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

Uniflow

Uniflow is an open-source Python library that uses a unified LLM interface to extract text from PDFs, HTML and TXT files and transform or cluster that text for downstream work.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Uniflow — 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 Uniflow when document content needs to be extracted and shaped into material for downstream machine-learning workflows, such as fine-tuning datasets.

Who it is for

  • Data scientists preparing document-derived material for LLM fine-tuning.
  • Developers building document extraction and text transformation into Python workflows.

Documented uses

  • Extract text from PDF, HTML and TXT documents.
  • Transform extracted text into summaries or question-and-answer datasets.
  • Cluster processed document text.
Before you choose

Requirements & limits

The repository identifies Uniflow as open source under the Apache-2.0 license.

  • The documented input types are PDF, HTML and TXT.
  • The chosen model configuration determines provider-specific setup; OpenAI flows need an API key.
  • The documented base installation requires Python 3.10 and PyTorch, with the PyTorch choice depending on CPU or GPU use.

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

Install Uniflow in a Python 3.10 environment

Prepare the documented base environment and install the library.

Before you start

  • Conda
  • Python 3.10
  • PyTorch installed for the CPU or GPU setup

Steps

  1. Create and activate a Conda environment with Python 3.10.

  2. Install PyTorch; use the CPU installation or select a GPU build suited to the CUDA version.

  3. Install Uniflow with pip3.

Expected outcome

The documented base installation is in place.

Guide limitations

  • This covers installation only, not running a particular extraction or transformation flow.
  • OpenAI flows additionally require an API key; Hugging Face and LMQG flows have separate optional package requirements.
Documentation 1 ↗
Evidence and transparency

Sources & review

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