Astra DB Reviews & Insights

Maester leverages Astra DB’s advanced vector search and retrieval capabilities to create an adaptive AI system that continuously refines its responses based on real-world user interactions. Maester also relies on Astra’s performance for semantic clustering. Maester can suggest relevant prompts and related analyses by grouping semantically similar user queries. This approach improves user experience and drives feature adoption, highlighting capabilities such as advanced forecasting and custom financial reporting.

We've been super happy with Astra DB. It's been extremely well-suited for our vector search needs as described in previous responses. With Astra DB’s high-performance vector search, Maester’s AI dynamically optimizes responses in real-time, adapting to new user interactions without requiring costly retraining cycles.

We use Astra DB to enable our Graph Database functionality. This graph database is the core of our e-commerce delivery planning and execution systems. This system enables the business to provide accurate ETAs to customers. It also enables the business to grow our national delivery network simply via configuration. Routes and their capabilities are individually configured to account for the network capacity and courier capabilities around different geographic areas.

Anyone looking for a hosted solution of Cassandra DB will find a good offering with AstraDB. It provides the scalability of Cassandra with added security, permissions and visibility. As a user you forget there is a cluster behind the scenes.

Astra DB had helped us in building our indigenous algo for social audio consumption for one of the most dynamic digital consumption markets in the entire world. We started with a problem statement that did not have an existing inspiration and hence it was as as abstract it can get. Astra DB helped us quickly get into a solid ground

The vector database offering from Astra DB forms the core of our algorithm and the computational speed is satisfying for our current, low scale. Will be happy to reccomend if the speed can be witnessed when we grow to 10X of the current scale

We use Astra DB as the database for our OB3 web application, which is used by Higher Education organisations and Universities in Australia and New Zealand. It is therefore one of the core technologies we and our customers rely on for delivery of our service. Our product brings course content and discussions together in online collaborative documents, to enable teacher-led and student-led learning activities. It is delivered integrated with enterprise learning management systems such as Canvas and Blackboard.

We are coming to Astra DB from a background of having used and relied on Cassandra (open source) database for over 10 years. Our use case is particularly well suited to NoSQL. We selected Datastax Astra primarily for scalability, support, contingency planning, and reducing the technical complexity of our operations. We were looking for a reliable partner with strong presence in our region (APAC) and we are confident we've found this in Datastax.

For vector search capabilities where you need some powerful querying capability like CQL, Astra DB is the solution. Also Astra DB suits well where someone wants to build a RAG setup. Its cloud-native design and distributed architecture make Astra DB a great fit for companies operating across multiple regions or requiring high availability.

Astra DB helps us in some of our RAG solutions. At this moment, we have a chatbot SAAS application with more than 55.000 users and they can use a wide variety of documents in their chat. We use the Astra DB solution to help us power all the features related to this topic.

If you want to develop complex AI solutions that use RAG as part of its core, Astra DB is a really good choice. Also, if you have an application used by a relevant number of users and some seconds on I/O matters to you, Astra DB will also suits very well.

If you are just starting, building a very small MVP, maybe there are better solutions for you,

To enhance productivity and significantly boost our win ratio for building successful proposals, we aim to implement a system that provides highly contextual retrieval of relevant information from our extensive archive. This archive includes tens of thousands of proposals, Statements of Work (SOW), case studies, and pitches stored in SharePoint. By leveraging this system, we can quickly access pertinent data, enabling us to craft more competitive and informed proposals.

Easy to use and available across different hyper scalers.

We mainly use Astra DB Vector databases for our internal and customer support chatbots. The internal chatbot uses a database with more critical data and is therefore, separated from the customer facing chatbot.

Especially the personal customer support over Slack is very helpful and this why I would always recommend Astra DB to anyone starting with RAG and LLMs.

We have used Astra DB as our database for university class.During the semester we had multiple assignments that required us to make multiple data manipulation using many read and write calls to the db. We had no issue and the performance was satisfactory. I would reccomend Astra DB to anyone who wants to try a solid database to work with.

For class assignments it is doing the job very well

When our engineering team started developing ChatStack, we needed a backend solution that could meet all our requirements within our budget constraints. DataStax was the right fit.Their platform enabled seamless deployment across multiple clouds, ensuring ChatStack would operate smoothly as we scaled up users. Performance remained consistently fast even with substantial user growth, thanks to DataStax's low latency capabilities.Onboarding with the DataStax team was straightforward. Their engineering expertise allowed simple integration for our developers. Having their support significantly reduced deployment stress and provided valuable learning opportunities.Additionally, DataStax integrated well with our existing tools, avoiding a full stack rebuild. Their pay-as-you-go pricing delivered cost-effective scaling by eliminating the overhead of managing our own servers.In summary, DataStax provided the robust, flexible solution essential for launching ChatStack on time and on budget. Their technology and engineering knowledge were instrumental in delivering our product within constraints. We highly recommend DataStax to engineering teams needing a reliable, scalable backend platform. Our developers were satisfied with the seamless integration into our stack.

Astra DB works well for cloud-native applications needing highly scalable and resilient data storage with millisecond response times but is less ideal for situations requiring advanced SQL functionality or total control over the infrastructure.