pip install langsmith

undefined

from langsmith import traceable
from openai import OpenAI

client = OpenAI()

@traceable
def generate_response(prompt: str) -> str:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content

undefined

from langsmith.wrappers import wrap_openai
from openai import OpenAI

undefined

from langsmith import traceable

@traceable(run_type="chain")
def process_query(query: str) -> str:
    # Parent run
    context = retrieve_context(query)  # Child run
    response = generate_answer(query, context)  # Child run
    return response

@traceable(run_type="retriever")
def retrieve_context(query: str) -> list:
    return vector_store.search(query)

@traceable(run_type="llm")
def generate_answer(query: str, context: list) -> str:
    return llm.invoke(f"Context: {context}\n\nQuestion: {query}")

import os
os.environ["LANGSMITH_PROJECT"] = "my-project"

undefined

from langsmith import Client

client = Client()

undefined

from langsmith import Client

client = Client()

undefined

from langsmith import evaluate

def my_model(inputs: dict) -> dict:
    # Your model logic
    return {"answer": generate_answer(inputs["question"])}

def correctness_evaluator(run, example):
    prediction = run.outputs["answer"]
    reference = example.outputs["answer"]
    score = 1.0 if reference.lower() in prediction.lower() else 0.0
    return {"key": "correctness", "score": score}

results = evaluate(
    my_model,
    data="qa-test-set",
    evaluators=[correctness_evaluator],
    experiment_prefix="v1"
)

print(f"Average score: {results.aggregate_metrics['correctness']}")

from langsmith.evaluation import LangChainStringEvaluator

undefined

from langsmith import tracing_context

with tracing_context(
    project_name="experiment-1",
    tags=["production", "v2"],
    metadata={"version": "2.0"}
):
    # All traceable calls inherit context
    result = my_function()

from langsmith import trace

with trace(
    name="custom_operation",
    run_type="tool",
    inputs={"query": "test"}
) as run:
    result = do_something()
    run.end(outputs={"result": result})

def sanitize_inputs(inputs: dict) -> dict:
    if "password" in inputs:
        inputs["password"] = "***"
    return inputs

@traceable(process_inputs=sanitize_inputs)
def login(username: str, password: str):
    return authenticate(username, password)

import os
os.environ["LANGSMITH_TRACING_SAMPLING_RATE"] = "0.1"  # 10% sampling

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

undefined

from langsmith import Client

client = Client()

undefined

from langsmith import AsyncClient

async def main():
    client = AsyncClient()

    runs = []
    async for run in client.list_runs(project_name="my-project"):
        runs.append(run)

    return runs

from langsmith import Client

client = Client()

undefined

from langsmith import test

@test
def test_qa_accuracy():
    result = my_qa_function("What is Python?")
    assert "programming" in result.lower()

from langsmith import evaluate

def run_evaluation():
    results = evaluate(
        my_model,
        data="regression-test-set",
        evaluators=[accuracy_evaluator]
    )

    # Fail CI if accuracy drops
    assert results.aggregate_metrics["accuracy"] >= 0.9, \
        f"Accuracy {results.aggregate_metrics['accuracy']} below threshold"

import os

**High latency from tracing:**
```python

**Large payloads:**
```python

undefined