Skip to main content
When you create a Pinecone index, you choose a name, the cloud region where it’s hosted, a similarity metric for dense vectors, and, for integrated embedding, a hosted embedding model. To index only the metadata fields you filter on, rather than all of them, see Configure metadata indexing.

​
Index names

An index name must be unique within its project and 1 to 45 characters long. It can contain only lowercase letters, numbers, and hyphens (-), and it must start and end with a letter or number.

​
Cloud regions

When creating an index, you must choose the cloud and region where you want the index to be hosted. The following table lists the available public clouds and regions and the plans that support them: The cloud and region can’t be changed after a serverless index is created.
On the Starter plan, you can create serverless indexes in the us-east-1 region of AWS only. To create indexes in other regions, upgrade to the Builder, Standard, or Enterprise plan.

​
Similarity metrics

When creating an index that stores dense vectors, you can choose from the following similarity metrics. For the most accurate results, choose the similarity metric used to train the embedding model for your vectors. For more information, see Vector Similarity Explained.
Indexes that store sparse vectors must use the dotproduct metric.
Querying indexes with this metric returns a similarity score equal to the squared Euclidean distance between the result and query vectors.This metric calculates the square of the distance between two data points in a plane. It’s one of the most commonly used distance metrics. For an example, see the IT threat detection example.When you use metric='euclidean', the most similar results are those with the lowest similarity score.
This is often used to find similarities between different documents. The advantage is that the scores are normalized to [-1,1] range. For an example, see the generative question answering example.
This multiplies two vectors to measure how similar they are. The more positive the result, the closer the two vectors are in direction. For an example, see the semantic search example.

​
Embedding models

Dense vectors and sparse vectors are the basic units of data in Pinecone and what Pinecone was specially designed to store and work with. Dense vectors represent the semantics of data such as text, images, and audio recordings, while sparse vectors represent documents or queries in a way that captures keyword information. To transform data into vector format, you use an embedding model. Pinecone hosts several embedding models so it’s easy to manage your vector storage and search process on a single platform. You can use a hosted model to embed your data as an integrated part of upserting and querying, or you can use a hosted model to embed your data as a standalone operation. The following embedding models are hosted by Pinecone.
To understand how cost is calculated for embedding, see Embedding cost. To get model details via the API, see List models and Describe a model.

​
multilingual-e5-large

multilingual-e5-large is an efficient dense embedding model trained on a mixture of multilingual datasets. It works well on messy data and short queries expected to return medium-length passages of text (1-2 paragraphs). Details
  • Vector type: Dense
  • Modality: Text
  • Dimension: 1024
  • Recommended similarity metric: Cosine
  • Max sequence length: 507 tokens
  • Max batch size: 96 sequences
For rate limits, see Embedding tokens per minute and Embedding tokens per month. Parameters The multilingual-e5-large model supports the following parameters:

​
llama-text-embed-v2

llama-text-embed-v2 is a high-performance dense embedding model optimized for text retrieval and ranking tasks. It’s trained on a diverse range of text corpora and provides strong performance on longer passages and structured documents. Details
  • Vector type: Dense
  • Modality: Text
  • Dimension: 1024 (default), 2048, 768, 512, 384
  • Recommended similarity metric: Cosine
  • Max sequence length: 2048 tokens
  • Max batch size: 96 sequences
For rate limits, see Embedding tokens per minute and Embedding tokens per month. Parameters The llama-text-embed-v2 model supports the following parameters:

​
pinecone-sparse-english-v0

pinecone-sparse-english-v0 is a sparse embedding model for converting text to sparse vectors for sparse-vector search or hybrid search. Built on the innovations of the DeepImpact architecture, the model directly estimates the lexical importance of tokens by using their context, unlike traditional retrieval models like BM25, which rely solely on term frequency. Details
  • Vector type: Sparse
  • Modality: Text
  • Recommended similarity metric: Dotproduct
  • Max sequence length: 512 or 2048
  • Max batch size: 96 sequences
For rate limits, see Embedding tokens per minute and Embedding tokens per month. Parameters The pinecone-sparse-english-v0 model supports the following parameters: