Extracting Tables using GPT-Vision¶

from io import StringIO
from typing import Annotated, Any
from pydantic import BeforeValidator, PlainSerializer, InstanceOf, WithJsonSchema
import pandas as pd


def md_to_df(data: Any) -> Any:
    # Convert markdown to DataFrame
    if isinstance(data, str):
        return (
            pd.read_csv(
                StringIO(data),  # Process data
                sep="|",
                index_col=1,
            )
            .dropna(axis=1, how="all")
            .iloc[1:]
            .applymap(lambda x: x.strip())
        )
    return data


MarkdownDataFrame = Annotated[
    InstanceOf[pd.DataFrame],
    BeforeValidator(md_to_df),
    PlainSerializer(lambda df: df.to_markdown()),
    WithJsonSchema(
        {
            "type": "string",
            "description": "The markdown representation of the table, each one should be tidy, do not try to join tables that should be seperate",
        }
    ),
]

class Table(BaseModel):
    caption: str
    dataframe: MarkdownDataFrame

import instructor
from openai import OpenAI

# Apply the patch to the OpenAI client to support response_model
# Also use MD_JSON mode since the visino model does not support any special structured output mode
client = instructor.from_openai(OpenAI(), mode=instructor.function_calls.Mode.MD_JSON)


def extract_table(url: str) -> Iterable[Table]:
    return client.chat.completions.create(
        model="gpt-4-vision-preview",
        response_model=Iterable[Table],
        max_tokens=1800,
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Extract table from image."},
                    {"type": "image_url", "image_url": {"url": url}},
                ],
            }
        ],
    )

url = "https://a.storyblok.com/f/47007/2400x2000/bf383abc3c/231031_uk-ireland-in-three-charts_table_v01_b.png"
tables = extract_table(url)
for table in tables:
    print(table.caption, end="\n")
    print(table.dataframe)