crewai-xberg

CrewAI tools backed by Xberg. Give an agent document intelligence: extract text, metadata, keywords, entities, and summaries from 97 file formats — PDF, DOCX, XLSX, HTML, images with OCR, and more. Extraction is async at the core; the batch tool routes many files through Xberg's extract_batch in a single native call.

Install

pip install crewai-xberg

Requires Python 3.10+.

Tools

Tool	Input	Returns
`XbergExtractTool`	`file_path`	Extracted text, plus any requested rich results.
`XbergExtractBatchTool`	`file_paths`	One section per document via `extract_batch`, then errors.
`XbergExtractMetadataTool`	`file_path`	Title, authors, dates, page/table/image counts, format info.

Use

from crewai import Agent
from crewai_xberg import XbergExtractTool, XbergExtractBatchTool, XbergExtractMetadataTool

agent = Agent(
    role="Document Analyst",
    goal="Extract and analyze document content",
    backstory="You process documents of any format.",
    tools=[XbergExtractTool(), XbergExtractBatchTool(), XbergExtractMetadataTool()],
)

Call a tool directly to see its output:

tool = XbergExtractTool()

# Plain extraction
text = tool.run(file_path="report.pdf")

# Force OCR and surface keywords, entities, and a summary
enriched = tool.run(
    file_path="scan.pdf",
    output_format="markdown",
    force_ocr=True,
    extract_keywords=True,
    extract_entities=True,
    summarize=True,
)

# Many files in one batched extraction
combined = XbergExtractBatchTool().run(file_paths=["report.pdf", "notes.docx", "sheet.xlsx"])

Options

Both extraction tools accept the same options. Each toggles an Xberg ExtractionConfig capability:

Option	Default	Effect
`output_format`	`"markdown"`	`plain`, `markdown`, or `html`.
`force_ocr`	`False`	Run OCR on every page, even with a text layer.
`chunk`	`False`	Split into semantic chunks; report the chunk count.
`extract_keywords`	`False`	Append a keyword list.
`extract_entities`	`False`	Append named entities (people, orgs, locations).
`summarize`	`False`	Append a short summary.

Detected languages and tables are surfaced automatically when present.

Async

The tools are async at the core. Inside an event loop, await tool.arun(...); the synchronous run bridges to it and must not be called from a running loop.

Errors

A missing file raises from Xberg directly. In batch mode, per-file failures land in ExtractionResult.errors and are reported in a trailing Errors section instead of aborting the batch.

For the full API, see the Xberg documentation.

Metadata

Release files for crewai-xberg 1.0.0rc36

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for crewai-xberg 1.0.0rc36
File	Interpreter	ABI	Platform	Reset
crewai_xberg-1.0.0rc36-py3-none-any.whl 8.0 kB Jul 24, 2026	Python 3	none	any	Details

Release files / crewai_xberg-1.0.0rc36-py3-none-any.whl

Download URL	crewai_xberg-1.0.0rc36-py3-none-any.whl
Size	8.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`fa20886989cab58c31714c9e403ff2fad30d7245063b7963b930ee40fee1df5f`
BLAKE2b-256 checksum How to use checksums	`0efdc98c1c542d231c6d790290e1da74494ac8c5f01663b7dbfebede73111f6b`
Upload date	Jul 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`uv/0.11.32 {"installer":{"name":"uv","version":"0.11.32","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`