> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# LangChain
> Trace LangChain Python applications with OpenInference and send spans to Arize AX for LLM observability.
[LangChain](https://www.langchain.com/) is a Python framework for composing LLM applications — chains, agents, RAG, tool use. Arize AX captures every LangChain run — prompt templates, chat-model calls, retrievals, tools, and the runnable hierarchy that wraps them — via the [`openinference-instrumentation-langchain`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-langchain) package.
## Prerequisites
* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* An `OPENAI_API_KEY` from the [OpenAI Platform](https://platform.openai.com/api-keys)
## Launch Arize AX
1. Sign in to your [Arize AX account](https://app.arize.com/).
2. From **Space Settings**, copy your **Space ID** and **API Key**. You will set them as `ARIZE_SPACE_ID` and `ARIZE_API_KEY` below.
## Install
```bash theme={null}
pip install arize-otel \
openinference-instrumentation-langchain \
langchain langchain-openai
```
## Configure credentials
```bash theme={null}
export ARIZE_SPACE_ID=""
export ARIZE_API_KEY=""
export ARIZE_PROJECT_NAME="langchain-tracing-example"
export OPENAI_API_KEY=""
```
## Setup tracing
```python theme={null}
# instrumentation.py
import os
from arize.otel import register
from openinference.instrumentation.langchain import LangChainInstrumentor
tracer_provider = register(
space_id=os.environ["ARIZE_SPACE_ID"],
api_key=os.environ["ARIZE_API_KEY"],
project_name=os.environ["ARIZE_PROJECT_NAME"],
)
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for LangChain.")
```
## Run LangChain
```python theme={null}
# example.py
# Importing instrumentation first ensures tracing is set up
# before `langchain_openai` is imported.
from instrumentation import tracer_provider
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
# ChatOpenAI reads OPENAI_API_KEY from the environment.
prompt = ChatPromptTemplate.from_template(
"Why is the {celestial_object} {color}? Answer in two sentences."
)
chain = prompt | ChatOpenAI(model="gpt-5")
response = chain.invoke({"celestial_object": "sky", "color": "blue"})
print(response.content)
```
### Expected output
```text wrap theme={null}
Arize AX tracing initialized for LangChain.
The sky appears blue because of Rayleigh scattering — molecules in the atmosphere scatter shorter (blue) wavelengths of sunlight more than longer ones, so the diffuse light reaching your eyes is dominated by blue. At sunrise and sunset, light travels through more atmosphere, so the blue is scattered out and reds dominate.
```
## Verify in Arize AX
1. Open your Arize AX space and select project **`langchain-tracing-example`**.
2. You should see a new trace within \~30 seconds containing a `RunnableSequence` parent span (the LCEL chain) wrapping `ChatPromptTemplate` and `ChatOpenAI` child spans, with the prompt, response, and token usage attached.
3. If no traces appear, see [Troubleshooting](#troubleshooting).
## Troubleshooting
* **No traces in Arize AX.** Confirm `ARIZE_SPACE_ID` and `ARIZE_API_KEY` are set in the same shell that runs `example.py`. Enable OpenTelemetry debug logs with `export OTEL_LOG_LEVEL=debug` and re-run.
* **LangChain spans missing but other spans present.** `LangChainInstrumentor().instrument(...)` must run before any `langchain` import. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from OpenAI.** Verify `OPENAI_API_KEY` is set and has access to `gpt-5`. Swap for a model your key can call.
* **Other LLM providers.** Install the matching `langchain-` package (e.g. `langchain-anthropic`, `langchain-google-genai`) and replace `ChatOpenAI` with the equivalent chat model. The same `LangChainInstrumentor` covers every provider.
## Resources