Get started with LangWatch Skills in seconds: Set up evals, scenario tests, and tracing just by asking your AI coding assistant.
import requests
url = "https://app.langwatch.ai/api/evaluations/v3/runs/{runId}"
headers = {"X-Auth-Token": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text){
"runId": "<string>",
"progress": 123,
"total": 123,
"startedAt": 123,
"finishedAt": 123,
"summary": {
"runId": "<string>",
"totalCells": 123,
"completedCells": 123,
"failedCells": 123,
"duration": 123,
"runUrl": "<string>"
},
"error": "<string>"
}Get the current status of an evaluation run for polling. Returns progress while running, and summary when completed.
import requests
url = "https://app.langwatch.ai/api/evaluations/v3/runs/{runId}"
headers = {"X-Auth-Token": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text){
"runId": "<string>",
"progress": 123,
"total": 123,
"startedAt": 123,
"finishedAt": 123,
"summary": {
"runId": "<string>",
"totalCells": 123,
"completedCells": 123,
"failedCells": 123,
"duration": 123,
"runUrl": "<string>"
},
"error": "<string>"
}Documentation Index
Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI.
The run ID returned from POST /api/evaluations/v3/{slug}/run
Run status
pending, running, completed, failed, stopped Number of cells completed
Total number of cells
Unix timestamp when run started
Unix timestamp when run finished (only present when completed/failed/stopped)
Execution summary (only present when completed)
Show child attributes
Error message (only present when failed)
Was this page helpful?