Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Backport 8301 to 2.16 #8302

Closed
wants to merge 1 commit into from
Closed

Backport 8301 to 2.16 #8302

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions _tools/sycamore.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,23 +11,23 @@ has_children: false

To get started, visit the [Sycamore documentation](https://sycamore.readthedocs.io/en/stable/sycamore/get_started.html).

# Sycamore ETL pipeline structure
## Sycamore ETL pipeline structure

A Sycamore extract, transform, load (ETL) pipeline applies a series of transformations to a [DocSet](https://sycamore.readthedocs.io/en/stable/sycamore/get_started/concepts.html#docsets), which is a collection of documents and their constituent elements (for example, tables, blocks of text, or headers). At the end of the pipeline, the DocSet is loaded into OpenSearch vector and keyword indexes.

A typical pipeline for preparing unstructured data for vector or hybrid search in OpenSearch consists of the following steps:

* Read documents into a [DocSet](https://sycamore.readthedocs.io/en/stable/sycamore/get_started/concepts.html#docsets).
* [Partition documents](https://sycamore.readthedocs.io/en/stable/sycamore/transforms/partition.html) into structured JSON elements.
* Extract metadata, filter, and clean data using [transforms](https://sycamore.readthedocs.io/en/stable/sycamore/APIs/docset.html).
* Extract metadata and filter and clean data using [transforms](https://sycamore.readthedocs.io/en/stable/sycamore/APIs/docset.html).
* Create [chunks](https://sycamore.readthedocs.io/en/stable/sycamore/transforms/merge.html) from groups of elements.
* Embed the chunks using the model of your choice.
* [Load](https://sycamore.readthedocs.io/en/stable/sycamore/connectors/opensearch.html) the embeddings, metadata, and text into OpenSearch vector and keyword indexes.

For an example pipeline that uses this workflow, see [this notebook](https://github.com/aryn-ai/sycamore/blob/main/notebooks/opensearch_docs_etl.ipynb).


# Install Sycamore
## Install Sycamore

We recommend installing the Sycamore library using `pip`. The connector for OpenSearch can be specified and installed using extras. For example:

Expand All @@ -45,4 +45,4 @@ pip install sycamore-ai[opensearch,local-inference]

## Next steps

For more information, visit the [Sycamore documentation](https://sycamore.readthedocs.io/en/stable/sycamore/get_started.html).
For more information, visit the [Sycamore documentation](https://sycamore.readthedocs.io/en/stable/sycamore/get_started.html).
Loading