Samples for VLM video input.

[popovaan]

Description

Python and C++ samples for VLM video input.

CVS-175408

Checklist:

• Tests have been updated or added to cover the new code.
• This patch fully addresses the ticket. - This PR doesn't cover C sample, need a separate ticket for it.
• I have made corresponding changes to the documentation.

[Copilot]

Pull Request Overview

This PR adds a Python sample demonstrating video-to-text functionality for Vision Language Models (VLMs). The sample enables users to input video files and interact with VLMs through a chat interface.

• Adds new video_to_text_chat.py sample for VLM video input processing
• Updates test configuration to include a tiny random LLaVA-NeXT-Video model and sample video file
• Updates documentation to describe the new video-to-text sample usage

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
tests/python_tests/samples/conftest.py	Adds test model configuration for LLaVA-NeXT-Video and sample video file resource
samples/python/visual_language_chat/video_to_text_chat.py	New sample implementing video-to-text chat functionality using VLM pipeline
samples/python/visual_language_chat/README.md	Updates documentation to describe the new video-to-text sample and its usage
samples/deployment-requirements.txt	Adds opencv-python dependency required for video processing

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.