diff --git a/docs/source/sycamore/tutorials/etl_for_opensearch.md b/docs/source/sycamore/tutorials/etl_for_opensearch.md index eced954a9..f6a94e4ef 100644 --- a/docs/source/sycamore/tutorials/etl_for_opensearch.md +++ b/docs/source/sycamore/tutorials/etl_for_opensearch.md @@ -1,4 +1,4 @@ -# ETL tutorial with Sycamore and OpenSearch +# Loading OpenSearch with Sycamore This tutorial provides a walkthrough of how to use Sycamore to extract, enrich, transform, and create vector embeddings from a PDF dataset in S3 and load it into OpenSearch. The way in which you run ETL on these document is critical for the end quality of your application, and you can easily use Sycamore to facilitate this. The example below shows a few transforms Sycamore can do in a pipeline, and how to use LLMs to extract information. diff --git a/docs/source/sycamore/tutorials/etl_for_weaviate_tutorial.md b/docs/source/sycamore/tutorials/etl_for_weaviate_tutorial.md index f6a12d71b..34ca96682 100644 --- a/docs/source/sycamore/tutorials/etl_for_weaviate_tutorial.md +++ b/docs/source/sycamore/tutorials/etl_for_weaviate_tutorial.md @@ -1,4 +1,4 @@ -# ETL tutorial with Sycamore and Weaviate +# Loading Weaviate with Sycamore [This tutorial](https://github.com/aryn-ai/sycamore/blob/main/notebooks/weaviate-writer.ipynb) shows how to create an ETL pipeline with Sycamore to load a Weaviate vector database. It walks through how to use Sycamore to partition, extract, clean, chunk, embed, and load your data. You will need an [Aryn Partitioning Service API key](https://www.aryn.ai/get-started) and an [OpenAI API key](https://platform.openai.com/signup) (for LLM-powered data enrichment and creating vector embeddings). At the time of writing, there are free trial or free tier options for all of these services. diff --git a/docs/source/sycamore/tutorials/etl_pinecone_tutorial.md b/docs/source/sycamore/tutorials/etl_pinecone_tutorial.md index d6bf3b4c4..47ce4f32f 100644 --- a/docs/source/sycamore/tutorials/etl_pinecone_tutorial.md +++ b/docs/source/sycamore/tutorials/etl_pinecone_tutorial.md @@ -1,4 +1,4 @@ -# ETL tutorial with Sycamore and Pinecone +# Loading Pinecone with Sycamore [This tutorial](https://colab.research.google.com/drive/1oWi50uqJafBDmLWNO4QFEbiotnU7o75B) is meant to show how to create an ETL pipeline with Sycamore to load a Pinecone vector database. It walks through an intermediate-level ETL flow: partitioning, extraction, cleaning, chunking, embedding, and loading. You will need an [Aryn Partitioning Service API key](https://www.aryn.ai/get-started), [OpenAI API key](https://platform.openai.com/signup) (for LLM-powered data enrichment and creating vector embeddings), and a [Pinecone API key](https://app.pinecone.io/?sessionType=signup) (for creating and using a vector index). At the time of writing, there are free trial or free tier options for all of these services.