Reviews from AWS Marketplace
0 AWS reviews
-
5 star0
-
4 star0
-
3 star0
-
2 star0
-
1 star0
External reviews
External reviews are not included in the AWS star rating for the product.
The worst customer service experience when you're having any form of issue
What do you like best about the product?
the initial setup is genuinely quite easy
What do you dislike about the product?
We had an issue where our data corrupted and weaviate became entirely useless, retrieving different data at each request. During this time, weaviate took a day to respond each time, consistently shifting the blame onto us and not resolving the issue. There is no way you can help yourself as the actual management console is incredibly barebones. We had to move away from weaviate as the other two options were negotiating with support (which is a painful process when the blame is entirely shifted on you at all times) or using the control panel (which is incredibly barebones - there is not even a way of turning off your instance). Again, if you have an issue, do not expect to ever be able to resolve it.
What problems is the product solving and how is that benefiting you?
Weaviate can be used to run vector queries on data...when it works.
- Leave a Comment |
- Mark review as helpful
Empowering AI with Versatility
What do you like best about the product?
Weaviate proves to be user-friendly, with a well-designed interface that facilitates easy navigation. The platform's intuitive nature makes it accessible for both beginners and experienced users. Weaviate's customer support is responsive and helpful. The support team is quick to address queries, and the community forums provide an additional resource for collaborative problem-solving. It becomes an integral part of our workflow, especially for projects that demand advanced AI capabilities. Its reliability and consistent performance contribute to its frequent use in our AI development projects. The platform's flexibility ensures compatibility with a wide range of applications and use cases. The implementation process is smooth.
What do you dislike about the product?
While Weaviate excels in many aspects, there's room for improvement in terms of documentation clarity. Some aspects of implementation might be clearer with more detailed examples and use cases.
What problems is the product solving and how is that benefiting you?
Weaviate is a pivotal tool in addressing the complexities associated with unstructured data, fostering innovation in AI applications, and contributing to more effective and data-driven decision-making within the business context.
Easy to use and powerful vector database
What do you like best about the product?
Weaviate is such a joy to use. I got a cluster set up in a couple of hours. Very good documentation, performant, a good level of abstraction where I don't feel like things are hand-wavy.
It's flexible enough that I get to use my IR and ML knowledge and feel quite in control of how the search performs.
I can use my own embedding model, reranker, and tune hybrid search to suit my usecase.
It's flexible enough that I get to use my IR and ML knowledge and feel quite in control of how the search performs.
I can use my own embedding model, reranker, and tune hybrid search to suit my usecase.
What do you dislike about the product?
It could be cheaper! But it's cheaper than another competitor I tried.
What problems is the product solving and how is that benefiting you?
I don't have to
1) set everything up. In the past I had to spin up an Elasticsearch instance, manage my own embeddings, do ANN and combine them myself.
2) tweak the code so searches run very quickly, which can take a while
3) manage my embeddings and index when my data changes
I'd much rather focus on the other logic because weaviate got things right.
1) set everything up. In the past I had to spin up an Elasticsearch instance, manage my own embeddings, do ANN and combine them myself.
2) tweak the code so searches run very quickly, which can take a while
3) manage my embeddings and index when my data changes
I'd much rather focus on the other logic because weaviate got things right.
Advanced Open Source Vector Database
What do you like best about the product?
Setting up an AI client is a complex task. Weaviate makes it possible to try different LLMs combined with hybrid search. This way we get the best of both worlds. We can make inferences based on more traditional search and help the model churn out better results.
Weaviate can be run locally, on-premise or in the cloud. This is really useful for a large number of use-cases. It also provides a clear pathway in case we want to move away from Weaviate Cloud.
Weaviate can be run locally, on-premise or in the cloud. This is really useful for a large number of use-cases. It also provides a clear pathway in case we want to move away from Weaviate Cloud.
What do you dislike about the product?
So far our greatest challenge has been to create a chat like interface with Weaviate. I am sure it's possible but there are no official guides around it. Maybe something on the lines of Assistants API provided by OpenAI would be really useful.
What problems is the product solving and how is that benefiting you?
We have a large corpus of ancient Hindu scriptures. Weaviate helps us to 'see-through' this data and find interesting results, which were simply not possible before.
Out of the box solution of Vector Databases
What do you like best about the product?
I appreciate Weaviate's efficiency as a Vector Database, offering seamless integration with LLM models. Its fast computation, coupled with the capabilities for semantic search and RAGs, is admirable. Moreover, its out-of-the-box computing service is not only efficient but also reasonably priced, making it an excellent choice for various applications. It's encouraging to see its continuous development and the growing, supportive community that accompanies it, with a very competent support team.
What do you dislike about the product?
A challenge of using Weaviate is its steep learning curve, especially for those new to the field, requiring a fair amount of technical programming skills to fully utilize its features. Once you reach it, the possibilities are endless!
What problems is the product solving and how is that benefiting you?
Weaviate addresses the need for efficient data management and retrieval in large-scale applications. By utilizing vector databases, it enables rapid, semantic-based search and integrates smoothly with large language models, enhancing data interaction capabilities. This has been immensely beneficial for me in terms of time efficiency and accuracy in data handling, particularly in complex queries where context and nuance are crucial.
Ease of use - Was up and running in a few hours.
What do you like best about the product?
Weaviate is the cost-effective and fastest way to get your Vector Indexing and Vector Similarity search implemented for your platform! We were up and running in a few hours. The support team on Slack is very helpful. A 10/10 for the product and people behind it
What do you dislike about the product?
Automatic updates would be helpful atleast on the Weaviate managed cloud instances.
What problems is the product solving and how is that benefiting you?
Whautomate - our platform empowers small and medium businesses to provide omnichannel customer experiences through our custom GPT-powered AI chatbot, ensuring seamless AI-to-human transfer across WhatsApp, Telegram, Instagram, Messenger, and Live Chat, all at an affordable price. We owe our efficiency to Weaviate's multi-tenanted vector database, which seamlessly processes and searches embeddings, making our services possible.
Great vector database
What do you like best about the product?
It's performant, easy to use, and has lots of great features. It's also a huge plus that it has cloud hosting to get started but is also open source and can be self-hosted. The cloud hosting was easy to set up and integrate with and includes various handy tools like the ability to run GraphQL queries against the data directly from the cloud console. Docs are also excellent, and aside from one issue it has been very robust and reliable.
What do you dislike about the product?
It definitely feels like a young product (which it is), especially the cloud hosting which feels a little barebones. We were also affected by one substantial bug which resulted in broken keyword search (which admittedly is a secondary feature for most Weaviate users). On the plus side, I had some fairly technical questions about how to recover from the bug and received excellent support through Slack.
What problems is the product solving and how is that benefiting you?
We use Weaviate as the database for a RAG/content generation app.
Weaviate Cloud Services is the best vector store option for both novices and advanced users.
What do you like best about the product?
As a novice only a few short months ago, I needed a way to impement embeddings which was easy and relatively inexpensive. WCS came through on both of those for me. In addition, as I began to gain more experience, I was able to appreciate more the vast array of embed and retrieval options WCS had to offer. Now, as a grizzled veteran now deploying my 3rd RAG system, I am extremely happy with the decision I made early on to go with WCS. Integrating into my code as very easy. Their support is great and timely, and they appear to spend a good amount of effort continuously improving an already superior system. In RAG, your answers are only ever going to be as good as the documents your model is given to analyze, and I have to say that WCS cosine similarity searches have consistently given me back the best documents for the best answers.
What do you dislike about the product?
I find it necessary to do queries in the WCS dashbord to both design processing code as well as troubleshoot -- and just to see what's in my vector store. The query syntax, while not terribly difficult, isn't the most intuitive. It sometimes takes a few minutes to go back and research how to construct the specific queries you need. It would be helpful if the queries you create are stored in the dashboard. Unfortunately WCS has a bad habit of deletiing them, forcing you to have to go back and re-create them every time you need them. That's actually my biggest pet peeve.
What problems is the product solving and how is that benefiting you?
The biggest problem in RAG is retrieving the documents in your vector store which are most relevant to your prompt. In my experience so far, WCS excels at this. I am working with 3 different datasets which require slightly differenc configurations, and I am able to accomodate them all with WCS. And, again, I have to point out that one of the big hurdles starting out was the cost. The next best competitor was way more expensive than I could afford, especially in the beginning. WCS pricing made this option affordable, thus making it possible to explore and build upon.
Easy to get up and running and loaded with convenient features
What do you like best about the product?
* Simple to get a local dev env working with docker
* Their new v4 python sdk makes things way easier to work with
* Built-in hybrid search with the options to tailor it to exactly what you need is a huge plus
* Reliable, been using it in production for 6 months without a hiccup
* Their new v4 python sdk makes things way easier to work with
* Built-in hybrid search with the options to tailor it to exactly what you need is a huge plus
* Reliable, been using it in production for 6 months without a hiccup
What do you dislike about the product?
* It's a fast moving product, so documentation could use some more frequent updating.
What problems is the product solving and how is that benefiting you?
We needed a hybrid vector search that came out of the box and was quick to implement.
Fantastic vector database
What do you like best about the product?
It was very easy to get started with weaviate, the pricing is simple and they take care of importing models from huggingface for us and provisioning the db instances so we can concentrate on building our product.
We were able to quickly integrate weaviate with our existing stack using the python libraries.
The documentation is good and we have been impressed by the support we received for our more unusual use cases.
There is an active slack community and we've met several people from the team and they've all been very helpful.
What's more it's all open source so we feel safe choosing Weaviate for a cricical part of our tech stack.
We were able to quickly integrate weaviate with our existing stack using the python libraries.
The documentation is good and we have been impressed by the support we received for our more unusual use cases.
There is an active slack community and we've met several people from the team and they've all been very helpful.
What's more it's all open source so we feel safe choosing Weaviate for a cricical part of our tech stack.
What do you dislike about the product?
The only drawback I can think of is that recall speed can be slow with some queries (e.g. meta filters). I believe this is being worked on though.
What problems is the product solving and how is that benefiting you?
Weaviate makes it possible for us to retrieve embedded products at scale (10s of millions of items).
showing 11 - 20