Hi,
I am trying out pinecone via the LlamaIndex example here: Using Vector Stores — LlamaIndex documentation
This is the pythong code:
pinecone.init(api_key=api_key, environment="eu-west1-gcp")
pinecone.create_index("quickstart", dimension=1536, metric="euclidean", pod_type="p1")
the error I get is:
pinecone.core.client.exceptions.ApiException: (400)
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({‘content-type’: ‘text/plain; charset=UTF-8’, ‘date’: ‘Fri, 31 Mar 2023 11:56:54 GMT’, ‘x-envoy-upstream-service-time’: ‘518’, ‘content-length’: ‘131’, ‘server’: ‘envoy’})
HTTP response body: The index exceeds the project quota of 1 pods by 1 pods. Upgrade your account or change the project settings to increase the quota.
Can anyone help shed some light on this?
Hi @thompsonson,
If you’re on the free tier you’re limited to having one pod running at a time. So if you already have an index, you’ll need to delete that first before creating a new one.
If you want to keep both indexes running you can upgrade your plan in the console. Just click Organization then Billing.
thanks, that seems obvious now 
Hi Cory, I received same error so I deleted out my old index just leaving 1 new index i created. i still receive this same error though. How do i resolve?
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({‘content-type’: ‘text/plain; charset=UTF-8’, ‘date’: ‘Thu, 04 May 2023 15:50:38 GMT’, ‘x-envoy-upstream-service-time’: ‘1107’, ‘content-length’: ‘131’, ‘server’: ‘envoy’})
HTTP response body: The index exceeds the project quota of 1 pods by 1 pods. Upgrade your account or change the project settings to increase the quota.
I had to delete it - then it worked. On the free version, you can only have one instance.