From 4bbc249b134a6fba638f7b84dfd252ef0e75ae3e Mon Sep 17 00:00:00 2001
From: Armaanjeet Singh Sandhu
 <90208595+ArmaanjeetSandhu@users.noreply.github.com>
Date: Tue, 1 Apr 2025 16:43:06 +0530
Subject: [PATCH] community: Fix attribute access for transcript text in
 YoutubeLoader (Fixes #30309) (#30582)

**Description:**
Fixes a bug in the YoutubeLoader where FetchedTranscript objects were
not properly processed. The loader was only extracting the 'text'
attribute from FetchedTranscriptSnippet objects while ignoring 'start'
and 'duration' attributes. This would cause a TypeError when the code
later tried to access these missing keys, particularly when using the
CHUNKS format or any code path that needed timestamp information.

This PR modifies the conversion of FetchedTranscriptSnippet objects to
include all necessary attributes, ensuring that the loader works
correctly with all transcript formats.

**Issue:** Fixes #30309

**Dependencies:** None

**Testing:**
- Tested the fix with multiple YouTube videos to confirm it resolves the
issue
- Verified that both regular loading and CHUNKS format work correctly
---
 .../langchain_community/document_loaders/youtube.py      | 9 ++++++++-
 libs/community/uv.lock                                   | 8 ++++----
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/libs/community/langchain_community/document_loaders/youtube.py b/libs/community/langchain_community/document_loaders/youtube.py
index eeecad1af3..5b9dfe8736 100644
--- a/libs/community/langchain_community/document_loaders/youtube.py
+++ b/libs/community/langchain_community/document_loaders/youtube.py
@@ -272,7 +272,14 @@ class YoutubeLoader(BaseLoader):
             transcript = transcript.translate(self.translation)
         transcript_object = transcript.fetch()
         if isinstance(transcript_object, FetchedTranscript):
-            transcript_pieces = [{"text": x.text} for x in transcript_object.snippets]
+            transcript_pieces = [
+                {
+                    "text": snippet.text,
+                    "start": snippet.start,
+                    "duration": snippet.duration,
+                }
+                for snippet in transcript_object.snippets
+            ]
         else:
             transcript_pieces: List[Dict[str, Any]] = transcript_object  # type: ignore[no-redef]
 
diff --git a/libs/community/uv.lock b/libs/community/uv.lock
index 91ccbf4f44..99a14abe52 100644
--- a/libs/community/uv.lock
+++ b/libs/community/uv.lock
@@ -1492,7 +1492,7 @@ wheels = [
 
 [[package]]
 name = "langchain"
-version = "0.3.21"
+version = "0.3.22"
 source = { editable = "../langchain" }
 dependencies = [
     { name = "async-timeout", marker = "python_full_version < '3.11'" },
@@ -1747,7 +1747,7 @@ typing = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.47"
+version = "0.3.49"
 source = { editable = "../core" }
 dependencies = [
     { name = "jsonpatch" },
@@ -1777,7 +1777,7 @@ dev = [
     { name = "jupyter", specifier = ">=1.0.0,<2.0.0" },
     { name = "setuptools", specifier = ">=67.6.1,<68.0.0" },
 ]
-lint = [{ name = "ruff", specifier = ">=0.9.2,<1.0.0" }]
+lint = [{ name = "ruff", specifier = ">=0.11.2,<0.12.0" }]
 test = [
     { name = "blockbuster", specifier = "~=1.5.18" },
     { name = "freezegun", specifier = ">=1.2.2,<2.0.0" },
@@ -1805,7 +1805,7 @@ typing = [
 
 [[package]]
 name = "langchain-tests"
-version = "0.3.15"
+version = "0.3.17"
 source = { editable = "../standard-tests" }
 dependencies = [
     { name = "httpx" },