Xberg Document Extraction

pip install xberg

npm install @xberg-io/xberg

cargo add xberg

# Cargo.toml
[dependencies]
xberg = { version = "1.1.0", features = ["full"] }
tokio = { version = "1", features = ["full"] }
# feature flags: pdf, ocr, chunking, embeddings, language-detection, keywords, api, mcp
#                (or "formats" / "full" aggregates); tokio-runtime is on by default

brew install xberg-io/tap/xberg
# or run without a persistent install (the CLI proxy package self-installs the binary):
npx @xberg-io/xberg-cli --help
uvx --from xberg-cli xberg --help
# or download a prebuilt binary from the latest GitHub release:
#   https://github.com/xberg-io/xberg/releases/latest
# or build from source:
cargo install xberg-cli

import asyncio
from xberg import ExtractInput, extract, ExtractionConfig

async def main() -> None:
    result = await extract(ExtractInput(uri="document.pdf"), ExtractionConfig())
    doc = result.results[0]
    print(doc.content)    # extracted text
    print(doc.metadata)   # document metadata
    print(doc.tables)     # extracted tables

asyncio.run(main())

import { extract } from "@xberg-io/xberg";

const output = await extract({ kind: "uri", uri: "document.pdf" });
const doc = output.results[0];
console.log(doc.content);
console.log(doc.metadata);
console.log(doc.tables);

use xberg::{extract, ExtractInput, ExtractionConfig};

#[tokio::main]
async fn main() -> xberg::Result<()> {
    let output = extract(ExtractInput::from_uri("document.pdf"), &ExtractionConfig::default()).await?;
    println!("{}", output.results[0].content);
    Ok(())
}

xberg extract document.pdf
xberg extract document.pdf --format json
xberg extract document.pdf --content-format markdown

from xberg import (
    ExtractInput, extract,
    ExtractionConfig, OcrConfig, TesseractConfig, PdfConfig, ChunkingConfig, OutputFormat,
)

config = ExtractionConfig(
    ocr=OcrConfig(
        backend="tesseract",
        language=["eng"],
        tesseract_config=TesseractConfig(psm=6, enable_table_detection=True),
    ),
    pdf_options=PdfConfig(passwords=["secret123"]),
    chunking=ChunkingConfig(max_characters=1000, overlap=200),
    output_format=OutputFormat("markdown"),
)

result = await extract(ExtractInput(uri="document.pdf"), config)

import { extract, type ExtractionConfig } from "@xberg-io/xberg";

const config: ExtractionConfig = {
  ocr: { backend: "tesseract", language: ["eng"] },
  pdfOptions: { passwords: ["secret123"] },
  chunking: { maxCharacters: 1000, overlap: 200 },
  outputFormat: "markdown",
};

const output = await extract({ kind: "uri", uri: "document.pdf" }, config);

use xberg::{extract, ExtractInput, ExtractionConfig, OcrConfig, ChunkingConfig, OutputFormat};

let config = ExtractionConfig {
    ocr: Some(OcrConfig {
        backend: "tesseract".into(),
        language: vec!["eng".to_string()],
        ..Default::default()
    }),
    chunking: Some(ChunkingConfig {
        max_characters: 1000,
        overlap: 200,
        ..Default::default()
    }),
    output_format: OutputFormat::Markdown,
    ..Default::default()
};

let output = extract(ExtractInput::from_uri("document.pdf"), &config).await?;

output_format = "markdown"

[ocr]
backend = "tesseract"
language = "eng"

[chunking]
max_characters = 1000
overlap = 200

[pdf_options]
passwords = ["secret123"]

# CLI: auto-discovers xberg.toml/yaml/yml/json in current/parent directories
xberg extract doc.pdf
# or explicit:
xberg extract doc.pdf --config xberg.toml
xberg extract doc.pdf --config-json '{"ocr":{"backend":"tesseract","language":"deu"}}'

from xberg import ExtractInput, extract_batch, ExtractionConfig

inputs = [
    ExtractInput(uri="doc1.pdf"),
    ExtractInput(uri="doc2.docx"),
    ExtractInput(uri="doc3.xlsx"),
]
output = await extract_batch(inputs, ExtractionConfig())

for doc in output.results:
    print(f"{len(doc.content)} chars extracted")

import { extractBatch } from "@xberg-io/xberg";

const output = await extractBatch([
  { kind: "uri", uri: "doc1.pdf" },
  { kind: "uri", uri: "doc2.docx" },
]);
for (const doc of output.results) {
  console.log(`${doc.content.length} chars`);
}

use xberg::{extract_batch, ExtractInput, ExtractionConfig};

let config = ExtractionConfig::default();
let inputs = vec![ExtractInput::from_uri("doc1.pdf"), ExtractInput::from_uri("doc2.docx")];
let output = extract_batch(inputs, &config).await?;

xberg batch *.pdf --format json
xberg batch docs/*.docx --content-format markdown

config = ExtractionConfig(ocr=OcrConfig(language=["eng"]))          # English
config = ExtractionConfig(ocr=OcrConfig(language=["eng", "deu"]))   # Multiple
# The single-string shorthand ("eng+deu") is only accepted in config files / --config-json,
# not in the OcrConfig constructor (Python takes a list, Node takes an array).

config = ExtractionConfig(force_ocr=True)  # OCR even if text is extractable

from xberg import ExtractInput, extract, ExtractionConfig

try:
    result = await extract(ExtractInput(uri="file.pdf"), ExtractionConfig())
    for err in result.errors:
        print(f"Per-input error: {err}")
except RuntimeError as e:
    print(f"Extraction failed: {e}")

import { extract } from "@xberg-io/xberg";

try {
  const output = await extract({ kind: "uri", uri: "file.pdf" });
  if (output.errors.length > 0) {
    console.error("Per-input errors:", output.errors);
  }
} catch (e) {
  if (e instanceof Error) {
    console.error(`Extraction failed: ${e.message}`);
  }
}

use xberg::{extract, ExtractInput, ExtractionConfig, XbergError};

let config = ExtractionConfig::default();
match extract(ExtractInput::from_uri("file.pdf"), &config).await {
    Ok(output) => println!("{}", output.results[0].content),
    Err(XbergError::Parsing { message, .. }) => eprintln!("Parse error: {message}"),
    Err(XbergError::Ocr { message, .. }) => eprintln!("OCR error: {message}"),
    Err(XbergError::UnsupportedFormat(mime)) => eprintln!("Unsupported: {mime}"),
    Err(e) => eprintln!("Error: {e}"),
}