langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 04:15:25 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #442] docs: Reusing uploaded media (video) with Langchain + GoogleGenAI #66

New Issue
Closed
opened 2026-02-17 17:19:06 -05:00 by yindo · 0 comments
yindo commented 2026-02-17 17:19:06 -05:00
Owner
Copy Link
Copy Source

Originally created by @lnhsingh on GitHub (Sep 9, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/442

Idea or request for content:

When using GoogleGenAI directly, uploading a video and generating a response are two distinct steps, as described in the official API documentation.
This approach has the advantage that the uploaded media object can be reused in multiple requests.

For Langchain, I found the following reference after some searching:
https://v03.api.js.langchain.com/modules/_langchain_google_common.experimental_media.html

However, this media object handling is neither described nor used in the official Langchain documentation. Instead, videos are always sent directly with the request, as seen here:
https://js.langchain.com/docs/how_to/tool_calls_multimodal/#google-generative-ai

Could you provide a code snippet demonstrating how to use the Media object with Langchain?
Would it make sense to include this pattern in the official documentation, especially for use cases where media reuse is beneficial?

Thanks a lot,
Ingo

Original issue: https://github.com/langchain-ai/langchainjs/issues/8576

Originally created by @lnhsingh on GitHub (Sep 9, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/442 ### Idea or request for content: When using GoogleGenAI directly, uploading a video and generating a response are two distinct steps, as described in the [official API documentation](https://ai.google.dev/api/files#files_create_video-JAVASCRIPT). This approach has the advantage that the uploaded media object can be reused in multiple requests. For Langchain, I found the following reference after some searching: https://v03.api.js.langchain.com/modules/_langchain_google_common.experimental_media.html However, this media object handling is neither described nor used in the official Langchain documentation. Instead, videos are always sent directly with the request, as seen here: https://js.langchain.com/docs/how_to/tool_calls_multimodal/#google-generative-ai Could you provide a code snippet demonstrating how to use the Media object with Langchain? Would it make sense to include this pattern in the official documentation, especially for use cases where media reuse is beneficial? Thanks a lot, Ingo Original issue: https://github.com/langchain-ai/langchainjs/issues/8576
yindo added the langchainjs/tsinternal labels 2026-02-17 17:19:06 -05:00
yindo closed this issue 2026-02-17 17:19:06 -05:00
yindo changed title from docs: Reusing uploaded media (video) with Langchain + GoogleGenAI to [GH-ISSUE #442] docs: Reusing uploaded media (video) with Langchain + GoogleGenAI 2026-06-05 17:24:52 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label internal js/ts langchain
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#66
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?