LangChain

Trace LangChain (and LangGraph) runs with Rius: chains, tools, retrievers, and model calls arrive as a nested trace mirroring your graph.

Setup

pip install "glassflow-rius[langchain]" langchain

import rius
 
rius.init(api_key="ri_...", service_name="my-agent")
# build and run your chains exactly as before

npm install @arizeai/openinference-instrumentation-langchain

import { init } from '@glassflow-ai/rius'
 
const rius = init({ apiKey: 'ri_...', serviceName: 'my-agent' })
// build and run your chains exactly as before

What gets captured

One span per step, typed by what the step is: chains as CHAIN spans, tool invocations as TOOL, retrievers as RETRIEVER, and model calls as LLM spans with model, token usage, and messages (cost computed server-side). The nesting follows your chain structure, so a trace reads like the execution graph.

Combining with client instrumentation

Installing langchain alongside a client extra (say openai) works: LangChain’s chat model span wraps the client library’s span, so you get framework context and client-level detail, nested. Since glassflow-rius 1.1.0 and @glassflow-ai/rius 1.2.0 the SDK makes the chat model span current during the call, so the client span nests under it; before those versions the client span started a trace of its own.

Each model call is counted once in tokens and cost, and the LangChain span still shows the run’s total. Text-completion models (BaseLLM subclasses, such as langchain_openai.OpenAI) are still counted twice; see Still counted twice for that case, the others, and which layer to keep.

Verify

Run one chain that calls a model, then open the trace in the console: you should see the chain’s structure as nested spans, with the LLM leaf carrying model, tokens, and cost.