Managing indexes

Vector Databases for Embeddings with Pinecone

James Chapman

Curriculum Manager, DataCamp

Connecting to the index

pc = Pinecone(api_key="API_KEY")

pc.create_index(
    name='datacamp-index',
    dimension=1536,
    spec=ServerlessSpec(
        cloud='aws', 
        region='us-east-1'
    )
)


index = pc.Index('datacamp-index')

Connecting to the index

index = pc.Index('datacamp-first')

...
pinecone.core.client.exceptions.NotFoundException: (404)
Reason: Not Found
HTTP response headers: HTTPHeaderDict({'content-type': 'text/plain; charset=...
HTTP response body: {"error":{"code":"NOT_FOUND","message":"Resource datacamp-first
not found"},"status":404}

Index statistics

index.describe_index_stats()

{'dimension': 1536,
 'index_fullness': 0.0,
 'namespaces': {},
 'total_vector_count': 0}

Namespaces

Containers for partitioning indexes
- Separate datasets
- Data versioning
- Separate groups

Focus on the single namespace case for now

Indexes with several namespaces inside them.

Organizations

An organization containing two projects, each with their own indexes.

Organizations

A group of organization owners.

Permissions across entire org.
Manage billing, users, all projects

An owner with several users underneath them.

Restricted org-level permissions
Invited to specific projects
Become owner to those projects

Deleting indexes

pc.delete_index('datacamp-index')


pc.list_indexes()

{'indexes': []}

Let's practice!

Vector Databases for Embeddings with Pinecone