roboflow / roboflow/inference

Can add, delete, update stream realtime for only one pipeline has been run before?

Open
#362 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement question
Dominant language
Python
Stars
2.5k
Forks
320
Avg merge
1d 14h
Merged PRs (30d)
133

Description

Search before asking
  • I have searched the Inference issues and found no similar feature requests.
Question

Hello everyone,
I'm very interested in Roboflow Inference. I'm wondering, with the current InferencePipeline, is it possible to add, edit, and delete the number of inputs for just one pipeline?
For example, AI Model has a max_batch_size of 8
Initially I initialize:
pipeline = InferencePipeline(...) with only one RTSP stream
pipeline.start()

Can I add an RTSP stream to the pipeline running above? For example:
pipeline.add_stream("rtsp://...")
Does adding not affect previously running threads?

Can anyone help me answer if InferencePipeline currently has the ability to do that?
And in your opinion, add_stream to a running pipeline is better than having multiple copies of the pipeline running at the same time?
Thank!

Additional

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at the InferencePipeline entry point and trace how streams are created and managed; the issue names no files or tests. Done requires a maintainer-approved design or answer for adding, updating, and deleting streams on a running pipeline, including the behavior of existing threads.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.