Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Autogenerate annotations for evals with tarsier+LLM #37

Merged
merged 5 commits into from
Dec 11, 2023
Merged

Conversation

KhoomeiK
Copy link
Contributor

@KhoomeiK KhoomeiK commented Dec 7, 2023

Also added schemas for attorney and lawyer job posting data

TODO: determine if and how to integrate these abilities with bananalyze CLI

Copy link

vercel bot commented Dec 7, 2023

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
bananalytics ✅ Ready (Inspect) Visit Preview 💬 Add feedback Dec 11, 2023 6:44pm

Comment on lines 138 to 159
async def main():
openai_client = OpenAI()
ocr_service = GoogleVisionOCRService()
tarsier_client = Tarsier(ocr_service)

urls = [
"https://www.skadden.com/professionals/l/lanstra-allen-l",
"https://www.sullcrom.com/Lawyers/Erik-D-Lindauer",
"https://www.winston.com/en/professionals/padmanabhan-krishnan",
"https://www.mwe.com/people/michael-abercrombie/",
]
schema = get_fetch_schema("attorney").model_fields
metadata = {
"category": "legal",
"subcategory": "attorney_details",
"fetch_id": "attorney",
}
await add_examples_to_json(urls, schema, metadata, tarsier_client, openai_client)


# if __name__ == "__main__":
# asyncio.run(main())
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could also make this a CLI tool

Co-authored-by: Asim Shrestha <50181239+asim-shrestha@users.noreply.github.com>
@asim-shrestha asim-shrestha merged commit acc4d6d into main Dec 11, 2023
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants