Back to the registry
Agent passport

TurboPuffer on Ubuntu 24.04 with maintenance support by kCloudHubs

kCloudHubs LLC · Cybersecurity & IT

No attestation published

Certification per AWS Marketplace.

Provenance reach4 of 12 layers traced

Evidence tier Source Confirmed · 4 captures on record

User ratingNot rated0 reviews on the listing
Runs onUnknownVirtual machine
ProvenanceUnknown44% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on AWS Marketplace.

<section>

<p>

Show the rest of the publisher’s description (87 more lines)

<strong>TurboPuffer on Ubuntu 24.04 with Free Maintenance Support by ATH Infosystems</strong>

is a repackaged software offering wherein additional charges apply for support.

TurboPuffer is a high-performance, object-storage-native search engine designed for

scalable search and retrieval workloads. It supports vector search, full-text

search, filtering, ranking, and hybrid search, making it suitable for modern

applications that need to efficiently retrieve relevant information from large

document collections.

</p>

<p>

This offering provides a pre-configured TurboPuffer environment on Ubuntu 24.04

for developers, AI engineers, data engineers, and DevOps teams working with

search and retrieval applications. TurboPuffer uses object storage as durable

storage while using memory and NVMe SSD caching to accelerate frequently accessed

data. Its architecture separates compute from storage, allowing search workloads

to scale independently.

</p>

<p>

TurboPuffer organizes data into isolated namespaces, with each namespace providing

a separate document and vector search space. Applications can write, update,

delete, filter, and query documents through the API. The platform supports

approximate nearest-neighbor vector search, exact nearest-neighbor search,

BM25 full-text search, sparse vector search, attribute filtering, and hybrid

retrieval workflows.

</p>

<p><strong>Key Features of TurboPuffer:</strong></p>

<ul>

<li>Object-storage-native search engine architecture.</li>

<li>Vector and semantic search capabilities.</li>

<li>BM25 full-text search for text-based retrieval.</li>

<li>Hybrid search combining vector and full-text retrieval.</li>

<li>Attribute filtering and sorting.</li>

<li>Approximate and exact nearest-neighbor search.</li>

<li>Support for dense and sparse vector search.</li>

<li>Namespace-based data organization.</li>

<li>Copy-on-write namespace branching.</li>

<li>Object storage as the durable source of truth.</li>

<li>Memory and NVMe SSD caching for frequently accessed data.</li>

<li>Stateless compute architecture for scalable workloads.</li>

<li>APIs and SDKs for application integration.</li>

<li>Suitable for AI retrieval and large-scale search applications.</li>

</ul>

<p><strong>AI and Search Applications:</strong></p>

<p>

TurboPuffer can serve as a first-stage retrieval layer for AI and search

applications. It can efficiently narrow large collections of documents to a

smaller set of relevant results that can subsequently be processed or reranked

by application logic or AI models. This makes it suitable for retrieval-augmented

generation (RAG), semantic search, knowledge discovery, recommendation systems,

and document retrieval workflows.

</p>

<p><strong>Scalable Data Architecture:</strong></p>

<p>

TurboPuffer separates durable storage from compute and uses caching to improve

query performance. Its architecture is designed to support large datasets,

distributed workloads, and automatic scaling while keeping durable application

data in object storage.

</p>

<p><strong>Deployment and Integration:</strong></p>

<ul>

<li>Pre-configured TurboPuffer environment on Ubuntu 24.04.</li>

<li>Ready-to-use search and retrieval development environment.</li>

<li>Suitable for AI, vector search, and full-text search workflows.</li>

<li>Integration with Python and other application development environments.</li>

<li>Suitable for cloud-hosted development and production workflows.</li>

</ul>

<p><strong>ATH Infosystems Support:</strong></p>

<ul>

<li>Installation and configuration assistance.</li>

<li>Search environment troubleshooting.</li>

<li>Maintenance and update assistance.</li>

<li>Application integration and deployment guidance.</li>

<li>Operational support for supported deployment environments.</li>

</ul>

<p>

<strong>Keywords:</strong> TurboPuffer, Ubuntu 24.04, search engine, vector search,

semantic search, full-text search, BM25, hybrid search, AI search, RAG, vector

database, document retrieval, information retrieval, object storage, namespaces,

machine learning, artificial intelligence, data discovery, search API, cloud search,

ATH Infosystems.

</p>

<p>

<strong>Licensing &amp; Disclaimer:</strong> TurboPuffer and related trademarks

belong to their respective owners. This offering is independently packaged,

maintained, and supported by ATH Infosystems. Users should review the applicable

TurboPuffer service, licensing, API, and usage terms before deployment.

</p>

</section>

Highlights

Highlighted by the publisher on AWS Marketplace.

High-performance vector search capabilities.

Python-friendly and easy to integrate.

Works well with modern AI frameworks and pipelines.

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Plans and pricing as listed

21 listed
m4.large
  • Hrs
$0.10
t3.micro
  • Hrs
$0.10
t2.micro
  • Hrs
$0.001
t3.large
  • Hrs
$0.10
r4.large
  • Hrs
$0.10
r3.large
  • Hrs
$0.10
t2.large
  • Hrs
$0.10
t2.2xlarge
  • Hrs
$0.10
t2.medium
  • Hrs
$0.10
t3.medium
  • Hrs
$0.10
t3.nano
  • Hrs
$0.10
m3.medium
  • Hrs
$0.10
and 9 more plans on the listing

Refund terms

As stated by the publisher on AWS Marketplace.

No Refund

Sources

Marketplace listingaws.amazon.comSource
App certificationaws.amazon.comSource
StandardEulaStandardEulaSource

Linked repositories

RepositoriesUnknownUnknown

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Paid
21 plans listed
Delivery
Virtual machine
"Feel free to reach out anytime. Our support team is available 24x7 for assistance mail: meha@kcloudhubs.com"
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.