-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- feature: added youtube transcript tool
- Loading branch information
1 parent
6ea96d2
commit 4d7446a
Showing
12 changed files
with
337 additions
and
107 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| /* eslint-disable */ | ||
| export default { | ||
| displayName: '@shinkai_protocol/shinkai-tool-youtube-transcript', | ||
| preset: '../../jest.preset.js', | ||
| coverageDirectory: '../../coverage/apps/shinkai-tool-youtube-transcript', | ||
| }; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| { | ||
| "name": "@shinkai_protocol/shinkai-tool-youtube-transcript", | ||
| "type": "commonjs" | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| { | ||
| "name": "@shinkai_protocol/shinkai-tool-youtube-transcript", | ||
| "$schema": "../../node_modules/nx/schemas/project-schema.json", | ||
| "sourceRoot": "apps/shinkai-tool-youtube-transcript/src", | ||
| "projectType": "library", | ||
| "tags": ["tool"], | ||
| "targets": { | ||
| "build": { | ||
| "executor": "nx:run-commands", | ||
| "defaultConfiguration": "production", | ||
| "options": { | ||
| "command": "npx ts-node scripts/tool-bundler.ts --entry ./apps/shinkai-tool-youtube-transcript/src/index.ts --outputFolder ./dist/apps/shinkai-tool-youtube-transcript" | ||
| }, | ||
| "configurations": { | ||
| "development": {}, | ||
| "production": {} | ||
| } | ||
| }, | ||
| "lint": { | ||
| "executor": "@nx/linter:eslint", | ||
| "outputs": ["{options.outputFile}"], | ||
| "options": { | ||
| "lintFilePatterns": [ | ||
| "apps/shinkai-tool-youtube-transcript/**/*.ts", | ||
| "apps/shinkai-tool-youtube-transcript/package.json" | ||
| ] | ||
| } | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,20 @@ | ||
| import { Tool } from '../src/index'; | ||
|
|
||
| test('exists definition', async () => { | ||
| const tool = new Tool({}); | ||
| const definition = tool.getDefinition(); | ||
| expect(definition).toBeInstanceOf(Object); | ||
| }); | ||
|
|
||
| test('transcript video', async () => { | ||
| const tool = new Tool({}); | ||
| const result = await tool.run({ | ||
| // Video about Shinkai Sheets | ||
| url: 'https://youtu.be/RxxuM4wbVQc', | ||
| ollamaModel: 'llama3.1:8b-instruct-q4_1' | ||
| }); | ||
| expect(result.data.transcript).toBeInstanceOf(Array); | ||
| expect(result.data.transcript.length).toBeGreaterThan(0); | ||
|
|
||
| console.log(result.data.message); | ||
| }, 30000); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,105 @@ | ||
| import { BaseTool, RunResult } from '@shinkai_protocol/shinkai-tools-builder'; | ||
| import { ToolDefinition } from 'libs/shinkai-tools-builder/src/tool-definition'; | ||
| import { TranscriptResponse, YoutubeTranscript } from 'youtube-transcript'; | ||
| import { Ollama } from 'ollama'; | ||
|
|
||
| type Config = { | ||
| ollamaApiUrl?: string; | ||
| }; | ||
| type Params = { | ||
| url: string; | ||
| ollamaModel: string; | ||
| }; | ||
| type Result = { transcript: TranscriptResponse[]; message: string }; | ||
|
|
||
| export class Tool extends BaseTool<Config, Params, Result> { | ||
| definition: ToolDefinition<Config, Params, Result> = { | ||
| id: 'shinkai-tool-youtube-transcript', | ||
| name: 'Shinkai: YouTube Transcript', | ||
| description: 'Retrieve the transcript of a YouTube video', | ||
| author: 'Shinkai', | ||
| keywords: ['youtube', 'transcript', 'video', 'captions', 'subtitles'], | ||
| configurations: { | ||
| type: 'object', | ||
| properties: { | ||
| ollamaApiUrl: { type: 'string', nullable: true }, | ||
| }, | ||
| required: [], | ||
| }, | ||
| parameters: { | ||
| type: 'object', | ||
| properties: { | ||
| url: { | ||
| type: 'string', | ||
| description: 'The URL of the YouTube video to transcribe', | ||
| }, | ||
| ollamaModel: { | ||
| type: 'string', | ||
| description: 'The Ollama model to use for generating the summary', | ||
| }, | ||
| }, | ||
| required: ['url'], | ||
| }, | ||
| result: { | ||
| type: 'object', | ||
| properties: { | ||
| transcript: { | ||
| type: 'array', | ||
| items: { | ||
| type: 'object', | ||
| properties: { | ||
| text: { type: 'string' }, | ||
| duration: { type: 'number' }, | ||
| offset: { type: 'number' }, | ||
| lang: { type: 'string', nullable: true }, | ||
| }, | ||
| required: ['text', 'duration', 'offset'], | ||
| }, | ||
| }, | ||
| message: { type: 'string' }, | ||
| }, | ||
| required: ['transcript'], | ||
| }, | ||
| }; | ||
|
|
||
| async run(params: Params): Promise<RunResult<Result>> { | ||
| console.log(`transcripting ${params.url}`); | ||
|
|
||
| // Get transcription | ||
| const transcript = await YoutubeTranscript.fetchTranscript(params.url); | ||
|
|
||
| // Send to ollama to build a formatted response | ||
| const message = { | ||
| role: 'user', | ||
| content: ` | ||
| According to this transcription of a youtube video (which is in csv separated by ';'): | ||
| offset;text | ||
| ${transcript.map((v) => `${v.offset};${v.text}`).join('\n')} | ||
| --------------- | ||
| The video URL is ${params.url} | ||
| --------------- | ||
| Write a detailed summary divided in sections along the video. | ||
| Format the answer using markdown. | ||
| Add markdown links referencing every section using this format https://www.youtube.com/watch?v={video_id}&t={offset} where 'offset' is a number and can be obtained from the transcription in csv format and should be in seconds to generate the URL | ||
| `, | ||
| }; | ||
| const ollamaClient = new Ollama({ host: 'http://localhost:11435' }); | ||
| try { | ||
| const response = await ollamaClient.chat({ | ||
| model: params.ollamaModel, | ||
| messages: [message], | ||
| stream: false, | ||
| }); | ||
| return Promise.resolve({ | ||
| data: { transcript, message: response.message.content }, | ||
| }); | ||
| } catch (error) { | ||
| console.error('Error calling Ollama API:', error); | ||
| throw error; | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| { | ||
| "extends": "./tsconfig.json", | ||
| "include": ["./src/**/*.ts"] | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| { | ||
| "extends": "../../tsconfig.base.json", | ||
| "compilerOptions": { | ||
|
|
||
| }, | ||
| "include": [ | ||
| "./src/**/*.ts", | ||
| "webpack.config.ts" | ||
| ], | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "extends": "./tsconfig.json", | ||
| "compilerOptions": { | ||
| "outDir": "../../dist/out-tsc", | ||
| "module": "commonjs", | ||
| "types": ["jest", "node"] | ||
| }, | ||
| "include": [ | ||
| "jest.config.ts", | ||
| "src/**/*.test.ts", | ||
| "src/**/*.spec.ts", | ||
| "src/**/*.d.ts" | ||
| ] | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.