OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Text Extract API

Text Extract API is a self-hostable Python service for extracting content from images, PDFs and Office documents into Markdown text or structured JSON. It combines OCR strategies and Ollama-supported models with a FastAPI API, Celery task processing and Redis caching; its examples also cover removing personally identifiable information from documents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Text Extract API — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you need a self-hosted document-processing component that can accept common office and image formats and produce Markdown or structured JSON for later workflows.

Who it is for

  • Developers building document-ingestion workflows that need Markdown or JSON output.
  • Teams processing document collections with OCR and asynchronous task handling.
  • Operators who want to run document processing in their own development or server environment.

Documented uses

  • Extract text, tables, numbers and formulas from images, PDFs and Office files.
  • Convert document content into Markdown for downstream search or knowledge workflows.
  • Turn PDF or Office content into structured JSON using Ollama-supported models.
  • Apply an example prompt for removing personally identifiable information.
  • Submit processing tasks through the included CLI.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. Its README documents Docker-based and local development setup paths; no account or pricing details are given.

  • The README identifies EasyOCR, MiniCPM-V and Ollama-supported models among the available OCR or model approaches.
  • The README describes processing without cloud or external dependencies in its Docker Compose configuration, with data remaining in the development or server environment.
  • Celery handles asynchronous tasks and Redis caches OCR results before LLM processing.
  • Storage strategies are switchable, with local filesystem and Google Drive listed as examples.
  • Docker is not described as supporting Apple GPUs; the README suggests direct local execution for that use case.

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

Set up Text Extract API with Docker

Prepare the documented Docker environment for the API.

Before you start

  • Docker
  • Docker Compose

Steps

  1. Clone the repository and change into its directory.

  2. Create a root .env file by copying .env.example or .env.example.localhost.

  3. Modify the environment variables as needed.

  4. Use the command below and the command below to set up and run the Docker environment.

    Documented command
    make install
    Documented command
    make run

Expected outcome

The README's Docker setup procedure prepares the API environment for use.

Guide limitations

  • The documented DISABLE_LOCAL_OLLAMA setting cannot disable Ollama in Docker; the README describes removing its service from the Compose file as a workaround.
  • These are repository instructions, not an independently verified deployment.
Documentation 1 ↗
Source-based practical guide

Run an example extraction from a local setup

Use the documented CLI example to submit an example PDF for OCR and PII removal.

Before you start

  • A cloned repository
  • Ollama and Docker installed
  • A configured local environment and running API dependencies
  • The README's example files

Steps

  1. Follow the README's local setup instructions, including creating the Python virtual environment and installing the project.

  2. Start the Celery worker as shown in the README for Mac setups.

  3. Run the command below.

    Documented command
    python client/cli.py ocr_upload --file examples/example-mri.pdf --ocr_cache --prompt_file=examples/example-mri-remove-pii.txt

Expected outcome

The documented CLI command submits the MRI PDF example for OCR with caching and a PII-removal prompt.

Guide limitations

  • The README says Redis is installed via Docker even in the manual local setup.
  • The recipe reflects documented commands and is not a report of a successful execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
CatchTheTornado/text-extract-api · Official homepage title · retained in its source language
How we review sourcesSuggest a correction