langpath is a semantic router for AI applications. It lets you control the path that AI information takes through your application or infrastructure—like a mail sorting centre for AI prompts and outputs.
Use langpath to reduce LLM costs (and their carbon footprint), protect private and customer data, avoid reputation damage, and improve customer experience.
How It Works
The core of langpath is a descriptive knowledge graph containing more than 100,000 connected concepts that cover just about everything humans talk about and use to describe their world. More than one million words can be used to search this graph, and the connections enable Natural Language Understanding (NLU) logic during that search.
This NLU-based search is highly effective, transparent, predictable, fast, and computationally inexpensive. Each concept also carries a precisely-worded description that allows Vector search (Embeddings) to augment the NLU result.
From Concepts to Paths
Configuring langpath is as easy as selecting blocks from its knowledge graph. Your selected block describes a "semantic scope" that will be applied to prompts and other data sent to the langpath Router. Select each block by choosing one or more parent concepts, then assign a path and priority. Input that matches the block will be routed to the model, RAG store, API, middleware, or other component that you specify.
AI Safety in Your Hands
Language Models are trained on enormous quantities of text from varied sources. These sources—and consequently the models—contain biases and misinformation, and don't always reflect values we'd want to call our own.
We have the power to make our own AI applications safe. We control the gateways that provide access to unsafe models. With langpath in our applications and infrastructure, we can recognize risky prompts and outputs and route them appropriately.
Key Benefits
- Cost Reduction — Route work to the most cost-effective model; block non-approved tasks
- Transparency — Unlike black-box classifiers, langpath decisions are deterministic and explainable
- Flexibility — Works with LangChain, LlamaIndex, Semantic Kernel, and enterprise orchestration frameworks
- Security — Semantic firewall capabilities for prompt injection protection
langpath is a FactNexus product, and powers the CAT3 AI governance appliance.