Destinations
Pinecone
Pinecone is a vector database that can be used as a source
or destination
within your mixpeek pipeline.
Setup connection
First we’ll need to create the pinecone connection, which returns a connection_id
we use that when we create the pipeline from S3 to Pinecone.
Python
from mixpeek import Mixpeek
mixpeek = Mixpeek('API_KEY')
connection_id = mixpeek.connections.create(
alias="my-pinecone",
engine="pinecone",
details={
"api_key": "your_api_key",
"environment": "your_environment",
"index_name": "your_index_name"
}
)
Create the pipeline
Assuming we already have our source connection_id ready, which if using S3 can be done here: S3 connection we can then map it in our Pipeline:
Python
pipeline_id = mixpeek.pipelines.create(
alias="MyPipeline",
code="function execute() { return true; }",
source={
"connection_id": "conn_456",
"filters": {
"foo": "bar"
}
},
destination={
"connection_id": "conn_431",
"namespace": "my_pinecone_namespace",
"metadata": {
"type": "storage"
}
}
)
Notice how we have a namespace key, this is where the data from the pipeline’s response will be sent.
Enable the pipeline
mixpeek.pipelines.enable(
pipeline_id="123",
enable=True
)
Once done, all S3 object changes will be sent to your Pinecone namespace: my_pinecone_namespace
.