# ETL

## Explanation

ETL is the process of sourcing data from diverse origins, transforming it for usability, and loading it into a target system.

ETL stands for Extract, Transform and Load. These are the three main steps to convert/move from a data source to a target destination.

Here we are getting the documents from various different sources (Extract) and converting it into embeddings (transform) and finally loading it to a vector database (Load) . Hence this ETL process achieves the data loading part from a source to a vectordb destination.

**Our workflow diagram:**

<figure><img src="https://3806397856-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FeycDZ2xq9bBJ7YOeSLfc%2Fuploads%2Fgit-blob-2aaca1e7720fd61f55955f211756b755d92b786a%2Fimage.png?alt=media" alt=""><figcaption><p>Data Loaders Architecture Diagram</p></figcaption></figure>

### Supported Data Loaders:

Currently we support three ETL platforms , they are:

* Airbyte
* Llama Hub
* Langchain

You can use any one of these loaders to carry out the ETL process.


---

# 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://genaistack.aiplanet.com/components/etl.md?ask=<question>
```

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.