Custom Logging

pl_client.log_request(
    provider="provider_name",
    model="model_name",
    input=input_in_blueprint_format,
    output=output_in_blueprint_format,
    # Optional parameters
    request_start_time=start_time,
    request_end_time=end_time,
    prompt_name="template_name",
    prompt_version_number=1,
    prompt_input_variables={"variable": "value"},
    tags=["tag1", "tag2"],
    metadata={"custom_field": "value"}
)

def openai_to_blueprint(messages, completion=None):
    """Convert OpenAI format to PromptLayer blueprint format."""
    # Convert input
    input_blueprint = {
        "type": "chat",
        "messages": [
            {
                "role": msg["role"],
                "content": [{"type": "text", "text": msg["content"]}] 
                if isinstance(msg["content"], str) else msg["content"]
            }
            for msg in messages
        ]
    }
    
    # Convert output if provided
    output_blueprint = None
    if completion:
        if hasattr(completion.choices[0].message, "tool_calls") and completion.choices[0].message.tool_calls:
            # Handle tool calls
            output_blueprint = {
                "type": "chat",
                "messages": [{
                    "role": "assistant",
                    "tool_calls": [
                        {
                            "id": tool_call.id,
                            "type": "function",
                            "function": {
                                "name": tool_call.function.name,
                                "arguments": tool_call.function.arguments
                            }
                        }
                        for tool_call in completion.choices[0].message.tool_calls
                    ]
                }]
            }
        else:
            # Standard response
            output_blueprint = {
                "type": "chat",
                "messages": [{
                    "role": "assistant",
                    "content": [{"type": "text", "text": completion.choices[0].message.content}]
                }]
            }
    
    return input_blueprint, output_blueprint

def anthropic_to_blueprint(messages, system=None, response=None):
    """Convert Anthropic format to PromptLayer blueprint format."""
    # Convert input
    input_blueprint = {
        "type": "chat",
        "messages": []
    }
    
    # Add system message if present
    if system:
        input_blueprint["messages"].append({
            "role": "system",
            "content": [{"type": "text", "text": system}]
        })
    
    # Add conversation messages
    for msg in messages:
        input_blueprint["messages"].append({
            "role": msg["role"],
            "content": [{"type": "text", "text": msg["content"]}]
            if isinstance(msg["content"], str) else msg["content"]
        })
    
    # Convert output if provided
    output_blueprint = None
    if response:
        response_text = ""
        if hasattr(response, "content") and response.content:
            # Get text from first content block
            if hasattr(response.content[0], "text"):
                response_text = response.content[0].text
        
        output_blueprint = {
            "type": "chat",
            "messages": [{
                "role": "assistant",
                "content": [{"type": "text", "text": response_text}]
            }]
        }
    
    return input_blueprint, output_blueprint

from openai import OpenAI
from promptlayer import PromptLayer
import time

# Setup clients
pl_client = PromptLayer(api_key="pl_...")
client = OpenAI()

# Prepare request
messages = [
    {"role": "system", "content": "You are an AI assistant"},
    {"role": "user", "content": "Write a one-sentence bedtime story about a unicorn."}
]

# Execute request
request_start_time = time.time()
completion = client.chat.completions.create(
    model="gpt-4o",
    messages=messages
)
request_end_time = time.time()

# Convert formats
input_blueprint, output_blueprint = openai_to_blueprint(messages, completion)

# Log to PromptLayer
pl_client.log_request(
    provider="openai",
    model="gpt-4o",
    input=input_blueprint,
    output=output_blueprint,
    request_start_time=request_start_time,
    request_end_time=request_end_time,
    input_tokens=completion.usage.prompt_tokens,
    output_tokens=completion.usage.completion_tokens
)

import anthropic
from promptlayer import PromptLayer
import time

# Setup clients
pl_client = PromptLayer(api_key="pl_...")
client = anthropic.Anthropic()

# Prepare request
system = "You are a seasoned data scientist at a Fortune 500 company."
messages = [
    {"role": "user", "content": "Analyze this dataset for anomalies: <dataset>{{DATASET}}</dataset>"}
]

# Execute request
request_start_time = time.time()
response = client.messages.create(
    model="claude-3-7-sonnet-20250219",
    system=system,
    max_tokens=2048,
    messages=messages
)
request_end_time = time.time()

# Convert formats
input_blueprint, output_blueprint = anthropic_to_blueprint(messages, system, response)

# Log to PromptLayer
pl_client.log_request(
    provider="anthropic",
    model="claude-3-7-sonnet-20250219",
    input=input_blueprint,
    output=output_blueprint,
    request_start_time=request_start_time,
    request_end_time=request_end_time,
    input_tokens=response.usage.input_tokens,
    output_tokens=response.usage.output_tokens
)

# Tool call response example
tool_response_blueprint = {
    "type": "chat",
    "messages": [
        # Previous messages...
        {
            "role": "tool",
            "content": [{"type": "text", "text": "{\"temperature\": 72}"}],
            "tool_call_id": "call_abc123"
        }
    ]
}

import { PromptLayer } from "@promptlayer/promptlayer";
import { OpenAI } from "openai";

const plClient = new PromptLayer({ apiKey: "pl_..." });
const openai = new OpenAI();

// Helper function
function openaiToBlueprint(messages, completion = null) {
  const inputBlueprint = {
    type: "chat",
    messages: messages.map(msg => ({
      role: msg.role,
      content: typeof msg.content === "string" 
        ? [{ type: "text", text: msg.content }] 
        : msg.content
    }))
  };
  
  let outputBlueprint = null;
  if (completion) {
    outputBlueprint = {
      type: "chat",
      messages: [{
        role: "assistant",
        content: [{
          type: "text",
          text: completion.choices[0].message.content
        }]
      }]
    };
  }
  
  return { inputBlueprint, outputBlueprint };
}

async function main() {
  const messages = [
    { role: "user", content: "Hello world" }
  ];
  
  const requestStartTime = Date.now();
  const completion = await openai.chat.completions.create({
    model: "gpt-4o",
    messages
  });
  const requestEndTime = Date.now();
  
  const { inputBlueprint, outputBlueprint } = openaiToBlueprint(messages, completion);
  
  await plClient.logRequest({
    provider: "openai",
    model: "gpt-4o",
    input: inputBlueprint,
    output: outputBlueprint,
    requestStartTime,
    requestEndTime,
    inputTokens: completion.usage.prompt_tokens,
    outputTokens: completion.usage.completion_tokens
  });
}

main();