Setting up LangSmith tracing in LangChain - Visual Walkthrough

Concept Flow - Setting up LangSmith tracing

Import LangSmithTracer

↓

Create tracer instance

↓

Configure LangChain to use tracer

↓

Run LangChain operations

↓

Tracer collects and sends data

↓

View traces in LangSmith UI

This flow shows how to import, create, and configure LangSmith tracing, then run LangChain code that sends trace data to LangSmith.

Execution Sample

LangChain

from langchain import OpenAI, LLMChain
from langchain_experimental.langsmith import LangSmithTracer

tracer = LangSmithTracer()
llm = OpenAI()
llm.chain_type = "stuff"
llm.tracer = tracer

chain = LLMChain(llm=llm, prompt=some_prompt)
result = chain.run("Hello")

This code sets up LangSmithTracer, attaches it to an OpenAI LLM, then runs a chain to generate output while tracing.

Execution Table

Step	Action	Evaluation	Result
1	Import LangSmithTracer	Module found	LangSmithTracer class ready
2	Create tracer instance	tracer = LangSmithTracer()	tracer object created
3	Create OpenAI LLM instance	llm = OpenAI()	llm object created
4	Attach tracer to llm	llm.tracer = tracer	llm now sends traces
5	Create LLMChain with llm	chain = LLMChain(llm=llm, prompt=some_prompt)	chain ready to run
6	Run chain with input 'Hello'	chain.run('Hello')	Output generated, trace sent
7	Tracer collects data	Trace data captured	Data sent to LangSmith UI
8	View traces	Open LangSmith UI	Trace visible for analysis

💡 Tracing setup complete and data sent after chain run

Variable Tracker

Variable	Start	After Step 2	After Step 3	After Step 4	After Step 5	After Step 6	Final
tracer	undefined	LangSmithTracer instance	LangSmithTracer instance	LangSmithTracer instance	LangSmithTracer instance	LangSmithTracer instance	LangSmithTracer instance
llm	undefined	undefined	OpenAI instance	OpenAI instance with tracer	OpenAI instance with tracer	OpenAI instance with tracer	OpenAI instance with tracer
chain	undefined	undefined	undefined	undefined	LLMChain instance	LLMChain instance	LLMChain instance
result	undefined	undefined	undefined	undefined	undefined	Output string	Output string

Key Moments - 2 Insights

Why do we attach the tracer to the LLM instead of the chain?

The tracer is attached to the LLM because it captures the calls and responses of the language model itself. The chain uses the LLM, so tracing the LLM covers the core operations. This is shown in execution_table step 4 where llm.tracer is set.

What happens if we run the chain without setting the tracer?

If the tracer is not set on the LLM, no trace data is collected or sent. The chain still runs and produces output, but tracing is inactive. This is implied by the absence of tracer in variable_tracker before step 4.

Visual Quiz - 3 Questions

Look at the execution_table at step 6, what happens when chain.run('Hello') is called?

A The OpenAI LLM is instantiated

B The tracer is created

C The chain generates output and sends trace data

D The prompt is defined

💡 Hint

Refer to execution_table row with Step 6 describing chain.run action and result

According to variable_tracker, when does the 'tracer' variable get its instance value?

A After Step 2

B After Step 3

C After Step 5

D After Step 6

💡 Hint

Check variable_tracker row for 'tracer' and see when it changes from undefined

If we did not assign llm.tracer = tracer, what would change in the execution?

A The chain would fail to run

B Trace data would not be collected during chain.run

C The tracer would not be created

D The prompt would not be set

💡 Hint

Look at key_moments explaining the importance of attaching tracer to llm

Concept Snapshot

Setting up LangSmith tracing:
1. Import LangSmithTracer
2. Create tracer instance
3. Attach tracer to your LLM (e.g., OpenAI)
4. Run your LangChain code
5. Tracer collects and sends trace data
6. View traces in LangSmith UI

Full Transcript

To set up LangSmith tracing, first import the LangSmithTracer class. Then create an instance of it. Next, create your language model object, such as OpenAI. Attach the tracer instance to the llm by setting llm.tracer = tracer. After this, create your LangChain chain using the llm. When you run the chain with input, the tracer collects data about the calls and responses. This data is sent to the LangSmith UI where you can view detailed traces of your language model usage. Without attaching the tracer to the llm, no trace data is collected even if the chain runs successfully.