# create_feedback_config

> **Method** in `langsmith`

📖 [View in docs](https://reference.langchain.com/python/langsmith/client/Client/create_feedback_config)

Create a feedback configuration.

Defines how feedback with a given key should be interpreted.
If an identical configuration already exists for the key, it is
returned unchanged. If a different configuration already exists
for the key, an error is raised.

## Signature

```python
create_feedback_config(
    self,
    feedback_key: str,
    *,
    feedback_config: ls_schemas.FeedbackConfig,
    is_lower_score_better: Optional[bool] = False,
) -> ls_schemas.FeedbackConfigSchema
```

## Description

**Example:**

.. code-block:: python

from langsmith import Client

client = Client()
config = client.create_feedback_config(
    feedback_key="user-rating",
    feedback_config={
        "type": "continuous",
        "min": 0.0,
        "max": 5.0,
    },
)

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `feedback_key` | `str` | Yes |  The feedback key to configure. |
| `feedback_config` | `FeedbackConfig` | Yes |  The configuration defining type, bounds, and categories. |
| `is_lower_score_better` | `Optional[bool]` | No |  Whether a lower score is considered better. Defaults to False. (default: `False`) |

## Returns

`ls_schemas.FeedbackConfigSchema`

The created or existing feedback
configuration.

---

[View source on GitHub](https://github.com/langchain-ai/langsmith-sdk/blob/ce9e9e8973442b33e98ec3ce1b9c2dd3f58a43a7/python/langsmith/client.py#L8029)