# LangSmith

> Build and manage LangSmith datasets (create datasets, add examples, and find existing datasets) for evaluating your LLM apps.

App · AI Models · 3 actions. Web page: https://docs.lodol.com/docs/integrations/langsmith

## Actions

### Create dataset

Create a new LangSmith dataset to collect examples in.

**Inputs**

- Name (`name`, text, required): A name for the dataset.
- Description (`description`, text): Optional description of the dataset.
- Data type (`data_type`, text): The kind of examples this dataset holds. One of: `kv` (Key-value (general data)), `llm` (LLM (prompt / completion text)), `chat` (Chat (message lists)). Default: `kv`.

**Outputs**

- `created_at` (text): When it was created (ISO 8601).
- `data_type` (text): The dataset's data type.
- `description` (text): The dataset description.
- `example_count` (number): Number of examples in the dataset.
- `id` (text): The new dataset's ID.
- `name` (text): The dataset name.

**Example output**

```json
{
  "created_at": "2026-07-31T12:00:00Z",
  "data_type": "kv",
  "description": "Golden QA pairs",
  "example_count": 0,
  "id": "3f29a1e2-8c4b-4f7a-9c1a-1b2c3d4e5f60",
  "name": "QA regression set"
}
```

### Create example

Add an input/output example to a LangSmith dataset.

**Inputs**

- Dataset (`dataset_id`, text, required): The dataset to add the example to.
- Inputs (`inputs`, object, required): The example's inputs, as fields and values (for example, question: 'What is 2+2?').
- Outputs (`outputs`, object): Optional expected outputs, as fields and values (for example, answer: '4').
- Metadata (`metadata`, object): Optional extra details to store with the example.
- Split (`split`, text): Optional split to file the example under (for example, 'train' or 'test'). Defaults to 'base'.

**Outputs**

- `created_at` (text): When it was created (ISO 8601).
- `dataset_id` (text): The dataset the example belongs to.
- `id` (text): The new example's ID.
- `inputs` (object): The example's inputs.
- `outputs` (object): The example's outputs.

**Example output**

```json
{
  "created_at": "2026-07-31T12:05:00Z",
  "dataset_id": "3f29a1e2-8c4b-4f7a-9c1a-1b2c3d4e5f60",
  "id": "7c1d2e3f-4a5b-6c7d-8e9f-0a1b2c3d4e5f",
  "inputs": {
    "question": "What is the capital of France?"
  },
  "outputs": {
    "answer": "Paris"
  }
}
```

### Find datasets

Search your LangSmith datasets by name and type.

**Inputs**

- Name contains (`name_contains`, text): Optional text to match within dataset names. Leave blank to return all datasets.
- Data type (`data_type`, text): Optional. Only return datasets of this type. One of: `kv` (Key-value (general data)), `llm` (LLM (prompt / completion text)), `chat` (Chat (message lists)).
- Max results (`limit`, number): Most datasets to return (1-100). Defaults to 20. From 1 to 100. Default: `20`.

**Outputs**

- `count` (number): How many datasets were returned.
- `datasets` (list): The matching datasets.

**Example output**

```json
{
  "count": 1,
  "datasets": [
    {
      "created_at": "2026-07-31T12:00:00Z",
      "data_type": "kv",
      "description": "Golden QA pairs",
      "example_count": 12,
      "id": "3f29a1e2-8c4b-4f7a-9c1a-1b2c3d4e5f60",
      "name": "QA regression set"
    }
  ]
}
```