Skip to content

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

License

Notifications You must be signed in to change notification settings

smartground/unstract

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Unstract

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

pdm-managed CLA assistant pre-commit.ci status Quality Gate Status Bugs Code Smells Coverage Duplicated Lines (%)

πŸ€– Go beyond co-pilots

While co-pilots enable machine-to-human automation, with Unstract, you can go beyond co-pilots by enabling machine-to-machine automation. You can launch APIs that take in complex documents and return structured JSON all with a simple no-code approach. You can also launch unstructured data ETL Pipelines that can read complex documents from a variety of cloud file / object storage systems and write structured data into popular data warehouses and databases.

img Prompt Studio

πŸ§˜β€β™€οΈ Three step nirvana

Automate critical business processes that involve complex documents with a human in the loop. Go beyond RPA with the power of Large Language Models.

🌟 Step 1: Add documents to no-code Prompt Studio and do prompt engineering to extract required fields
🌟 Step 2: Configure Prompt Studio project as API deployment or configure input source and output destination for ETL Pipeline
🌟 Step 3: Deploy Workflows as unstructured data APIs or unstructured data ETL Pipelines!

img Using Unstract

πŸš€ Getting started

System Requirements

  • 8GB RAM (recommended)

Prerequisites

  • Linux or MacOS (Intel or M-series)
  • Docker
  • Docker Compose (if you need to install it separately)
  • Git

Next, either download a release or clone this repo and do the following:

βœ… ./run-platform.sh
βœ… Now visit http://frontend.unstract.localhost in your browser
βœ… Use user name and password unstract to login

That's all there is to it!

Another really quick way to experience Unstract is by signing up for our hosted version.

⏩ Quick Start Guide

Unstract comes well documented. You can get introduced to the basics of Unstract, and learn how to connect various systems like LLMs, Vector Databases, Embedding Models and Text Extractors to it. The easiest way to wet your feet is to go through our Quick Start Guide where you actually get to do some prompt engineering in Prompt Studio and launch an API to structure varied credit card statements!

🀝 Ecosystem support

LLM Providers

Provider Status
OpenAI βœ… Working
Google VertexAI, Gemini Pro βœ… Working
Azure OpenAI βœ… Working
Google PaLM βœ… Working
Anyscale βœ… Working
Mistral AI βœ… Working
Anthropic βœ… Working
Ollama βœ… Working
Replicate πŸ—“οΈ Coming soon!

Vector Databases

Provider Status
Qdrant βœ… Working
Weaviate βœ… Working
Pinecone βœ… Working
PostgreSQL βœ… Working
Milvus πŸ—“οΈ Coming soon!

Embeddings

Provider Status
OpenAI βœ… Working
Azure OpenAI βœ… Working
Google PaLM βœ… Working

Text Extractors

Provider Status
Unstract LLMWhisperer βœ… Working
Unstructured.io Community πŸ—“οΈ Coming soon!
Unstructured.io Enterprise πŸ—“οΈ Coming soon!
LlamaIndex Parse πŸ—“οΈ Coming soon!

ETL Sources

Provider Status
AWS S3 βœ… Working
Minio βœ… Working
Dropbox βœ… Working
Google Drive πŸ—“οΈ Coming soon!
Box πŸ—“οΈ Coming soon!
Google Cloud Storage πŸ—“οΈ Coming soon!
Azure Cloud Storage πŸ—“οΈ Coming soon!
HTTP/HTTPS πŸ—“οΈ Coming soon!

ETL Destinations

Provider Status
Snowflake βœ… Working
Amazon Redshift βœ… Working
Google Bigquery βœ… Working
PostgreSQL βœ… Working
MySQL πŸ—“οΈ Coming soon!
MariaDB πŸ—“οΈ Coming soon!
Microsoft SQL Server πŸ—“οΈ Coming soon!

πŸ™Œ Contributing

Contributions are welcome! Please read CONTRIBUTE.md for further details on setting up the development environment, etc. It also points you to other detailed documents as needed.

πŸ‘‹ Join the LLM-powered automation community

πŸ“Š A note on analytics

In full disclosure, Unstract integrates Posthog to track usage analytics. As you can inspect the relevant code here, we collect the minimum possible metrics.

About

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 66.5%
  • JavaScript 29.2%
  • CSS 2.3%
  • Shell 1.2%
  • Other 0.8%