OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Pdfstract

Pdfstract is a Python document-preparation library for retrieval-augmented generation, with CLI, web UI and API interfaces for extracting content, chunking it and generating embeddings.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pdfstract — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pdfstract when a RAG or semantic-search workflow needs a configurable document-preparation stage before content is passed to a downstream system.

Who it is for

  • Developers preparing document content for RAG knowledge bases.
  • Teams building document-intelligence or semantic-search pipelines.
  • Python users who want to select among extraction, chunking and embedding components.

Documented uses

  • Convert documents into extracted text or structured output.
  • Split extracted text using token, semantic, sentence, recursive or other listed chunking methods.
  • Generate embeddings for chunks with a listed provider.
  • Process PDF files in batches or compare extraction libraries.
Before you choose

Requirements & limits

The project is open source under the Apache-2.0 license. The README documents pip installation and a locally started web UI and API.

  • Choose a package extra based on required dependencies: base, standard, advanced or all.
  • Select an embedding provider from the listed options, which include OpenAI, Azure OpenAI, Google, Ollama and Sentence Transformers.
  • The documented web UI setup requires cloning the repository and running make up.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start the documented local web UI and API

Launch the repository's web UI and API using its documented setup sequence.

Before you start

  • Git clone access and a local environment with the repository's documented make up workflow.

Steps

  1. Clone https://github.com/aksarav/pdfstract.git.

  2. Change into the pdfstract directory.

  3. Run the command below.

    Documented command
    make up

  4. Open the listed local UI at http://localhost:3000 or API at http://localhost:8000.

Expected outcome

The README identifies local addresses for the web UI and API after startup.

Guide limitations

  • The README does not specify further environment prerequisites for this setup sequence.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
PdfstractConvert documents into extracted text or structured output.CLI, Server, WebThe project is open source under the Apache-2.0 license. The README documents pip installation and a locally started web UI and API.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
AKSarav/pdfstract · Official homepage title · retained in its source language
How we review sourcesSuggest a correction