migration.mdx

title	Migration Guide
icon	person-running

PromptLayer takes less than 5 minutes to setup.

• Sign up for an account at www.promptlayer.com
• Grab an API key from PromptLayer. Find it in settings (click the cog on the top right).

It's super easy to add PromptLayer to an existing project.

Option 1: Use the run Method (Recommended)

The run() method fetches a prompt template from the Prompt Registry, executes it, and logs the result automatically.

# pip install promptlayer
from promptlayer import PromptLayer
promptlayer_client = PromptLayer()

response = promptlayer_client.run(
    prompt_name="my-prompt",
    input_variables={"variable": "value"}
)

// npm install promptlayer
import { PromptLayer } from "promptlayer";
const promptLayerClient = new PromptLayer();

const response = await promptLayerClient.run({
  promptName: "my-prompt",
  inputVariables: { variable: "value" }
});

Option 2: Use log_request for Custom Logging

If you want to keep using your existing LLM client code, use log_request to manually log requests to PromptLayer.

# pip install promptlayer
from openai import OpenAI
from promptlayer import PromptLayer
import time

pl_client = PromptLayer()
client = OpenAI()

messages = [{"role": "user", "content": "Hello!"}]

start = time.time()
completion = client.chat.completions.create(model="gpt-4o", messages=messages)
end = time.time()

pl_client.log_request(
    provider="openai", model="gpt-4o",
    input={"type": "chat", "messages": [{"role": m["role"], "content": [{"type": "text", "text": m["content"]}]} for m in messages]},
    output={"type": "chat", "messages": [{"role": "assistant", "content": [{"type": "text", "text": completion.choices[0].message.content}]}]},
    request_start_time=start, request_end_time=end
)

// npm install promptlayer openai
import { PromptLayer } from "promptlayer";
import OpenAI from "openai";

const plClient = new PromptLayer();
const openai = new OpenAI();

const messages = [{ role: "user", content: "Hello!" }];

const start = Date.now();
const completion = await openai.chat.completions.create({ model: "gpt-4o", messages });
const end = Date.now();

await plClient.logRequest({
  provider: "openai", model: "gpt-4o",
  input: { type: "chat", messages: messages.map(m => ({ role: m.role, content: [{ type: "text", text: m.content }] })) },
  output: { type: "chat", messages: [{ role: "assistant", content: [{ type: "text", text: completion.choices[0].message.content }] }] },
  requestStartTime: start, requestEndTime: end
});

See the Custom Logging documentation for more details including format converters for OpenAI and Anthropic.