Adding gpt4o vision example

[karbon0x]

Summary:
Adds an example of vision using gpt4o

Key points:

• Adds vision example using gpt4o
• Currently utilizes two receipts. One of them is parsed correctly, the second one isn't highlighting the limitations of these models for OCR.
• Model validator helps us ensure sum of items = total in the receipt.

---

🚀 This description was created by Ellipsis for commit 18b5c96

Summary:

Introduces a new example script for demonstrating OCR capabilities of GPT-4o using receipts, with data validation.

Key points:

• Adds run_vision_gpt4o.py under examples/extract-table/
• Utilizes openai and pydantic for OCR and data validation
• Demonstrates model's OCR capabilities with two receipt images
• Includes a model validator to ensure accuracy of extracted data

---

Generated with ❤️ by ellipsis.dev

[ellipsis-dev]

❌ Changes requested. Reviewed everything up to 18b5c96 in 39 seconds

More details

• Looked at 72 lines of code in 1 files
• Skipped 0 files when reviewing.
• Skipped posting 0 drafted comments based on config settings.

Workflow ID: wflow_dSZ3efBx0qzaOErv

---

Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[ellipsis-dev]

Sorry, I don't know how to help with that. If you tag me (@ellipsis-dev) in a comment, I can do one of these things (but not multiple at once):

• review and summarize this pull request
• make changes to this pull request
• answer questions about this PR, or about the codebase in general
• hide my old reviews on this PR (to reduce clutter)