https://github.com/Zipstack/unstract

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

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.

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!

• 8GB RAM (recommended)

• 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:

✅ ./run-platform.sh
✅ Now visit http://frontend.unstract.localhost in your browser
✅ 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.

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!

	Provider	Status
	OpenAI	✅ Working
	Google VertexAI, Gemini Pro	✅ Working
	Azure OpenAI	✅ Working
	Google PaLM	✅ Working
	Anyscale	✅ Working
	Mistral AI	✅ Working
	Anthropic	✅ Working
	Ollama	✅ Working
	Replicate	🗓️ Coming soon!

	Provider	Status
	Qdrant	✅ Working
	Weaviate	✅ Working
	Pinecone	✅ Working
	PostgreSQL	✅ Working
	Milvus	✅ Working

	Provider	Status
	OpenAI	✅ Working
	Azure OpenAI	✅ Working
	Google PaLM	✅ Working

	Provider	Status
	Unstract LLMWhisperer	✅ Working
	Unstructured.io Community	🗓️ Coming soon!
	Unstructured.io Enterprise	🗓️ Coming soon!
	LlamaIndex Parse	🗓️ Coming soon!

	Provider	Status
	AWS S3	✅ Working
	Minio	✅ Working
	Dropbox	✅ Working
	Google Drive	🗓️ Coming soon!
	Box	🗓️ Coming soon!
	Google Cloud Storage	🗓️ Coming soon!
	Azure Cloud Storage	🗓️ Coming soon!
	HTTP/HTTPS	🗓️ Coming soon!

	Provider	Status
	Snowflake	✅ Working
	Amazon Redshift	✅ Working
	Google Bigquery	✅ Working
	PostgreSQL	✅ Working
	MySQL	🗓️ Coming soon!
	MariaDB	🗓️ Coming soon!
	Microsoft SQL Server	🗓️ Coming soon!

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.

• On Slack, join great conversations around LLMs, their ecosystem and leveraging them to automate the previously unautomatable!
• Follow us on X/Twitter
• Follow us on LinkedIn

In full disclosure, Unstract integrates Posthog to track usage analytics. As you can inspect the relevant code here, we collect the minimum possible metrics. Posthog can be disabled if desired by setting REACT_APP_ENABLE_POSTHOG to false in the frontend's .env file.