Vector Retrieval and RAG · Public

kreuzberg

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Vector databaseRAGEmbeddingsSemantic searchData boundaries

Best fitDevelopers connecting knowledge bases, documents, or app data to semantic retrieval or RAG workflows.

Check whether this project matches your task before installing it.

What it can doVector database setup checks, embedding model boundaries, collection management, query acceptance, and deletion guidance

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot8.5k stars

501 forks · 46 contributors

Doramagic.ai Last verification date: 2026-07-05 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-07-05

What is kreuzberg?

kreuzberg is a vector database, retrieval, or RAG storage component for AI applications.
Best fit: Developers connecting knowledge bases, documents, or app data to semantic retrieval or RAG workflows.
Not for: Not for one-off model API calls or environments that cannot isolate indexed data, credentials, and persistence paths.
Capability added to an AI workflow: Vector database setup checks, embedding model boundaries, collection management, query acceptance, and deletion guidance
First safe verification step: Verify create, query, delete, and rollback with a small public text sample before using real data.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/kreuzberg-dev/kreuzberg, https://github.com/kreuzberg-dev/kreuzberg#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers connecting knowledge bases, documents, or app data to semantic retrieval or RAG workflows.

Match the project to your task before installing it.

CapabilityVector database setup checks, embedding model boundaries, collection management, query acceptance, and deletion guidance

Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.

Repositorykreuzberg-dev/kreuzberg

8.5k stars · 501 forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Introduction & Capabilities

Related topics: Workspace Layout & Crate Structure, Language Bindings, FFI & Polyglot, Deployment Modes & Serving

Sources: [docs/features.md:60-120](), community issues #1144 (pruning) and #1149 (PaddleOCR-VL 1.6 / PP-OCRv6 model support).

Workspace Layout & Crate Structure

Related topics: Extraction Pipeline & Format Handlers, Language Bindings, FFI & Polyglot

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

Extraction Pipeline & Format Handlers

Related topics: OCR Backends & Configuration, Plugin System, Enrichment & Embeddings, Known Issues, Limitations & Migration Notes

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

OCR Backends & Configuration

Related topics: Extraction Pipeline & Format Handlers, Known Issues, Limitations & Migration Notes

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

Language Bindings, FFI & Polyglot

Related topics: Workspace Layout & Crate Structure, Plugin System, Enrichment & Embeddings

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

Sources: https://github.com/kreuzberg-dev/kreuzberg, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars8.5k stars

Forks501 forks

Contributors46 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using kreuzberg with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
No cheap PDF page count in 5.x (PdfPageIterator removed)
github / github_issue
02
v5.0.0-rc.30: Tesseract C++ shim built without -std=c++17 (fails where c
github / github_issue
03
Default OcrConfig() raises ValueError (VlmFallbackPolicy "disabled")
github / github_issue
04
feat: support PaddleOCR-VL 1.6 and PP-OCRv6 models
github / github_issue
05
bug: Docker container does not respond to stop signals, resulting in tim
github / github_issue
06
bug: Processing warning for single-page very wide PDF during chunking
github / github_issue
07
feat: markdown footnote and citation parsing API
github / github_issue
08
bug: OCR bakes the build-runner's TESSDATA path into the released binary
github / github_issue
09
bug: HF/ONNX model download fails behind corporate TLS-MITM — no custom
github / github_issue
10
feat: sentence-level pruning (prune_async / open_provence) mirroring the
github / github_issue
11
bug: section heading present in markdown output but missing from `result
github / github_issue
12
bug: kreuzberg maps PDF ligature glyphs to C0 control characters
github / github_issue

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install kreuzberg

Official start command · https://github.com/kreuzberg-dev/kreuzberg#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

kreuzberg Manual

The Plugin System is kreuzberg's extension surface, letting integrators add custom extraction, post-processing, and validation logic without modifying the core extraction pipeline. It is d...

Open the full manual

https://github.com/kreuzberg-dev/kreuzberg Project Manual
Table of Contents
Introduction & Capabilities
Related Pages
What Kreuzberg Solves
Core Capabilities
Extraction Pipeline
OCR Backends

Introduction & Capabilities

Related topics: Workspace Layout & Crate Structure, Language Bindings, FFI & Polyglot, Deployment Modes & Serving

Sources: [docs/features.md:60-120](), community issues #1144 (pruning) and #1149 (PaddleOCR-VL 1.6 / PP-OCRv6 model support).

Workspace Layout & Crate Structure

Related topics: Extraction Pipeline & Format Handlers, Language Bindings, FFI & Polyglot

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

Extraction Pipeline & Format Handlers

Related topics: OCR Backends & Configuration, Plugin System, Enrichment & Embeddings, Known Issues, Limitations & Migration Notes

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

OCR Backends & Configuration

Related topics: Extraction Pipeline & Format Handlers, Known Issues, Limitations & Migration Notes

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

Language Bindings, FFI & Polyglot

Related topics: Workspace Layout & Crate Structure, Plugin System, Enrichment & Embeddings

Source: https://github.com/kreuzberg-dev/kreuzberg / Human Manual

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

high

Security or permission risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

Developers may fail before the first successful local run: bug: HF/ONNX model download fails behind corporate TLS-MITM — no custom CA support

medium

Installation risk requires verification

Developers may fail before the first successful local run: bug: kreuzberg maps PDF ligature glyphs to C0 control characters

medium

Installation risk requires verification

Developers may fail before the first successful local run: feat: support PaddleOCR-VL 1.6 and PP-OCRv6 models

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.