POST
/
api
/
request-logs
url = "https://api.keywordsai.co/api/request-logs/?page=1&sort_by=-id&is_test=false&all_envs=false&fetch_filters=false&page_size=1"


from urllib.parse import urlencode
params = {
    "page": 1,
    "sort_by": "-id",
    "is_test": "false",
    "all_envs": "false",
    "fetch_filters": "false",
    "page_size": 1
}
url = f"https://api.keywordsai.co/api/request-logs/?{urlencode(params)}"
headers = {
    "Authorization": f"Api-Key {YOUR_KEYWORDS_AI_API_KEY}",
}
data = {
    "filters": {}
}
response = requests.post(url, headers=headers, json=data)

{
    "results": [
       {
        "unique_id": "xxxxx",
        "organization_key__name": "Keywords AI Default",
        "organization": "Keywords AI",
        "user": "hendrix@keywordsai.co",
        "is_example": false,
        "status": "success",
        "prompt_tokens": 452,
        "completion_tokens": 89,
        "cost": 0.0005869,
        "prompt_messages": [
                {
                    "role": "system",
                    "content": "You are a helpful assistant"
                },
                {
                    "role": "user",
                    "content": "What is Keywords AI?"
                }
        ],
        "completion_message": {
                "role": "assistant",
                "content": "Keywords AI is a unified DevOps platform for AI products."
        },
        "latency": 1.2114145755767822,
        "model": "gpt-3.5-turbo",
        "foundation_model": "gpt-3.5-turbo",
        "provider_id": "openai",
        "tool_choice": null,
        "tools": null,
        "tool_calls": null,
        "timestamp": "2024-06-24T21:33:06.601353Z",
        "failed": false,
        "time_to_first_token": null,
        "routing_time": 0.0,
        "metadata": {
            // any params you want to pass in the request
            },
        "stream": false,
        "status_code": 200,
        "customer_identifier": "123456",
        "customer_email": "",
        "used_custom_credential": false,
       // ... other models ... 
       },
    ]
}

The Logs List endpoint allows you to get the past logs with specified filters.

​
Query params

You can add these params to the URL params. For example:

"https://api.keywordsai.co/api/request-logs/?page=1&sort_by=-id&is_test=false&all_envs=false&fetch_filters=false&page_size=1"
​
sort_by
string
required

The field to sort by. Default is -id (same as sort by -timestamp, but with better performance). - is for descending order, if not provided, it will be in ascending order.

​
all_envs
string
default:"false"

Whether to include logs from all environments. is_test parameter will override this parameter. Options: true, false.

​
is_test
string
default:"false"

Whether the log is a test call or not. This parameter will override the all_envs parameter. Options: true, false.

​
fetch_filters
string
default:"false"

Whether to retrieve the available filtering options. Enabling this could slow down the response time. Options: true, false.

​
page_size
number
default:100

The number of logs to return per page. Maximum is 1000.

​
page
number
default:1

The page number of the current logs.

​
POST params

You can add these params to the body:

url = "https://api.keywordsai.co/api/request-logs/"
headers = {
    "Authorization": f"Api-Key {YOUR_KEYWORDS_AI_API_KEY}",
}
data = {
    "filters":    {
      "cost": {
        "operator": "gt",
        "value": [0.01]
      },
    }
}
response = requests.post(url, headers=headers, json=data)
​
filters
object
default:{}

The filters be applied to the logs. For available options in the response body, use the fetch_filters parameter.

​
operator
string
required

Default is "" (equal).

url = "https://api.keywordsai.co/api/request-logs/?page=1&sort_by=-id&is_test=false&all_envs=false&fetch_filters=false&page_size=1"


from urllib.parse import urlencode
params = {
    "page": 1,
    "sort_by": "-id",
    "is_test": "false",
    "all_envs": "false",
    "fetch_filters": "false",
    "page_size": 1
}
url = f"https://api.keywordsai.co/api/request-logs/?{urlencode(params)}"
headers = {
    "Authorization": f"Api-Key {YOUR_KEYWORDS_AI_API_KEY}",
}
data = {
    "filters": {}
}
response = requests.post(url, headers=headers, json=data)

{
    "results": [
       {
        "unique_id": "xxxxx",
        "organization_key__name": "Keywords AI Default",
        "organization": "Keywords AI",
        "user": "hendrix@keywordsai.co",
        "is_example": false,
        "status": "success",
        "prompt_tokens": 452,
        "completion_tokens": 89,
        "cost": 0.0005869,
        "prompt_messages": [
                {
                    "role": "system",
                    "content": "You are a helpful assistant"
                },
                {
                    "role": "user",
                    "content": "What is Keywords AI?"
                }
        ],
        "completion_message": {
                "role": "assistant",
                "content": "Keywords AI is a unified DevOps platform for AI products."
        },
        "latency": 1.2114145755767822,
        "model": "gpt-3.5-turbo",
        "foundation_model": "gpt-3.5-turbo",
        "provider_id": "openai",
        "tool_choice": null,
        "tools": null,
        "tool_calls": null,
        "timestamp": "2024-06-24T21:33:06.601353Z",
        "failed": false,
        "time_to_first_token": null,
        "routing_time": 0.0,
        "metadata": {
            // any params you want to pass in the request
            },
        "stream": false,
        "status_code": 200,
        "customer_identifier": "123456",
        "customer_email": "",
        "used_custom_credential": false,
       // ... other models ... 
       },
    ]
}

Was this page helpful?

Suggest editsRaise issue