Troubleshooting

This section describes common issues and how to solve them. Need help? Ask your question in our support forum. Standard, Enterprise, and Dedicated customers can also contact support for help.

Unable to pip install

Python 3.x uses pip3. Use the following commands in your terminal to install the latest version of the Pinecone
Python client:

pip3 install -U pinecone-client

Index creation error - missing spec parameter

Using the new API, creating an index requires passing appropriate values into the spec parameter. Without this spec parameter, the create_index method raises the following error:

TypeError: Pinecone.create_index() missing 1 required positional argument: 'spec'

For guidance on how to set this parameter, see Create a serverless index and Create a pod-based index.

Serverless index creation error - max serverless indexes

Each project is limited to 20 serverless indexes. Trying to create more than 20 serverless indexes in a project raises the following 403 (FORBIDDEN) error:

This project already contains 20 serverless indexes, the maximum per project. 
Delete any unused indexes and try again, or create a new project for more serverless indexes. 
For additional help, please contact [email protected].

Delete any unused serverless indexes in the project and try again, or create a new project to hold additional serverless indexes.

Also consider using namespaces to partition vectors of the same dimensionality within a single index. Namespaces can help speed up queries as well as comply with multi-tenancy requirements.

Serverless index connection errors

To connect to a serverless index, you must use an updated Pinecone client. Trying to connect to a serverless index with an outdated client will raise errors similar to one of the following:

Failed to resolve 'controller.us-west-2.pinecone.io'

controller.us-west-2-aws.pinecone.io not found

Request failed to reach Pinecone while calling https://controller.us-west-2.pinecone.io/actions/whoami

Upgrade to the latest Python or Node.js client and try again:

# Python
pip install pinecone-client --upgrade
# Node.js
npm install @pinecone-database/pinecone@latest

Slow uploads or high latencies

To minimize latency when accessing Pinecone:

  • Switch to a cloud environment. For example: EC2, GCE, Google Colab, GCP AI Platform Notebook, or SageMaker Notebook. If you experience slow uploads or high query latencies, it might be because you are accessing Pinecone from your home network.
  • Consider deploying your application in the same environment as your Pinecone service. For users on the Starter (free) plan, the environment is GCP US-West (Oregon).
  • See performance tuning for more tips.

High query latencies with batching

If you're batching queries, try reducing the number of queries per call to 1 query vector. You can make these calls in parallel and expect roughly the same performance as with batching.

Upsert throttling when using the gRPC client

It's possible to get write-throttled sooner when upserting using the gRPC index. If you see this often, then we recommend using a backoff algorithm while upserting.

Pods are full

ℹ️

Note

This guidance applies to pod-based indexes only. With serverless indexes, you don't configure any compute or storage resources. Instead, serverless indexes scale automatically based on usage.

There is a limit to how much vector data a single pod can hold. Create an index with more pods to hold more data. Estimate the right index configuration and scale your index to increase capacity.

If your metadata has high cardinality (e.g. you have unique values for every vector in a large index) the index will
take up more memory. This could result in the pods becoming full sooner than expected. Consider only indexing metadata to be
used for filtering
, and storing the rest in a separate key-value store.

See the Configure pod-based indexes for information on how to specify the number of pods for your index.

Security concerns

We work hard to earn and maintain trust by treating security and reliability as a cornerstone of our company and product. Pinecone is SOC 2 Type II compliant and GDPR-ready. See the Trust & Security page for more information. Contact us to report any security concerns.

CORS errors

When sending requests to Pinecone, you may receive the following error:

No 'Access-Control-Allow-Origin' header is present on the requested resource.

This error occurs in response to cross-origin requests. Most commonly, it occurs when a user is running a local web server with the hostname localhost, which Pinecone's Same Origin Policy (SOP) treats as distinct from the IP address of the local machine.

To resolve this issue, host your web server on an external server with a public IP address and DNS name entry.