Overview
SearchAI Hybrid Search
SearchAI unifies keyword, semantic (vector), and hybrid search with built-in LLM features - RAG answers with citations, AI Overviews, conversational chatbots, knowledge graphs, and e-commerce product discovery. Natural-language queries are understood, expanded, and re-ranked so users find the right result even when they don't use the exact words. Runs self-contained on Amazon ECS/EKS; connect your OpenSearch cluster and index content from 300+ connectors.
Highlights
- Hybrid + semantic (vector) search with RAG answers and citations
- Built-in AI chatbots, knowledge graphs, and e-commerce product discovery
- Container-native: ECS, EKS, ECS/EKS-Anywhere; no heavy dependencies
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
This product is offered under a Bring Your Own License (BYOL) model. There are no software charges through AWS Marketplace. Licenses are purchased directly from SearchBlox and are governed by the SearchBlox license agreement; all license, billing, and refund matters are handled directly by SearchBlox. Contact sales@searchblox.com for licensing and refund inquiries.
Custom pricing options
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
SearchBlox SearchAI Container Image
- Amazon ECS
- Amazon EKS
- Amazon ECS Anywhere
- Amazon EKS Anywhere
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
[NEW] SearchAI Native Inference Engine - in-process, Python-free inference for the Qwen3.5 model family on CPU (ARM/x86/Windows) and NVIDIA GPU; no external model server. [NEW] llama.cpp Provider - bundled, managed llama-server; new default backend for text and agent tasks, with optional GPU offload and automatic fallback. [NEW] AI Overview - grounded, RAG-based answers with citations (/rest/v2/api/ai-overview, streaming), also exposed as an MCP tool. [NEW] Virtual Filesystem (VFS) - volume-scoped file storage: upload/download/move/copy/search, automatic content indexing, versioning, static-site hosting, sandboxed script execution. [NEW] RAG Chunking Overhaul - pluggable strategies (recursive, sentence, paragraph, structural, semantic) with token-aware sizing and per-collection overrides. [NEW] Vision-based OCR - scanned-document extraction via vision-LLM OCR (replaces Tesseract), including multi-page scanned PDFs. [NEW] New Collections - native Jira, Alfresco ECM, Drupal CMS, Adobe Edge Delivery Services; a generic descriptor-driven REST/OData connector (130+ SaaS integrations); a generic CMIS connector; native JDBC drivers for 15+ databases (Snowflake, Databricks, SAP HANA, Teradata, and more). [NEW] Per-Collection Stopwords - custom stopword list per collection. [NEW] Five new SSO providers - Amazon Cognito, Microsoft Entra ID, Google Workspace, Generic OIDC (discovery/presets), Generic SAML 2.0 (cert upload + Validate). [NEW] OpenAI-Compatible Chat Completions - /v1/chat/completions (streaming) for MCP tool-calling.
Additional details
Usage instructions
Run the SearchAI container with ports 8443 (HTTPS admin console), 8444, and 8446 exposed:
docker run -p 8443:8443 -p 8444:8444 -p 8446:8446 <image>
Replace <image> with the image URI you pulled from AWS Marketplace.
Once the container starts, open the admin console: https://<host-or-ip>:8443/console
Setup and configuration guide: https://developer.searchblox.com/docs
Support
Vendor support
Visit our Developer Documentation
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.