# Datanets
### **Create a datanet**
1. **Input Metadata**
2. Navigate to Model Datanets and select Create Datanet.
3. Enter the required metadata:
* Name
* Summary
* Description (supports markdown)
* Tags
4. Upload valid .md, .pdf, .txt and .docx files (maximum size: 5 MB, UTF-8 encoded for a submission).
5. Add relevant tags
6. Click Create to complete the process.
Upon creation, a draft Datanet is initialized and displayed.
### **Publish to Blockchain**
After creation, datanet contract should be created onchain with fee payment.
1. Review the uploaded files under **Unpublished Datanets,** uploaded files can be deleted before Publish to Blockchain.
2. Click **Publish to Blockchain**
3. Review the details:
* Datanet Name
* Your OPEN balance
* Deployment fee
4. Deployment fee is calculated based on the file size
5. Click **Confirm & Create** to initiate a wallet transaction
6. On success, the transaction hash is displayed and a confirmation popup appears.
1. On failure, an error modal appears (e.g., insufficient balance).
1. Files are parsed and datanet rows are generated using LLM, and all the generated rows are stored on-chain.
### **Review and Publish**
1. Datanet owners can review the datanet rows and delete any unwanted entries.
2. Once all the rows are onchain, datanet can be published.
1. Your Datanet is now live, reusable, and trainable to any AI models within OpenLedger.
### Datanet Versioning and Contributions
* **Metadata update:** Only **Summary**, **Description and Tags** can be edited after creation.
* **File update:** Uploading new files or modifying existing rows will create a new version and incur an applicable fee.
### Contributions
* Public Datanets allow file uploads via the **Contribute** button.
* The owner can **Approve** or **Reject** submissions.
* Approved submissions create a new on-chain version (e.g., AI\_Model\_V2).
* On approval, Datanet owners are charged deployment fees for the new versions.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://openledger.gitbook.io/openledger/product-walkthrough/datanets.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.