> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt
> Use this file to discover all available pages before exploring further.
# Use prompt in logging
> Monitor a prompt in production and get detailed metrics.
## Overview
Prompt logging gives you visibility into how your prompts perform in real-world applications. Track usage patterns, identify issues, and make data-driven improvements to your AI interactions.
## Why monitor prompts?
* **Measure performance metrics:** Track token usage, request volume, latency, and error rates to understand your prompt's efficiency.
* **Compare version performance:** Identify your best-performing prompt variants with side-by-side metric comparisons.
* **Analyze request distribution:** See exactly how your LLM traffic is distributed across different prompts.
## Quickstart
You need to first [create a prompt](/documentation/products/prompt_management/quickstart) in Keywords AI, and find the **prompt ID** in Prompts.
Although you might already defined the configuration for a prompt like model, temperature, etc, you should still pass those parameters in the payload.
You don't need to pass things like token-related parameters, we'll calculate them for you, but you need to pass time-related parameters like generation time, ttft, etc.
```python Python {10-15} theme={"system"}
import requests
url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
"model": "claude-3-5-sonnet-20240620",
"completion_message": {
"role": "assistant",
"content": "Hi, how can I assist you today?"
},
"prompt": {
"prompt_id": "xxxxxx", # prompt ID in UI
"variables": {
# You can pass variables in the prompt if you defined any variables in the UI
},
},
"generation_time": 5.7,
"ttft": 3.1,
}
headers = {
"Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
"Content-Type": "application/json"
}
response = requests.request("POST", url, headers=headers, json=payload)
```
```typescript Typescript {13-18} theme={"system"}
const url = 'https://api.keywordsai.co/api/request-logs/create/';
const headers = {
'Authorization': 'Bearer YOUR_KEYWORDS_AI_API_KEY',
'Content-Type': 'application/json'
};
const payload = {
model: 'claude-3-5-sonnet-20240620',
completion_message: {
role: "assistant",
content: "Hi, how can I assist you today?"
},
prompt: {
prompt_id: "xxxxxx", // prompt ID in UI
variables: {
// You can pass variables in the prompt if you defined any variables in the UI
},
},
generation_time: 5.7,
ttft: 3.1,
};
fetch(url, {
method: 'POST',
headers: headers,
body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => {
console.log(data);
})
```
Read [Prompt in LLM gateway](/documentation/products/prompt_management/management_collaboration/version_control) to know how to integrate prompts into your codebase, once you integrate prompts into the LLM gateway, you will have the prompt metrics and usage automatically logged.
Integrate prompts into gateway
### Variables logging
When you make a request through the Logging API, you can send the prompt variables in the `prompt_messages` field. Just simply wrap your prompt variables in pairs of `{{}}`.
Learn how to use the **Logging API [here](/documentation/products/logs/quickstart)**.
**Example:**
```json theme={"system"}
"prompt": {
"prompt_id": "xxxxxx", // prompt ID in UI
"variables": {"language": "Python","task_description": "Square a number", "specific_library": "math"}
}
```
**Example:**
```json theme={"system"}
"model": "gpt-4o-mini",
"prompt": {
"prompt_id": "xxxxxx",
"variables": {"language": "Python","task_description": "Square a number", "specific_library": "math"}
}
```
Yes, you can log variables in LLM logs even if you haven't created a prompt in Keywords AI. You can pass the variables in the `variables` field.
Check out the [tutorial here](/documentation/products/logs/log_variables).
### External prompt logging
If you dont want to create any prompt in Keywords AI but you still want to log your prompts, you can pass your prompt ID in the `prompt_id` field, and set `is_custom_prompt` to `true` so the system knows it's a custom prompt.
**Example code**
```python Logging API Python{16-17} theme={"system"}
import requests
url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
"model": "claude-3-5-sonnet-20240620",
"prompt_messages": [
{
"role": "user",
"content": "Hi"
},
],
"completion_message": {
"role": "assistant",
"content": "Hi, how can I assist you today?"
},
"prompt_id": "xxxxxx", # any prompt ID you want
"is_custom_prompt": true,
"generation_time": 5.7
}
headers = {
"Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
"Content-Type": "application/json"
}
response = requests.request("POST", url, headers=headers, json=payload)
```
```typescript Typescript {11-12} theme={"system"}
const url = 'https://api.keywordsai.co/api/request-logs/create/';
const headers = {
'Authorization': 'Bearer YOUR_KEYWORDS_AI_API_KEY',
'Content-Type': 'application/json'
};
const payload = {
model: 'claude-3-5-sonnet-20240620',
prompt_messages: [{role: 'user', content: 'Hi'}],
completion_message: {role: 'assistant', content: 'Hi, how can I assist you today?'},
prompt_id: 'xxxxxx',
is_custom_prompt: true,
generation_time: 5.7
}
fetch(url, {
method: 'POST',
headers: headers,
body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => {
console.log(data);
})
```
You can then see the prompt metrics in Dashboard and Logs.