Pinecone is tested on Python 3.6+.
We strongly recommend that you install Pinecone in a virtual environment. We think it’s good for Python hygiene. It’s really easy to start using virtual environments with one of these guides: , .
pip install pinecone-client
A neat feature of Pinecone is that you can visualize the graphical representations
of your Pinecone services. If you plan to use Pinecone in a Jupyter notebook,
you should install the graph visualization tool
graphviz in your operating system.
Throughout the documentation, we assume that you have
# OSX brew install graphviz # Debian sudo apt install graphviz # RPM sudo yum install graphviz # Windows winget install graphviz
Setting Up Pinecone¶
You will need a Pinecone API key for this step. If you haven’t received your API key, visit pinecone.io <https://www.pinecone.io/start/> to get started. You will receive an API key after registration.
The following command writes your Pinecone configurations to
pinecone init --api_key=YOUR_API_KEY
Alternatively, you can specify or override your API key when you import the Pinecone package:
import pinecone pinecone.init(api_key="YOUR_API_KEY")
import pinecone.graph import pinecone.service import pinecone.connector service_name="hello-pinecone" graph = pinecone.graph.IndexGraph() # create a graph graph.view() # view the graph pinecone.service.deploy(service_name, graph) # deploy the graph as a service conn = pinecone.connector.connect(service_name) # connect to the service conn.upsert(items=[("A", [1, 1, 1]), ("B", [1, 1, 1])]).collect() # insert vectors conn.query(queries=[[0,1,0]], top_k=5).collect() # query conn.info() # index info pinecone.service.stop(service_name=service_name) # stop the service