PDFStract
PDFStract is a data preparation layer for RAG pipelines. It is built to take PDF documents through extraction, chunking, and embedding so they become vector-ready in one command. The page describes it as the first layer in a RAG pipeline and as a tool for AI applications.
Its conversion step uses 10+ libraries, including Marker, Docling, and PyMuPDF4LLM, with each library described as optimized for different document types. For text splitting, it offers 10+ chunking methods ranging from simple token-based approaches to advanced semantic chunking powered by AI. It also generates vector embeddings with multiple providers, including OpenAI, Sentence Transformers, and local models. The interface is described as a unified API, and switching between libraries, chunkers, and embedding providers is done by changing a single parameter.
PDFStract is delivered through a Python API, a CLI, and a Web UI. The CLI example shown on the page uses a convert-chunk-embed command. The site also links to documentation, installation, features, GitHub, PyPI, and guides for the Python API, CLI, and Web UI. It is available under the MIT license.
Open SourceApache-2.0WebEmbeddableCLIAPICloud-managed
151stars
13forks
10features
2025since
Overview
10 featuresIn the RAG, search & retrieval space, PDFStract takes a focused approach. It focuses on preparing and converting PDF documents into vector-ready data for retrieval-augmented generation pipelines. It is built as an open-source project for AI developers and data engineers. PDFStract is open source under the Apache-2.0 license. It ships for the web, embeddable surfaces, the command line, and API.
PDFStract builds and maintains PDFStract, and it first shipped in 2025. The project is developed in the open on GitHub with 151 stars. Among its 10 catalogued features are PDF extraction, text chunking, and vector embeddings. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
- PDF extraction
- Text chunking
- Vector embeddings
- Multiple libraries
- Semantic chunking
- Python API
- CLI interface
- Web UI
- Open source
- Multi-provider support
Tags
pdf-extractionrag-pipelinesemantic-chunkingembedding-providervectorization
AI capabilities
Text
Inference: Hybrid
Built with & integrations
Framework
FastAPI
Hosting
NetlifyCloudflare
AI providers
openaimultiple
Connectors
API
Runs on
BrowserEmbeddableCLIAPI-onlyCloud-managed
Detected from
- Netlify
- x-nf-request-id header
- Cloudflare
- cf-ray header · cf-cache-status header
Trust & compliance
License
Apache-2.0
Verified signals
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about PDFStract
- What does PDFStract do?
- PDFStract focuses on preparing and converting PDF documents into vector-ready data for retrieval-augmented generation pipelines. It is catalogued under RAG, search & retrieval on PulseGate.
- Who is PDFStract for?
- PDFStract is an open-source project built for AI developers and data engineers.
- Is PDFStract free?
- Yes — PDFStract is open source under the Apache-2.0 license and free to use.
- What platforms does PDFStract run on?
- PDFStract runs on the web, embeddable surfaces, the command line, and API.
- Is PDFStract still maintained?
- Unverified. PDFStract has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
- Who develops PDFStract?
- PDFStract is developed by PDFStract.
- When did PDFStract launch?
- PDFStract first shipped in 2025.
- Is PDFStract open source?
- Yes — PDFStract is open source under the Apache-2.0 license, developed on GitHub.
Similar projects
Closest matches by what these projects do