Sold by: Trieve
Trieve Vector Inference is an in-VPC solution for fast, unmetered embedding vector inference.
Get fastest-in-class embeddings using any private, custom, or open-source models from dedicated embedding servers hosted in your own cloud.
Overview
Trieve Vector Inference is an in-VPC solution for lightning-fast vector inference, unlocking performance and productivity by eliminating cloud latency and rate limits.
SaaS offerings for text embeddings have 2 major issues: 1) High latency due to batch processing 2) Heavy rate limits. This fuzzies the end-user experience and makes ingestion of large datasets impossible.
Host your embeddings locally for maximum speed, control, and scalability using any private, custom, or open-source model. TVI is great for large-scale deployments demanding high throughput.
Benchmarks can be found at https://docs.trieve.ai/vector-inference/introduction .
Highlights
- Blazing-Fast Inference: Achieve ultra-low latency for seamless embedding generation, eliminating bottlenecks in your pipelines.
- Unmetered Performance: Process massive datasets without rate limits, ensuring consistent performance and a frictionless user experience.
- Support Any Embedding Model: Use your preferred private, custom, or open-source models for maximum flexibility.
Details
Sold by
Categories
Delivery method
Delivery option
Trieve Vector Inference via helm
Latest version
Operating system
Linux
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 a fixed monthly subscription cost. You pay the same amount each month for unlimited usage of the product. Pricing is prorated, so you're only charged for the number of days you've been subscribed. Subscriptions have no end date and may be canceled any time.
- $500.001/month
Vendor refund policy
Trieve backs all products with a 45 day integration guarantee. Simply provide proof that TVI was unable to run on your clusters and we will refund you fees paid to Trieve.
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
Trieve Vector Inference via helm
Supported services: Learn more
- Amazon EKS
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
Trieve Vector Inference version 1
Additional details
Usage instructions
Support
Vendor support
Trieve General Support is available 24/7 with a maximum 6 hour response times. SLAs are available as custom add-ons.
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
Consulting services for enterprise AI-native search, discovery, RAG infrastructure.
Customer reviews
Evan L.
Real pro's changing web-search experiences
Reviewed on Oct 03, 2024
Review provided by G2
What do you like best about the product?
Their team has incredible documentation that leverages the same retreival and generation techniques as their platform. As a non-technical user, I was able to:
1. Use their playground to learn the platform and structure
2. Generate a functional web search experience
3. Connect my document / chunk data
1. Use their playground to learn the platform and structure
2. Generate a functional web search experience
3. Connect my document / chunk data
What do you dislike about the product?
There is a bit of a learning curve around structuring chunks for optimal retreival, but their team provides incredible support.
What problems is the product solving and how is that benefiting you?
Trieve has taken PHD level research and thought into new and old AI stacks and has brought it to the masses in a seemless and user-friendly way. They are improving the way document text and other forms of data are stored, searched and retreived to improve web and application experiences.
Their platform has provided our company with immense user value and offers the opportunity to grow and scale engagement on our platform.
Their platform has provided our company with immense user value and offers the opportunity to grow and scale engagement on our platform.
Leave a comment0 comments
Information Services
Good tool which creates short and easy summaries
Reviewed on Aug 22, 2024
Review provided by G2
What do you like best about the product?
It helps in providing gist of many articles it's difficult to read through entire article so this tool provides summary of articles
What do you dislike about the product?
New tool which is not used by many so it should be provided free of cost for few days to know about ease of use
What problems is the product solving and how is that benefiting you?
It reduces my time in going through entire article instead it provides short summary and gist of articles
Soniya W.
Best AI tool to create and manage Dataset
Reviewed on Jul 25, 2024
Review provided by G2
What do you like best about the product?
Its interface is quite user friendly and you will find resolution to almost all of your tasks
What do you dislike about the product?
Need to enhance the support functionality
What problems is the product solving and how is that benefiting you?
Generating the AI infrastructure in the organisation