# June 2024 Product Update

> This month, we launched Pinecone Assistant in beta and many other new features. Watch our latest Quarterly Pinecone Summary (QPS) for product highlights in Q2 and also get a glimpse into our Q3 roadmap.

Xian Huang · 2024-07-01

This month, we launched [Pinecone Assistant](https://www.pinecone.io/blog/pinecone-assistant/) in beta and many other new features. Learn more below and in our monthly [release notes](https://docs.pinecone.io/release-notes/2024). Want to refresh your memory about our product highlights in Q2? Watch our latest [Quarterly Pinecone Summary (QPS)](https://www.youtube.com/watch?v=Hh6fdOp0BhE) and also get a glimpse into our Q3 roadmap.

## Pinecone Assistant - now in beta

[Pinecone Assistant](https://www.pinecone.io/blog/pinecone-assistant/) — an API service for accurately and securely answering complex questions about your proprietary data within your applications — [is now available](https://www.pinecone.io/product/pinecone-assistant/) for developers to try and share feedback in beta. [Join the waitlist](https://www.pinecone.io/product/pinecone-assistant/) for access to Pinecone Assistant during the beta period.

![Pinecone Assistant](https://cdn.sanity.io/images/vr8gru94/production/1c331be8d61a377bb9f58f191bed2ed3b567647f-1920x1080.gif)


With Pinecone Assistant you get:

- Simplicity: Just add your files and start building your killer AI app using [the API](https://docs.pinecone.io/guides/assistant/understanding-assistant).
- [High-quality](https://www.pinecone.io/blog/ai-assistant-quality/) results: Relevant answers grounded in your data, with references.
- Full control over your data: Your uploaded files help generate useful answers without training the model, and you can easily and permanently remove data.

## Serverless namespace quota doubled to support massive multitenancy

The Enterprise [quota for namespaces per serverless index](https://docs.pinecone.io/reference/quotas-and-limits#namespaces-per-serverless-index) has doubled to 100,000. You can use one [namespace](https://docs.pinecone.io/guides/indexes/use-namespaces) per tenant to build a [multitenant](https://www.pinecone.io/learn/series/vector-databases-in-production-for-busy-engineers/vector-database-multi-tenancy/) solution. Namespaces allow you to physically partition records in an index. Queries and other operations are then limited to one namespace at a time, leading to faster response times and reduced costs.

## Streamline your workflow with the revamped Model Gallery and new sample apps

When building GenAI apps, picking the best model can be challenging. With our revamped [Model Gallery](https://docs.pinecone.io/models/overview), you can view the details of a curated list of popular models (both open-source and proprietary), choose one that fits your needs, and create an index in Pinecone with just two clicks.

[Video](https://www.youtube.com/watch?v=sCXpFSaJXPk)


And with our [sample apps](https://docs.pinecone.io/examples/sample-apps), you can have an end to end application up and running in minutes. Use one npx command line npx create-pinecone-app to clone and set up the project locally and then tailor it to your own purposes. Try our latest [Legal semantic search](https://docs.pinecone.io/examples/sample-apps/legal-semantic-search) sample app and build your own semantic search apps.

[Video](https://www.youtube.com/watch?v=7FCTKbq47sY)


Check out the [release notes](https://docs.pinecone.io/release-notes/2024) for a running list of all product and feature releases. If you’re new to Pinecone, [try it out](https://app.pinecone.io/) for free today.