feat: Integrate video reading #883
Conversation
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
- Update .gitignore to include new download configuration files and temporary video directory - Refactor test_video_function.py to use VideoDownloaderToolkit class and update test cases
Thank you! @Wendong-Fan . During the testing process, I found that our test folder was named |
…nto_chunks parameter and updated the
I see, thanks @ZackYule |
There was a problem hiding this comment.
Thanks @ZackYule 's update, some comments below, please also solve conflicts with master branch
camel/toolkits/video_toolkit.py
Outdated
| print( | ||
| f'''Warning: cookies.txt file not found at path | ||
| {cookies_path}.''' | ||
| ) | ||
| self._cookies_path = None |
There was a problem hiding this comment.
here we can return the warning message directly for agent using
There was a problem hiding this comment.
Thanks @Wendong-Fan！ This is a good idea. However, when we download certain videos, cookies may not be necessary. So this is just a warning and does not terminate the program.
- Added calculate_file_hash and file_exists_and_is_identical functions to utils/__init__.py - Added test_video_screenshots_download function to test_video_function.py
Thank @Wendong-Fan for the comments, these issues have been resolved. |
|
|
||
| print(f"Trying to download video from: {video_url}") | ||
| try: | ||
| downloader = VideoDownloaderToolkit(video_url=video_url) |
There was a problem hiding this comment.
I believe that we need to understand how to support multi modal capability. The toolkits are defined for the agent. I think that the ideal way is the agent could figure out the steps by itself, instead of that developers call the toolkit functions to process the data and pass the final results to the agent.
There was a problem hiding this comment.
For now if we want to make it fully automatic we need to define another agent to handle multi-modal information, I think we can finish the functionality part first and add further support if possible
There was a problem hiding this comment.
Because the agent currently has multiple input channels, I think we should first manage the selection of these input channels in the next step.
|
|
||
| print(f"Trying to download video from: {video_url}") | ||
| try: | ||
| downloader = VideoDownloaderToolkit(video_url=video_url) |
There was a problem hiding this comment.
For now if we want to make it fully automatic we need to define another agent to handle multi-modal information, I think we can finish the functionality part first and add further support if possible
…r and update usage in web_video_object_recognition.py, web_video_description_extractor.py, and test_video_function.py
Description
Download the video using yt-dlp and provide it to the multimodal agent for analysis. Two download options are available: full download and block download.
Motivation and Context
close #744Types of changes
What types of changes does your code introduce? Put an
xin all the boxes that apply:Implemented Tasks
Checklist
Go over all the following points, and put an
xin all the boxes that apply.If you are unsure about any of these, don't hesitate to ask. We are here to help!