolConfigs = toolFolders.map((tool) => {
   const inputPath = `src/${tool}/index.js`; // Adjusted for plain JavaScript

packages/tools/src/index.js

@@ -1,2 +1,3 @@
 export * from './firecrawl/index.js';
 export * from './tavily/index.js';
+export * from './youtube-video-caption/index.js';

packages/tools/src/youtube-video-caption/index.js

@@ -0,0 +1,83 @@
+import { Tool } from '@langchain/core/tools';
+import { z } from 'zod';
+import ky from 'ky';
+import { HTTPError } from 'ky';
+import { getSubtitles } from 'youtube-captions-scraper';
+
+export class YouTubeVideoCaption extends Tool {
+  constructor(fields) {
+    super(fields);
+    this.token = fields.token;
+    this.name = 'youtube_video_caption';
+    this.description = 'Tools to extract video caption from youtube';
+    this.httpClient = ky;
+
+    // Define the input schema using Zod
+    this.schema = z.object({
+      videoId: z
+        .string()
+        .describe('The ID of the YouTube video to extract captions from.'),
+    });
+  }
+
+  async _call(input) {
+    try {
+      const headers = {
+        Authorization: `Bearer ${this.token}`,
+      };
+      // Make an API request to the YouTube Data API
+
+      const jsonData = await this.httpClient
+        .get(
+          `https://www.googleapis.com/youtube/v3/captions?videoId=${input.videoId}&part=id,snippet`,
+          { headers }
+        )
+        .json();
+      // Extract and validate the results from the response
+      const captions = jsonData?.items[0]?.snippet;
+      if (!captions) {
+        return 'No captions found';
+      }
+      const captionContent = await downloadAutoGeneratedCaptions(
+        input.videoId,
+        captions.language
+      );
+
+      return captionContent;
+    } catch (error) {
+      if (error instanceof HTTPError) {
+        const statusCode = error.response.status;
+        let errorType = 'Unknown';
+        if (statusCode >= 400 && statusCode < 500) {
+          errorType = 'Client Error';
+        } else if (statusCode >= 500) {
+          errorType = 'Server Error';
+        }
+        return `API request failed: ${errorType} (${statusCode})`;
+      } else {
+        return `An unexpected error occurred: ${error.message}`;
+      }
+    }
+  }
+}
+
+const downloadAutoGeneratedCaptions = async (videoId, lang = 'en') => {
+  try {
+    const captions = await getSubtitles({
+      videoID: videoId, // YouTube video ID
+      lang, // Language code for captions, change as neededd
+    });
+
+    // Process and display the captions
+    let captionContent = `Video Id: ${videoId}\n\n`;
+
+    for (let index = 0; index < captions.length; index++) {
+      const caption = captions[index];
+      captionContent += `[${caption.start}]: ${caption.text}\n`;
+    }
+
+    return captionContent;
+  } catch (error) {
+    console.error('Error downloading captions:', error);
+  }
+};

packages/tools/src/youtube-video-caption/youtubeVideoCaption.stories.jsx

@@ -0,0 +1,67 @@
+import { ToolPreviewer } from '../_utils/ToolPreviewer.jsx';
+import { YouTubeVideoCaption } from './index.js';
+import { Agent, Task, Team } from '../../../../src/index';
+import React from 'react';
+import { AgentWithToolPreviewer } from '../_utils/AgentWithToolPreviewer.jsx';
+
+// More on how to set up stories at: https://storybook.js.org/docs/writing-stories#default-export
+export default {
+  title: 'Tools/YouTube',
+  component: ToolPreviewer,
+  parameters: {
+    layout: 'centered',
+  },
+  tags: ['autodocs'],
+};
+
+const youtubeTool = new YouTubeVideoCaption({
+  token: import.meta.env.VITE_YOUTUBE_LONG_LIVE_TOKEN,
+});
+
+// Create an agent with the YouTube tool
+const captionExtractor = new Agent({
+  name: 'Caption Extractor',
+  role: 'YouTube Caption Analyzer',
+  goal: 'Extract and analyze captions from YouTube videos',
+  tools: [youtubeTool],
+  maxIterations: 5,
+});
+
+// Create a caption extraction task
+const captionExtractionTask = new Task({
+  description:
+    'Extract captions for video ID: {videoId} and provide a structured summary',
+  agent: captionExtractor,
+  expectedOutput: 'A well-formatted analysis of the video captions',
+});
+
+// Create the team
+const team = new Team({
+  name: 'Caption Extraction Unit',
+  description:
+    'Specialized team for extracting and analyzing YouTube video captions',
+  agents: [captionExtractor],
+  tasks: [captionExtractionTask],
+  inputs: {
+    videoId: 'NFpqFEl-URY', // Example video ID
+  },
+  env: {
+    OPENAI_API_KEY: import.meta.env.VITE_OPENAI_API_KEY,
+  },
+});
+
+export const Default = {
+  args: {
+    toolInstance: youtubeTool,
+    callParams: {
+      videoId: 'NFpqFEl-URY',
+    },
+  },
+};
+
+export const withAgent = {
+  render: (args) => <AgentWithToolPreviewer {...args} />,
+  args: {
+    team: team,
+  },
+};