Pick your framework.

npm install @txtfetch/sdk

import { Txtfetch } from "@txtfetch/sdk";

// apiKey defaults to process.env.TXTFETCH_KEY
const txtfetch = new Txtfetch();

const { extracted_text, metadata } = await txtfetch.extract({ file: "./whitepaper.pdf" });
console.log(extracted_text, metadata.chars);

const byUrl = await txtfetch.extract({ url: "https://example.com/report.docx" });
console.log(byUrl.extracted_text);

pip install txtfetch

from txtfetch import Txtfetch

# api_key defaults to the TXTFETCH_KEY environment variable
client = Txtfetch(api_key="tf_live_...")

# Extract from a local file (path, bytes, or a file-like object all work)
result = client.extract(file="whitepaper.pdf")
print(result.extracted_text)
print(result.metadata.content_type, result.metadata.bytes, result.metadata.ocr)

# Extract from a URL — txtfetch fetches it server-side
result = client.extract(url="https://example.com/whitepaper.docx")

pip install langchain-txtfetch

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_txtfetch import TxtfetchLoader

# api_key defaults to the TXTFETCH_KEY environment variable
loader = TxtfetchLoader(
    files=["whitepaper.pdf"],           # single path/URL or a list of them
    urls=["https://example.com/spec.docx"],
)

documents = loader.load()

splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
chunks = splitter.split_documents(documents)

npm install @txtfetch/langchain @langchain/core

import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
import { TxtfetchLoader } from "@txtfetch/langchain";

// apiKey defaults to the TXTFETCH_KEY environment variable
const loader = new TxtfetchLoader({
  files: ["whitepaper.pdf"], // a single path/URL or an array of them
  urls: ["https://example.com/spec.docx"],
});

const documents = await loader.load();

const splitter = new RecursiveCharacterTextSplitter({ chunkSize: 1000, chunkOverlap: 100 });
const chunks = await splitter.splitDocuments(documents);

pip install llama-index-readers-txtfetch

from llama_index.core import VectorStoreIndex
from llama_index.readers.txtfetch import TxtfetchReader

# api_key defaults to the TXTFETCH_KEY environment variable
reader = TxtfetchReader()

documents = reader.load_data(
    files=["whitepaper.pdf"],           # single path/URL or a list of them
    urls=["https://example.com/spec.docx"],
)

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
print(query_engine.query("What is this document about?"))