Our use case for Qdrant is AI data analysis.
Qdrant Vector Database
QdrantReviews from AWS customer
0 AWS reviews
-
5 star0
-
4 star0
-
3 star0
-
2 star0
-
1 star0
External reviews
14 reviews
from
and
External reviews are not included in the AWS star rating for the product.
Our AI analysis has achieved sub‑second vector searches and now delivers faster insights
What is our primary use case?
What is most valuable?
The best features of Qdrant are GPU support, which enables very fast processing, and a very light footprint as it uses fewer resources.
I assess the value of Qdrant's ability to handle high-dimensional vectors for our AI projects as very positive. It is able to handle all of the AI workloads we have, and we are currently operating at a chunk size of 128KB, where it performs well.
My thoughts on the hybrid search capabilities of Qdrant are that they are very good.
What needs improvement?
The area for improvement in Qdrant is its clustering capability. While it has clustering functionality, it is not easy to set up, and not everyone can configure the clustering, so there is room for improvement in the clustering configuration.
Deploying Qdrant is complex when dealing with a cluster. A single node deployment is very easy, but if you want to deploy a cluster, it becomes complex.
For how long have I used the solution?
We have been using Qdrant for the last two years.
What do I think about the stability of the solution?
Qdrant requires maintenance. You need to patch Qdrant as soon as patches are released. We always perform minor updates, and for major updates, we consider them based on migration time and other factors. We always apply patches and minor updates.
How are customer service and support?
I rate the technical support of Qdrant as a nine because I think we have never reached out to them directly, but Qdrant has good support available online, and I can get answers from forums. The support is good.
Which other solutions did I evaluate?
When comparing Qdrant with other databases like MariaDB or TiDB, those databases do not have vector searching capabilities. Qdrant can be compared with other vector databases like Milvus, ClickHouse, and Pinecone. Qdrant operates in its own vector database segment and is good because it supports GPU acceleration, meaning if you can install a graphics card, it will use it, and it has cluster support. There is room for improvement, but it does have cluster support. If you compare other databases like Milvus or Pinecone, they do not have clustering or GPU support; those are very preliminary databases. Qdrant is an enterprise database, and we can rely on it for running enterprise applications. ClickHouse is somewhat comparable to Qdrant, but ClickHouse is a hybrid database rather than a specialized database designed for time series; it is only somewhat comparable to Qdrant.
What other advice do I have?
We are using the default query language for Qdrant, and we have not used anything else. Whatever Qdrant provides by default, we are using it, and we are satisfied with that.
The metrics I use to evaluate the performance in indexing and retrieving vectors with Qdrant focus on response time. Response time is the primary metric.
Qdrant has reduced our response time to less than one second for our 128 KB token sizes, and we are satisfied with that performance.
Qdrant is open source, which means the software is free if you handle it yourself, but you need one or two engineers working on it. Since it is free, it is very good compared to other databases. I rate this review an overall 8.
Hybrid search has improved legal and educational AI retrieval and supports fast model iteration
What is our primary use case?
My primary use cases for Qdrant are legal and educational.
What is most valuable?
The most valuable feature I have found in Qdrant is the sample code. I think they have good examples that make it developer-friendly.
Using Qdrant's hybrid search capability has improved my search results. The ability of Qdrant to handle high-dimensional vectors for my AI projects is pretty fast, and I think it's the best we have used so far. That's why we continue using it and did not check other options anymore.
The configuration of Qdrant is okay. For a developer, it was easy to set the product up and to use it.
What needs improvement?
I should check if real-time data updates in Qdrant have helped improve my models, as I don't even know they have that feature.
A lot of our work is agentic right now, and we have also segmented the content to be logical, so there's not a lot of vector search anymore. I haven't really thought of any additional features that would make Qdrant closer to a perfect score.
For how long have I used the solution?
I have been using Qdrant for two years.
How are customer service and support?
I would rate Qdrant's technical support as community-driven. There's community support since we're not paying anything, and it's more the community support for it. It's open source, so we house it on our server.
I think they provide enough information on the internet, and I am satisfied with it. They explain it well.
Which solution did I use previously and why did I switch?
I switched from Faiss because it's open source and there's not a lot of support. We were worried that moving forward, maybe no one will maintain it, so it's just good for experimenting.
How was the initial setup?
The configuration of Qdrant is okay. For a developer, it was easy to set the product up and to use it.
What's my experience with pricing, setup cost, and licensing?
Using Qdrant is free. We house it and have a VM where we just installed it on the VM.
Which other solutions did I evaluate?
Before finally choosing Qdrant, I did evaluate other options, but that was a long time ago, and I don't know what the state of vector databases is now.
What other advice do I have?
Currently, we are using a vector database called Qdrant, but most of our tasks are agentic, and we don't have it anymore. I can answer a few questions about Qdrant.
I have used Qdrant's hybrid search capability. The use of multiple query languages has impacted my data query processes mostly as Q&A.
We use the Ragas metrics to evaluate Qdrant's performance in indexing and retrieving vectors. All the metrics I consider in Ragas are useful.
In my company, we have around eight or nine people using Qdrant. I think Qdrant is popular enough in my region, but they can probably promote it more.
I rate this review a 9 out of 10.
A quick and easy to setup vector database for RAG needs
What do you like best about the product?
In our organization, we developed an RAG application and needed a way to store embeddings. I looked after many open-source tools like Pinecone and Superduperdb. Qdrant worked the best. The setup on our server was super easy, and their documentation is very elaborate. I also think the embedding search is more accurate than the other platforms I piloted with. We are still currently using Qdrant for our RAG application and are happy with it.
What do you dislike about the product?
Inability to perform rich operations from UI without writing code/query. For example, if I want to delete all collections or collections matching a name pattern, or even if I want to select multiple collections and delete, that is not possible through UI.
What problems is the product solving and how is that benefiting you?
Enable storing and searching of embeddings for AI applications.
scalability & availability
What do you like best about the product?
fully manage in all resource ,available on AWS , Google and azure plaform help with vector search technolgy
What do you dislike about the product?
non build in visualiztion ,significantly slower searching time in result.
What problems is the product solving and how is that benefiting you?
text searching is not enough , Qdrant vector database to find the similar image its detect duplicates ,including picture by text description
Self-hosted Qdrant Vector DB
What do you like best about the product?
Self-hosting Qdrant on a host is really simple and does not takes a lot of time to setup or troubleshoot issues. The documentation is also up to date. I prefer to install it using Docker to avoid installing dependencies.
What do you dislike about the product?
The initial learning curve is high but the documentation and resources makes up for it.
What problems is the product solving and how is that benefiting you?
I mainly use Qdrant for searches and building applications where I need to store vectors
depth review of Qdrant.Ai
What do you like best about the product?
desparate data sources makes easier to consolidate and analyze data from various sources,scaling data,data quality and governance.
What do you dislike about the product?
Learning might be quite difficult for who are not familiar with advanved data analytics.
pricing plans are high.
pricing plans are high.
What problems is the product solving and how is that benefiting you?
using this we can unify data from different sources,with its analyzing customer data we can gain clear insight of customer behaviour
Open-source platform gives freedom and management capability
What do you like best about the product?
Qdrant is fast and easily scalable, and I can index and query millions of vectors, essential for my work on image search. This is true because it is an open-source application, thereby allowing me to modify and adapt it to other tools that I use.
What do you dislike about the product?
Qdrant does not have integrated visualizations. This makes it difficult to make conclusions and draw visualization of the search results.
What problems is the product solving and how is that benefiting you?
Qdrant has been useful as an indexing tool for such high-dimensional vector data as mine. To that extent, it speeds up the search process that enables me to pull similar images for analysis and a search history.
Advanced vector database for developer
What do you like best about the product?
I can quickly scan through huge volumes of vectors – it is relevant for my AI work on image recognition. Since it is an open-source software, it can be used calmly and can be modified and integrated with my existing systems.
What do you dislike about the product?
Qdrant also has no incorporated visualization capabilities. Due to its basic functionalities I find it difficult to analyze and interpret the results as there are no additional software installed.
What problems is the product solving and how is that benefiting you?
Qdrant enhanced my skills to organise and query great vectors sets. The speed and scalability mean that I can manage a big flow of information and progress in my research faster.
Qdrant is vector search engine promising the scale
What do you like best about the product?
A tool for creating vector collections and performing vector operations. It excels at vector distance searches, offers convenient auto-completion features, and includes a free tier for evaluation.
What do you dislike about the product?
Although the interface is quite simple, it still has limited capabilities.
What problems is the product solving and how is that benefiting you?
Qdrant is a straightforward vector database, but its scalability remains an open question.
Offers tremendous opportunities for customization
What do you like best about the product?
In the pursuit of my AI research, Qdrant can expedite the process of searching high-dimensional vector data. The options and setting let me work on terabytes of data and perform similarity search in real time.
What do you dislike about the product?
Qdrant does not come with graphical utilities that can provide data visualization. This poses a problem when it comes to interpreting the retrieved results particularly for higher-orders of dimensions.
What problems is the product solving and how is that benefiting you?
They solve the problems in AI development - how to efficiently search large vector datasets. This in turn enables me to interact with the data in terms of relationships much faster hence information generation and model building.
showing 1 - 10