Bring vector search to your HCL Informix® data
Build AI Apps. No new databases. No added complexity.
Add vector search, semantic retrieval, and RAG capabilities directly into HCL Informix® 15.
Informix is a trademark of IBM Corporation in at least one jurisdiction and is used under license.
Join the Waitlist!
Be among the first to evaluate vector search and AI capabilities in HCL Informix.
(i.e. sales@..., support@...)
Build AI without added complexity
No separate vector database
Store embeddings alongside your existing data. No need to manage a separate database.
SQL-native vector search
Run similarity search and hybrid queries using standard SQL. No new APIs or tools to learn.
Built for enterprise
Maintain security, governance, and compliance within your existing HCL Informix environment.
Real-time read/write support
Continuously update embeddings to power dynamic RAG and semantic search applications.
What you can build
- Semantic search across documents and knowledge bases.
- Retrieval-augmented generation (RAG) pipelines.
- Personalized recommendation engines.
- Anomaly detection to identify hidden patterns.
- Hybrid search (keyword search + semantic search).
Built for developers
Works with your existing stack
- Connect using standard ODBC or JDBC clients.
- Use any programming language or application framework.
Flexible AI integration
- Works with your preferred frameworks like LangChain, Hugging Face, or LlamaIndex.
- HCL Informix acts as the vector store, while your application controls model interaction.
Optimized vector indexing
- Uses IVF + HNSW indexing for balanced performance and scalability.
- Designed for efficient similarity search across large datasets.
Why HCL Informix for AI
Most AI stacks require adding a separate vector database, syncing data across systems, and managing new infrastructure.
HCL Informix brings vector capabilities directly into your database, so you can:
- Reduce architecture complexity.
- Avoid data duplication.
- Keep governance and security intact.
