Sold by: GraphAI
Deployed on AWS
AWS Free Tier
VectorOn is a high-performance vector search extension that integrates directly into PostgreSQL. With support for multiple indexing algorithms (HNSW, Vamana, IVF, Flat) and flexible quantization, it allows you to store and retrieve vectors using familiar SQL workflows while balancing speed, memory, and accuracy to meet your requirements.
Overview
Welcome to VectorOn, a high-performance vector search extension that seamlessly integrates directly with your PostgreSQL database. Simply load the vectors extension to begin storing and searching vector data using your familiar SQL workflows.
VectorOn offers the flexibility to choose from multiple indexing algorithms - including HNSW, Vamana, IVF, and Flat - enabling you to select the ideal option for your specific speed, memory, and accuracy requirements. It also features Scalar and Product Quantization to effectively reduce memory consumption while maintaining acceptable accuracy.
For robust administration, VectorOn provides GUC parameters for performance tuning, index status monitoring, and simplified online upgrades. With client-language support and examples in SQL and Python, it ensures easy integration into a variety of environments.
Highlights
- Seamless SQL-native experience directly integrates into your existing PostgreSQL database. Simply load the extension and manage vectors using the familiar SQL commands and workflows you already know, eliminating the need for a separate database or new query language.
- Flexible performance tuning tailor performance to your exact needs. Choose from multiple advanced indexing algorithms like HNSW and Vamana and apply Scalar or Product Quantization to achieve the perfect balance between search speed, memory usage, and accuracy for your specific application.
- Robust management & easy integration simplify database operations with powerful administrative tools for performance tuning, index monitoring, and seamless online upgrades. With client support for languages like SQL and Python, integration into your existing environment is straightforward.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 22.04 LTS
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Cost/hour |
|---|---|
t3.medium Recommended | $0.10 |
t3.micro | $0.01 |
Dimensions summary
You pay by the hour based on the EC2 instance size you run. Two options are available: t3.medium and t3.micro. Both bill per hour of usage, with no upfront commitment. The t3.medium runs on more compute capacity than the t3.micro, so you choose the size that matches your workload. Your cost scales with the number of hours each instance runs. This usage-based model lets you start, stop, and switch instance sizes as your needs change, paying only for the hours you actually use.
Top-of-mind questions for buyers
Each rate maps to one running EC2 instance of that size. The t3.medium provides more vCPU and memory than the t3.micro. You pick the instance size that fits your workload, and the software meters each hour that instance runs.
Software charges apply per hour only while the instance runs. Fully stopped instances do not accrue software charges. Underlying AWS storage fees may still apply to stopped instances, but the software meters running time only.
It runs an AI data platform that unifies graph, vector, and relational data for retrieval and search. It supports document parsing, embedding, and decision-support features. The software optimizes for SSD use over heavy GPU dependence, so smaller instance sizes can handle data processing tasks.
www.graphai.io
Helpful?
Vendor refund policy
Please contact cloud@graphai.io for refund requests.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
-
AWS Marketplace Integration (Core Feature) This version officially supports integrated AWS Marketplace licensing. Vectoron now verifies licenses by directly checking AWS Marketplace subscription information via the EC2 Instance Metadata Service (IMDSv2).
-
License-Based Feature Activation The high-performance indexing feature (CREATE INDEX) has been converted to a paid, licensed feature. Index creation is now enabled only on instances with a valid AWS Marketplace subscription.
-
Freemium Feature Support Basic vector search functionality (e.g., SELECT ... <-> operators) is still supported via sequential scan, even without a license subscription. This allows users to test and evaluate the core features of the product.
-
Automated Configuration on Startup The Vectoron PostgreSQL extension is now pre-configured and set to load automatically (shared_preload_libraries). This ensures that Vectoron is ready to use immediately after the instance starts, requiring no manual setup.
Additional details
Usage instructions
Thank you for choosing Vectoron! To get started:
-
Launch the EC2 instance from this AMI.
-
Connect to the instance via SSH using the 'ubuntu' user and your selected key pair.
ssh -i /path/to/your-key.pem ubuntu@<INSTANCE_PUBLIC_IP> -
Get Your Initial Database Password Your default password for the 'postgres' user is your EC2 Instance ID. You can find this in the AWS EC2 Console (e.g., i-0123456789abcdef0).
-
Connect to PostgreSQL and Set a New Password Connect using the 'postgres' user. You will be prompted for the password from Step 3.
psql -U postgres- Enter your Instance ID as the password.
- (Required) You must immediately change the password:
-
Activate and Verify Vectoron You can now activate the extension in the database and verify its installation.
-- 1. Activate Vectoron postgres=# CREATE EXTENSION IF NOT EXISTS vectoron; -- 2. Verify installation (should show 'vectoron' in the list) postgres=# \dx vectoron
For detailed documentation, please visit: https://graphai-repository.github.io/akasicdb-docs/
Support
Vendor support
Official Documentation: https://graphai-repository.github.io/akasicdb-docs/
Please contact cloud@graphai.io
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Pinecone is a serverless vector database built to power production AI on AWS. It delivers fast, accurate retrieval with hybrid search, reranking, filtering, and real-time indexing - no infrastructure or tuning required. Purpose-built for scale, Pinecone handles billions of vectors with low latency and high reliability. Teams use Pinecone to power agents, semantic search, recommendations, and RAG pipelines without managing infrastructure or stitching together open-source tooling. With fully managed operations and predictable performance, developers can focus on building intelligent applications instead of operating vector infrastructure.
Qdrant is an open-source and fully managed high-performance Vector Database. The vector search engine provides a production-ready service with a convenient API to store, search, and manage vector embeddings.
Only for accepting private offers. Pinecone is a serverless vector database built to power production AI on AWS. It delivers fast, accurate retrieval with hybrid search, reranking, filtering, and real-time indexing - no infrastructure or tuning required. Purpose-built for scale, Pinecone handles billions of vectors with low latency and high reliability. Teams use Pinecone to power agents, semantic search, recommendations, and RAG pipelines without managing infrastructure or stitching together open-source tooling. With fully managed operations and predictable performance, developers can focus on building intelligent applications instead of operating vector infrastructure.
ClearVector helps you prepare for, detect, investigate, and stop threats in your AWS environment. Our realtime identity-driven approach enables you to quickly figure out who did it and take action.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.