[ 01 ]For teams
Give every team a clearer answer.
Bring together files, cloud storage, Confluence pages, and Jira issues. Give your teams a place to search, ask questions, and follow answers back to the evidence.
VectorAmp gives regulated companies answers they can prove. Every answer cited. Every query permission-scoped.
Building an AI product or evaluating customer-operated infrastructure? Explore SABLE's filter-native retrieval through the API or client SDKs, or discuss a scoped BYOC pilot.
Powered by our proprietary filter-native vector technology
Meet SABLE, engineered for filtered search
Illustrative legal retrieval: matter files in SharePoint, a privilege log in OneDrive, and approved case strategy in Google Drive feed VectorAmp. The answer cites the permitted matter record and strategy while the privilege boundary keeps an excluded memo out of the answer.
Bring together files, cloud storage, Confluence pages, and Jira issues. Give your teams a place to search, ask questions, and follow answers back to the evidence.
SABLE is the high-performance, filter-native vector search engine powering VectorAmp. It plans and applies permission filters before search to keep large-scale, high-selectivity workloads efficient and predictable. Build on it using the client SDKs, REST API, CLI, or MCP server.
Two vertical markets. One platform. A governed, no-code canvas serves knowledge-centric teams, while our filter-native retrieval engine serves AI-driven software platforms and developers.
VectorAmp brings ingestion, vector search, and AI answers together. Your teams get a straightforward way to explore their data. Your developers get the tools to build on it.
Explore use cases with your own sources, access rules, and evidence requirements. Deployment and regulatory fit are evaluated case by case.
SABLE is our standalone, filter-native retrieval engine: sharded and tuned for the high-selectivity, permission-heavy queries compliance-focused teams actually run. Filters, permissions, and provenance are built into the engine from the start.
# filtered semantic searchfrom vectoramp import VectorAmp
client = VectorAmp(api_key="va_...")dataset = client.datasets.get("acme-prod")
results = dataset.search( text="migration plan risks", top_k=20, filters={"team": "platform", "region": "eu"}, advanced_filters=[{"field": "year", "op": "gte", "value": 2025}], include_documents=True,)Choose the files, pages, issues, or cloud objects your team needs. Manage ingestion and scheduled runs in one place.
Team sites & document libraries
Working files & shared folders
Documents, sheets & presentations
Code, pull requests & reviews
Repositories, merge requests & reviews
Files & objects in your buckets
Knowledge bases, spaces & pages
Projects, issues & discussions
Cloud buckets & object collections
Websites, pages & linked documents
PDFs, Office documents & more
A no-code canvas for your users and an SDK for your developers, both pointing to the same governed data layer, so everyone works from a unified set of access rules, an audit trail, and a single source of truth.
The revenue outlook has changed.[1] Update the valuation assumptions[2] using the latest company filing.[3]
Revenue outlook revised after the latest company update. The investment committee pack needs the new assumptions.
Select a source to inspect the evidence behind the answer.
SABLE is designed to stay fast and predictable under heavy filtering. Permission filters are applied before search, not after, with recall and cost controls you can tune against your own workload.
region = EUyear = 2026Plan vector search around the requested metadata scope.
↓Relevant content, within your selected scope. Illustrates filtering, not measured ranking or latency.
See VectorAmp on your own data sources, with every answer permission-scoped and traceable to its source.
Spin up a SABLE index in five minutes: filter-native from the first query, with recall you can verify against your own data and transparent pricing with no surprises.