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.
Get started with LangWatch Skills in seconds: Set up evals, scenario tests, and tracing just by asking your AI coding assistant.
Traces
Datasets
- Overview
- GETList all non-archived datasets for the project
- POSTCreate a new dataset
- POSTCreate a new dataset from an uploaded file
- GETGet a dataset by its slug or id
- GETList records for a dataset
- PATCHUpdate a dataset by its slug or id
- PATCHUpdate or create a record in a dataset
- POSTAdd dataset entries programmatically using the LangWatch API to build evaluation sets for LLM testing and agent validation.
- POSTCreate records in a dataset in batch
- POSTUpload a file
- DELArchive a dataset
- DELDelete records from a dataset by IDs
Evaluators
Built-in Evaluators
Evaluations v3
Monitors
Prompts
Annotations
Scenarios
Scenario Events
Simulation Runs
Suites
Agents
Triggers
Workflows
Dashboards
Graphs
Analytics
Secrets
Projects
Gateway: Virtual Keys
Gateway: Provider Bindings
Gateway: Budgets
Evaluations v3
Overview
Run and monitor evaluation experiments. Start evaluation runs and poll for progress and results.
Was this page helpful?
⌘I