Pinecone Integration
Pricing
Pay per usage
Pinecone Integration
This integration transfers data from Apify Actors to a Pinecone and is a good starting point for a question-answering, search, or RAG use case.
Pricing
Pay per usage
Monthly users
99
Runs succeeded
96%
Response time
24 days
Last modified
10 days ago
Setting up the Pinecone Namespace
How do I set the Pinecone Namespace?
Thank you for the interested in the Pinecone integration. The namespace parameter is not exposed at the moment, but I will release it tomorrow (Friday, the 6th). Please let me know if there's anything else you'd like to see added.
Here's the revised version of your message:
Hi, in the latest build, I’ve added the option to select a Pinecone namespace using the pineconeIndexNamespace parameter. This parameter is optional:
1{ 2 "pineconeApiKey": "....", 3 "pineconeIndexName": "....", 4 "pineconeIndexNamespace": "ns1" 5}
I’m closing this issue now. Please let me know if there’s anything else I can help with.
sprouto_net
Thanks for the quick revert. However, we would need this pineconeIndexNamespace to be parametrized. So basically, when we send the URL for crawling to the website content crawler, we would send the "AccountID" of the user for whom we would want to crawl this website. This parameter of "AccountID" would be passed on to the pinecone and thus all the crawled data would be saved for this user in the same namespace. This way we can keep crawl data of one user separate from another.
So basically, we just want to send a parameter to website crawler in any available field and that should be passed as parameter to our pinecone integration. This is just same like how we are passing the URL as a parameter.
Ok, I understand your requirement. I'm not sure how you're executing the website content crawler, but I assume that if you want it to be parameterized, you’re calling the website content crawler via API or SDK (JavaScript, Python).
Here’s a simple example of how you can achieve this in Python:
- Call the website content crawler:
1actor_call = client.actor("apify/website-content-crawler").call( 2 run_input={"startUrls": [{"url": "https://docs.pinecone.io/home"}]} 3)
- After the website content crawl finishes, call the Pinecone integration:
1pinecone_integration_inputs = { 2 "pineconeApiKey": PINECONE_API_KEY, 3 "pineconeIndexName": PINECONE_INDEX_NAME, 4 "pineconeIndexNamespace": "AccountID", 5 "datasetId": actor_call["defaultDatasetId"], 6} 7 8actor_call = client.actor("apify/pinecone-integration").call(run_input=pinecone_integration_inputs)
Do you plan to execute it in any other way? From the console.apify.com?
Pricing
Pricing model
Pay per usageThis Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage.
