[PR #4552] [MERGED] Refactor loadYouTubeTranscript() to include YouTube Video Metadata in Content When parseOnly is true #4671

Closed
opened 2026-02-22 18:36:18 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/4552
Author: @angelplusultra
Created: 10/15/2025
Status: Merged
Merged: 10/15/2025
Merged by: @timothycarambat

Base: masterHead: 4551-feat-include-youtube-video-metadata-in-agent-scrapegenericurl-usage


📝 Commits (3)

  • 8b4df30 Enhance YouTube transcript loading to include video metadata in parsed content when parseOnly is true
  • 5a2be57 extract to function
  • 03e5eeb Merge branch 'master' into 4551-feat-include-youtube-video-metadata-in-agent-scrapegenericurl-usage

📊 Changes

1 file changed (+40 additions, -3 deletions)

View changed files

📝 collector/utils/extensions/YoutubeTranscript/index.js (+40 -3)

📄 Description

Pull Request Type

  • feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 🔨 chore
  • 📝 docs

Relevant Issues

resolves #4551

What is in this change?

This PR includes a small change to include the YouTube video metadata in the the returned content field from the loadyouTubeTranscript() function when the parseOnly options argument is set to true.

When chatting about a YouTube video with @agent, The LLM is now exposed to extra context about the YouTube video.

Original Result

image

New Result

image

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Mintplex-Labs/anything-llm/pull/4552 **Author:** [@angelplusultra](https://github.com/angelplusultra) **Created:** 10/15/2025 **Status:** ✅ Merged **Merged:** 10/15/2025 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `4551-feat-include-youtube-video-metadata-in-agent-scrapegenericurl-usage` --- ### 📝 Commits (3) - [`8b4df30`](https://github.com/Mintplex-Labs/anything-llm/commit/8b4df301db3f8191e928e321e05defe9703583c0) Enhance YouTube transcript loading to include video metadata in parsed content when parseOnly is true - [`5a2be57`](https://github.com/Mintplex-Labs/anything-llm/commit/5a2be57310519b10e0bb781905670f30976d3412) extract to function - [`03e5eeb`](https://github.com/Mintplex-Labs/anything-llm/commit/03e5eeb3acb9bbad8b2503fa12ed68b5f58177e5) Merge branch 'master' into 4551-feat-include-youtube-video-metadata-in-agent-scrapegenericurl-usage ### 📊 Changes **1 file changed** (+40 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `collector/utils/extensions/YoutubeTranscript/index.js` (+40 -3) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [ ] ✨ feat - [ ] 🐛 fix - [x] ♻️ refactor - [ ] 💄 style - [ ] 🔨 chore - [ ] 📝 docs ### Relevant Issues <!-- Use "resolves #xxx" to auto resolve on merge. Otherwise, please use "connect #xxx" --> resolves #4551 ### What is in this change? <!-- Describe the changes in this PR that are impactful to the repo. --> This PR includes a small change to include the YouTube video metadata in the the returned `content` field from the `loadyouTubeTranscript()` function when the `parseOnly` options argument is set to `true`. When chatting about a YouTube video with `@agent`, The LLM is now exposed to extra context about the YouTube video. ### Original Result <img width="1243" height="875" alt="image" src="https://github.com/user-attachments/assets/3acbd90a-bbfd-4373-bfdd-a11763ea868c" /> ### New Result <img width="1243" height="774" alt="image" src="https://github.com/user-attachments/assets/723cbb72-2e80-42fc-9caa-a65921d54b04" /> ### Additional Information <!-- Add any other context about the Pull Request here that was not captured above. --> ### Developer Validations <!-- All of the applicable items should be checked. --> - [x] I ran `yarn lint` from the root of the repo & committed changes - [x] Relevant documentation has been updated - [x] I have tested my code functionality - [ ] Docker build succeeds locally --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-22 18:36:18 -05:00
yindo closed this issue 2026-02-22 18:36:18 -05:00
yindo changed title from [PR #4552] Refactor `loadYouTubeTranscript()` to include YouTube Video Metadata in Content When `parseOnly` is `true` to [PR #4552] [MERGED] Refactor `loadYouTubeTranscript()` to include YouTube Video Metadata in Content When `parseOnly` is `true` 2026-06-05 15:19:45 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#4671