Skip to main content

​
Organization

An organization is a group of one or more projects that use the same billing. Organizations allow one or more users to control billing and permissions for all of the projects belonging to the organization. For more information, see Understanding organizations.

​
Project

A project belongs to an organization and contains one or more indexes. Each project belongs to exactly one organization, but only users who belong to the project can access the indexes in that project. API keys and Assistants are project-specific. For more information, see Understanding projects.

​
Index

There are two types of serverless indexes, dense and sparse.

​
Dense index

Dense indexes store records that have one dense vector each.
If any records in a dense index also have a sparse vector, the index is a hybrid index.
A dense vector is a series of numbers that represent the meaning and relationships of text, images, or other types of data. Each number in a dense vector corresponds to a point in a multidimensional space. Vectors that are closer together in that space are semantically similar. When you query a dense index, Pinecone retrieves records containing dense vectors that are most semantically similar to the query. This is often called semantic search, nearest neighbor search, similarity search, or just vector search.

​
Sparse index

Sparse indexes store records that have one sparse vector each. Every sparse vector is a series of numbers that represent the words or phrases in a document. Sparse vectors have a very large number of dimensions, where only a small proportion of values are non-zero. The dimensions represent words from a dictionary, and the values represent the importance of these words in the document. When you search a sparse index, Pinecone retrieves the records with sparse vectors that most exactly match the words or phrases in the query. Query terms are scored independently and then summed, with records that have the most similar vectors scored highest. This is often called lexical search or keyword search.

​
Namespace

A namespace is a partition within a dense or sparse index. It divides records in an index into separate groups. All upserts, queries, and other data operations always target one namespace: For more information, see Use namespaces.

​
Record

A record is a basic unit of data and consists of a record ID, a dense vector or a sparse vector (depending on the type of index), and optional metadata. For more information, see Upsert data.

​
Record ID

A record ID is a record’s unique ID. Use ID prefixes that reflect the type of data you’re storing.

​
Dense vector

A dense vector, also referred to as a vector embedding or simply a vector, is a series of numbers that represent the meaning and relationships of data. Each number in a dense vector corresponds to a point in a multidimensional space. Vectors that are closer together in that space are semantically similar. Dense vectors are stored in dense indexes. You use a dense embedding model to convert data to dense vectors. The embedding model can be external to Pinecone or hosted on Pinecone infrastructure and integrated with an index. For more information about dense vectors, see What are vector embeddings?.

​
Sparse vector

Sparse vectors are often used to represent documents or queries in a way that captures keyword information. Each dimension in a sparse vector typically represents a word from a dictionary, and the non-zero values represent the importance of these words in the document. Sparse vectors have a large number of dimensions, but a small number of those values are non-zero. Because most values are zero, Pinecone stores sparse vectors efficiently by keeping only the non-zero values along with their corresponding indices. Sparse vectors are stored in sparse indexes and hybrid indexes. To convert data to sparse vectors, use a sparse embedding model. The embedding model can be external to Pinecone or hosted on Pinecone infrastructure and integrated with an index. For more information about sparse vectors, see Sparse retrieval.

​
Metadata

Metadata is additional information included in a record to provide more context and enable additional filtering capabilities. For example, the original text that was embedded can be stored in the metadata.

​
Other concepts

Although not represented in the diagram above, Pinecone also contains the following concepts:

​
API key

An API key is a unique token that authenticates and authorizes access to the Pinecone APIs. API keys are project-specific.

​
User

A user is a member of organizations and projects. Users are assigned specific roles at the organization and project levels that determine the user’s permissions in the Pinecone console. For more information, see Manage organization members and Manage project members.

​
Backup or collection

A backup is a static copy of a serverless index. Backups only consume storage. They are non-queryable representations of a set of records. You can create a backup from an index, and you can create a new index from that backup. The new index configuration can differ from the original source index: for example, it can have a different name. However, it must have the same number of dimensions and similarity metric as the source index. For more information, see Understanding backups.

​
Pinecone Inference

Pinecone Inference is an API service that provides access to embedding models and reranking models hosted on Pinecone’s infrastructure.

​
Learn more