Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
docs: link common tasks to their guides
Maxfield Allison52486306f2d3
diff --git a/docs/index.md b/docs/index.mdindex c41eb0dd..4c8228c4 100644--- a/docs/index.md+++ b/docs/index.md@@ -3,16 +3,28 @@Multilingual, non-autoregressive System 1 decision engine: typed `choice`, `score` and `noul`decisions over any state, in a single forward pass.-The [README](https://github.com/NandhaKishorM/laya#readme) is the main guide. It covers-installation, the `Router` quickstart, the HTTP server, calibration, benchmarks and known limits.-The [Python API reference](reference/index.md) is generated from the docstrings.-These guides cover individual topics:+A `choice` question picks one of several options, a `score` question places the state on a+scale, and a `noul` question gives the probability that the answer is yes. Laya runs on your own+hardware, reads 100+ languages, and its `Router` picks the checkpoint for each request.-- [Docker quickstart](docker.md): run the SDK in a container, on CPU or an NVIDIA GPU.-- [ARM64 and DGX Spark containers](docker-platforms.md): builds for ARM64 CPU hosts and for- DGX Spark with CUDA 13.0.-- [LangChain & LangGraph](langchain.md): Laya as router, guardrail, triage and evaluator- components, in process or over HTTP.-- [Fine-tuning example: browser agent](finetune_browser_agent.md): specialising Laya as the- decision head of a browser agent, end to end.-- [Prediction hooks](hooks/index.md): observe or shape every decision without forking Laya.+## Start here++Install Laya and make a first decision with the README's+[Installation](https://github.com/NandhaKishorM/laya#installation) and+[Quickstart](https://github.com/NandhaKishorM/laya#quickstart). They stay in the README so there+is one copy to keep current.++## Find a guide++| To | Read |+|---|---|+| get typed values back from a JSON schema or a pydantic model | [Schema-driven decisions](structured.md) |+| log, redact, cache or gate every decision without forking Laya | [Prediction hooks](hooks/index.md) |+| route, screen or triage inside a LangChain or LangGraph app | [LangChain & LangGraph](langchain.md) |+| run the SDK or the `laya-serve` HTTP API in a container, on CPU or an NVIDIA GPU | [Docker quickstart](docker.md) |+| build for ARM64 hosts or DGX Spark | [ARM64 and DGX Spark containers](docker-platforms.md) |+| specialise a checkpoint for your own decisions | [Browser-agent fine-tuning example](finetune_browser_agent.md) and the [fine-tuning notebook](https://github.com/NandhaKishorM/laya/blob/main/notebooks/laya_finetune_typed_decisions_2xT4_kaggle.ipynb) |+| look up a class, function or parameter | [Python API reference](reference/index.md) |++Routing, the HTTP API, the command line, the MCP server, confidence gating, benchmarks and known+limits are in the [README](https://github.com/NandhaKishorM/laya#readme) for now.