# @empiricalrun/scorer

## 0.4.0

### Minor Changes

- f61545c: feat: add support for js/ts scripts as scorers

### Patch Changes

- @empiricalrun/ai@0.10.1

## 0.3.1

### Patch Changes

- Updated dependencies [a9c04d8]
- Updated dependencies [b379e7f]
  - @empiricalrun/ai@0.10.1

## 0.3.0

### Minor Changes

- 740a844: feat: add support for merging inputs and add multi-turn chat example

### Patch Changes

- @empiricalrun/ai@0.10.0

## 0.2.3

### Patch Changes

- Updated dependencies [973c9b2]
- Updated dependencies [f3b632e]
- Updated dependencies [0b2d1c0]
  - @empiricalrun/ai@0.10.0

## 0.2.2

### Patch Changes

- Updated dependencies [d6d8b5c]
- Updated dependencies [bde6bf0]
- Updated dependencies [93e12e0]
  - @empiricalrun/ai@0.9.0

## 0.2.1

### Patch Changes

- c7e5a4a: chore: remove sql semantic scorer
- 9f15c2d: feat: py-script scorer has a simpler return type
- Updated dependencies [2b0cc32]
- Updated dependencies [51f2f52]
  - @empiricalrun/ai@0.8.0

## 0.2.0

### Minor Changes

- 2517c74: feat: add support for openai assistants
- 215c54a: chore: change scorer names to json-syntax and llm-critic

### Patch Changes

- bc3aa56: fix: py-script getting timed out
- 2ad19be: chore: better error messages for scorer names
- Updated dependencies [2517c74]
- Updated dependencies [bc3aa56]
  - @empiricalrun/ai@0.7.0

## 0.1.10

### Patch Changes

- 4150b1f: fix: typo in chat prompt type
- Updated dependencies [ba98ebb]
- Updated dependencies [d81cff4]
- Updated dependencies [4150b1f]
  - @empiricalrun/ai@0.6.1

## 0.1.9

### Patch Changes

- Updated dependencies [7a67267]
  - @empiricalrun/ai@0.6.0

## 0.1.8

### Patch Changes

- Updated dependencies [66cddb3]
  - @empiricalrun/ai@0.5.0

## 0.1.7

### Patch Changes

- Updated dependencies [ac10032]
  - @empiricalrun/ai@0.4.2

## 0.1.6

### Patch Changes

- Updated dependencies [a952bd9]
  - @empiricalrun/ai@0.4.1

## 0.1.5

### Patch Changes

- 5079335: fix: sql syntax scorer should fail for empty output
- b065dad: chore: improve message string for valid sql-syntax
- 2bc5465: fix: minor improvements for execution accuracy in spider example
- Updated dependencies [e77b76e]
- Updated dependencies [9822db6]
- Updated dependencies [06b1667]
- Updated dependencies [bbd5cd0]
- Updated dependencies [2bc5465]
  - @empiricalrun/ai@0.4.0

## 0.1.4

### Patch Changes

- Updated dependencies [a94aa16]
  - @empiricalrun/ai@0.3.0

## 0.1.3

### Patch Changes

- b354507: fix: change script value property to path in run
- d7f4b53: fix: python script scorer should prefer config.name
- Updated dependencies [b354507]
- Updated dependencies [90082c8]
- Updated dependencies [a9e840a]
- Updated dependencies [b3cb527]
- Updated dependencies [a4cfb49]
  - @empiricalrun/ai@0.2.0

## 0.1.2

### Patch Changes

- 571986a: chore: update npm package license
- Updated dependencies [571986a]
- Updated dependencies [4a858f5]
  - @empiricalrun/ai@0.1.1

## 0.1.1

### Patch Changes

- 424f994: feat: add run summary in the header

## 0.1.0

### Minor Changes

- 8787bf0: feat: add run summary in cli
- dbb2abb: first version of empirical package

### Patch Changes

- Updated dependencies [8787bf0]
- Updated dependencies [dbb2abb]
  - @empiricalrun/ai@0.1.0