v2026.3Open SourceApache 2.0
Viglet Turing ES
Viglet Turing ES is an open-source enterprise search platform combining Semantic Navigation, content integration, and Generative AI. Index content from any source, deliver faceted search experiences, and deploy conversational AI grounded in your own data.
Key Capabilities
🔍
Semantic Navigation
Faceted search, autocomplete, spotlights, targeting rules, result ranking and per-site AI insights.
🤖
Generative AI
RAG over your indexed content, LLM instances, AI agents, tool calling and MCP server integration.
🔌
Content Integration
REST API connectors, AEM, web crawler, delta tracking, merge providers and indexing rules.
🔒
Security
Native session auth, REST API key tokens and production-grade Keycloak OAuth2/OIDC SSO.
Quick Start
STEP 01
Start here
The zero → first-agent learning path
STEP 02
Understand
SN Sites, connectors and the data model
STEP 03
Install
Docker, standalone JAR or from source
STEP 04
Search
REST API, search params and response format
Administration & Development
⚙️
Administration Guide
Users, roles, API tokens, global settings and system information
🛠️
Developer Guide
Tech stack, dev environment, Java SDK and contribution guide
📡
REST API Reference
Search, autocomplete, spell check, GenAI chat and token usage endpoints
Enterprise Search
🗄️
Search Engine
Manage Solr, Elasticsearch and Lucene backends, cores and monitoring
🧭
Semantic Navigation
Configure SN Sites: fields, facets, spotlights, targeting rules, result ranking and GenAI
🔗
Integration
Connect AEM and web crawler sources with indexing rules and monitoring
Generative AI
🧠
GenAI & LLM Configuration
RAG architecture, embedding pipeline and core GenAI concepts
📖
What is RAG?
How LLMs, embedding models and vector stores work together to ground AI in your content
⚡
LLM Instances
Configure provider connections: vendors, models, API keys and capabilities
🗃️
Embedding Stores
ChromaDB, PgVector and Milvus vector database backends
🧬
Embedding Models
Provider support, model selection and local transformers configuration
🗂️
Assets (Knowledge Base)
File manager backed by MinIO: upload, organise and train the RAG knowledge base
🔧
Tool Calling
27 native tools across 7 categories available to AI Agents
🌐
MCP Servers
Extend agents with external tools via the Model Context Protocol
🤖
AI Agents
Compose and deploy purpose-built AI assistants with custom tools and personas
🧩
Skills
Run portable, Anthropic-compatible skill folders in a Docker sandbox: usable in chat and semantic navigation
🗄️
Agent Workspace
Per-conversation file store: tool artifacts, downloads and auto-offloaded large results
🧠
Chat Memory
Persist history, retrieve relevant older turns with BM25, and compress long conversations
💬
Chat
Chat interface: direct LLM, Semantic Navigation and AI Agent views
📊
Token Usage
Monitor and analyse LLM token consumption by model and day
Technical Reference