tarsier icon indicating copy to clipboard operation
tarsier copied to clipboard

Vision utilities for web interaction agents 👀

Results 23 tarsier issues
Sort by recently updated
recently updated
newest added

Currently the only OCR service tarsier supports is GoogleOCR vision. It would be good to provide another ocr service that allows textextract to be used

good first issue

Currently the only OCR service Tarsier supports is GoogleOCR vision. We're told Microsoft's model is the most performant so would love to also include it! Documentation: https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-read?view=doc-intel-4.0.0

good first issue

As a user, I'd like to customize the colors of tags. I'd also like to set different tag colors based on the type of element. For example, maybe I want...

enhancement
help wanted

I'm working on something pretty similar to what you guys are doing and had a thought. Why not grab text directly from the web instead of using OCR? Langchain and...

Bumps [playwright](https://github.com/Microsoft/playwright-python) from 1.41.1 to 1.43.0. Release notes Sourced from playwright's releases. v1.43.0 New APIs Method BrowserContext.clear_cookies([options]) now supports filters to remove only some cookies. # Clear all cookies. context.clear_cookies()...

dependencies

Bumps [idna](https://github.com/kjd/idna) from 3.6 to 3.7. Release notes Sourced from idna's releases. v3.7 What's Changed Fix issue where specially crafted inputs to encode() could take exceptionally long amount of time...

dependencies

Bumps [pytest](https://github.com/pytest-dev/pytest) from 7.4.4 to 8.2.0. Release notes Sourced from pytest's releases. 8.2.0 pytest 8.2.0 (2024-04-27) Deprecations #12069: A deprecation warning is now raised when implementations of one of the...

dependencies

Bumps [selenium](https://github.com/SeleniumHQ/Selenium) from 4.17.2 to 4.20.0. Release notes Sourced from selenium's releases. Selenium 4.20.0 Changelog For each component's detailed changelog, please check: Ruby Python JavaScript Java DotNet IEDriverServer Commits in...

dependencies

Bumps [google-cloud-vision](https://github.com/googleapis/google-cloud-python) from 3.6.0 to 3.7.2. Release notes Sourced from google-cloud-vision's releases. google-cloud-vision: v3.7.2 3.7.2 (2024-03-05) Bug Fixes deps: Exclude google-auth 2.24.0 and 2.25.0 (#12388) (d2cd4ff) Commits c57e4a2 chore: release...

dependencies