pinecone-client
python library connect to a pinecone environment.
The required arguments to establish a connection are:
api_key
: the API key that can be found in your pinecone accountenvironment
: the environment name corresponding to the api_key
CREATE
statements:
dimension
: dimensions of the vectors to be stored in the index (default=8)metric
: distance metric to be used for similarity search (default=‘cosine’)pods
: number of pods for the index to use, including replicas (default=1)replicas
: the number of replicas. replicas duplicate your index. they provide higher availability and throughput (default=1)pod_type
: the type of pod to use, refer to pinecone documentation (default=‘p1’)DROP TABLE
supportcontent
column is not supported since it does not exist in Pineconetemp
in the following examples) based on id
or search_vector
, but not both:
id
or metadata
like so: