Try chunk size and overlap on sample pages

Created by

Joshua White

Actor

Dataset to Pinecone & Qdrant Vector Export

Splits the sample pages into 150-character chunks with a 30-character overlap, so you can see where text is cut and how the overlap keeps sentences whole. Change the two numbers and run again; nothing is embedded.

Try for free

Dataset to Pinecone & Qdrant Vector Exportoldjard/dataset-to-pinecone-qdrant

Record ID

Chunk

Characters

+2 fields

Input

Chunk size (characters):150

Chunk overlap (characters):30

Output fields

Record ID

Chunk

Characters

Text to embed

Metadata

How it works

Sign up on Apify or log in

The Dataset to Pinecone & Qdrant Vector Export Actor is ready to run with the inputs already set for "Try chunk size and overlap on sample pages". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Try chunk size and overlap on sample pages" task

The Dataset to Pinecone & Qdrant Vector Export Actor will start running based on the input automatically. You can also change all the input fields, like chunk size (characters) and chunk overlap (characters), to match your specific use case.

Receive the "Try chunk size and overlap on sample pages" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as record id, chunk, of, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Try chunk size and overlap on sample pages" task via API.