Problem
Months building search infrastructure.
You need your agent to find the right passage in a PDF, the right moment in a recording, the right image in a library.
So you build it. Chunking pipelines, embedding models, PDF parsers, transcription services, citation logic, reranking.
You stitch it together, tune the chunk sizes, handle edge cases for every file format. Then you maintain all of it.
And you still don't get the results you want.
Solution
Frontier deep search, ready to go.
State-of-the-art deep search, that works out of the box. Baked into Exabase's storage.
Everything you store becomes searchable at the sub-document level – paragraphs in PDFs, timestamps in audio and video, objects and colours in images.
Search with multi-modal input. Get back precise chunks with location references and relevance scores. No pipeline to build. No models to manage.
Up and running in 3 minutes.
Search modes
Text queries — hybrid semantic and keyword search, automatically balanced
Image queries — find visually similar content across your resources
Colour search — find resources by dominant colour or palette
File or resource similarity — use any stored resource as a query
Filtered search — narrow by tags, folders, resource type, date range
Multi-query search — fan out multiple queries in a single call
Results that deliver
Fast
Precise chunks with match scores
Neighbouring chunks for adjustable context
Location references — page and paragraph in PDFs, timestamps in audio and video, regions in images
Citations ready for your agent's response
Works across every resource type in your Base
Why Exabase
Most search APIs give you semantic search over vectors you create. You still build the ingestion pipeline, handle every file format, manage chunking, and figure out citations yourself.
Exabase owns the entire path from raw file to precise, locatable search result. Content is indexed automatically when you store it — PDFs, images, audio, video, notes, bookmarks. No external parsers, no embedding pipelines, no chunking logic to maintain.
And because Deep Search is built on the same infrastructure as Fabric — where hundreds of thousands of users store and search their files, notes, and links every day — it's production-tested at scale, not a research project.
How it works
Store a resource. Upload files, save notes, bookmark links — through the Resources API into any Base. Content is indexed automatically at write time.
Search with anything. Send a text query, an image, a colour, or a reference to another resource. Add filters to narrow scope.
Get precise results. Receive matched chunks with relevance scores and exact location references. Request neighbouring chunks for more context.
Works with everything
Model-agnostic. Framework-agnostic.
SDKs
Python and JavaScript clients. Or call the REST API directly.
CLI
Use Exabase from the command line. Works with Claude Code, shell scripts, or anywhere you can run a terminal.
MCP support
Connect to Claude Desktop, Cursor, Windsurf, Continue, and any MCP-compatible tool.
Ready for scale
Fast
Sub-300ms retrieval. Infrastructure that won't slow your agent down.
Secure
Encrypted in transit (SSL) and at rest (AES-256).
CASA certified.
Reliable
99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.
Deciding?
Ask your favourite AI about Exabase:
