AnnouncementPinecone serverless on AWS is now generally availableLearn more
Models

text-embedding-ada-002

Popular, good-performing text embedding model accessible via API.
Dimension:Size of a single vector
supported by this model.
1536
Distance Metric:Used to measure similarity
between vectors.
cosine or dot product
Max Seq. Length:Number of tokens the model
can process at once.
8192

Overview

Ideal for easy to use text embeddings. All round performance for variety of use-cases and handles messy data well. Can handle large passages of text but we recommend length of 300-500 tokens for best performance. Very common in RAG pipelines. See here for example.

Using the model

Installation:

Creating Embeddings:

Learn how vector databases work