Migrate from LlamaParse to txtfetch

curl -X POST https://api.txtfetch.com/v1/extract \
  -H "Authorization: Bearer $TXTFETCH_KEY" \
  -F file=@report.pdf

import os

import requests

with open("report.pdf", "rb") as f:
    r = requests.post(
        "https://api.txtfetch.com/v1/extract",
        headers={"Authorization": f"Bearer {os.environ['TXTFETCH_KEY']}"},
        files={"file": f},
    )

print(r.json()["extracted_text"])

import { readFile } from "node:fs/promises";

const file = new Blob([await readFile("report.pdf")]);
const form = new FormData();
form.append("file", file, "report.pdf");

const res = await fetch("https://api.txtfetch.com/v1/extract", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.TXTFETCH_KEY}` },
  body: form,
});

const { extracted_text } = await res.json();
console.log(extracted_text);

import os

import requests


def parse_like_pages(file_path: str) -> list[str]:
    """Drop-in swap for result.markdown.pages[n].markdown.

    txtfetch has no per-page split, so this returns a one-item list.
    Downstream code that joins all pages into one string keeps working
    unmodified; code that indexes a specific page needs a rewrite.
    """
    with open(file_path, "rb") as f:
        r = requests.post(
            "https://api.txtfetch.com/v1/extract",
            headers={"Authorization": f"Bearer {os.environ['TXTFETCH_KEY']}"},
            files={"file": f},
        )
    r.raise_for_status()
    return [r.json()["extracted_text"]]

import { readFile } from "node:fs/promises";

// Drop-in swap for result.markdown.pages[n].markdown. txtfetch has no
// per-page split, so this returns a one-item array.
async function parseLikePages(filePath) {
  const file = new Blob([await readFile(filePath)]);
  const form = new FormData();
  form.append("file", file, filePath);

  const res = await fetch("https://api.txtfetch.com/v1/extract", {
    method: "POST",
    headers: { Authorization: `Bearer ${process.env.TXTFETCH_KEY}` },
    body: form,
  });

  const { extracted_text } = await res.json();
  return [extracted_text];
}