Metadata-Version: 2.4
Name: dotevals
Version: 0.26.0
Summary: Simple and robust LLM evaluations
Author: .txt
Project-URL: repository, https://github.com/dottxt-ai/dotevals
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: click
Requires-Dist: pytest
Requires-Dist: rich
Requires-Dist: jsonschema
Requires-Dist: tenacity
Requires-Dist: nest-asyncio
Requires-Dist: Pillow
Provides-Extra: test
Requires-Dist: pytest-asyncio; extra == "test"
Requires-Dist: pre-commit; extra == "test"
Requires-Dist: pytest-cov; extra == "test"
Requires-Dist: coverage[toml]>=5.1; extra == "test"
Requires-Dist: diff-cover; extra == "test"
Requires-Dist: Pillow; extra == "test"
Provides-Extra: docs
Requires-Dist: mkdocs; extra == "docs"
Requires-Dist: mkdocstrings[python]; extra == "docs"
Requires-Dist: mkdocs-material[imaging]; extra == "docs"
Requires-Dist: mkdocs-mermaid2-plugin; extra == "docs"
Requires-Dist: mkdocs-section-index; extra == "docs"
Requires-Dist: mkdocs-git-committers-plugin-2; extra == "docs"
Requires-Dist: mkdocs-git-revision-date-localized-plugin; extra == "docs"

<div align="center" style="margin-bottom: 1em;">

<img src="./docs/assets/images/dotevals-logo-light.svg#gh-light-mode-only" alt="Dotevals Logo" width=300></img>
<img src="./docs/assets/images/dotevals-logo-dark.svg#gh-dark-mode-only" alt="Dotevals Logo" width=300></img>

*Write Once, Evaluate Anywhere*

</div>

## Why dotevals?

Just like everyone, we had to write evaluations. They needed to run with structured generation, use complex datasets, run at scale, and allow for easy exploration of failure modes. We looked around, but couldn't find what we needed. So dotevals was born.

- **No YAML, just Python** - Write evaluations as functions.
- **Works with pytest** - Integrate with CI/CD, use parametrization and fixtures.
- **Resumable** - Evaluations crash. dotevals picks them up where they left off.
- **Extensible** - Plugin architecture for any dataset, evaluator, storage or LLM.
- **Scale when needed** - Run dozens of experiments in parallel without changing the code.

### The dotevals philosophy

<div align="center"><img src="./docs/assets/images/use_philosophy.png" width=600></img></div>

Evaluations are just functions over data. Write a single function, we will handle running it at scale with:

- Failure recovery.
- Automatic and configurable concurrency.
- Result persistence.
- Resource management using pytest fixtures.

Focus on what to evaluate, not how to run evaluations.

## Quick Start

Getting started with `dotevals` is simple:

### 1. Install dotevals

```bash
pip install dotevals  # Core functionality with basic evaluators
pip install dotevals-datasets-common  # Common benchmark datasets (GSM8K, MMLU, etc.)
```


### 2. Create a model

``` python
import outlines
import openai

model = outlines.from_openai(openai.AsyncOpenAI() "gpt4o")
```

### 3. Write the evaluation function

```python
from dotevals import foreach
from dotevals.evaluators import numeric_match

dataset = [
    ("What is 2+2?", "4"),
    ("How many days are there in a week?", "7")
]

@foreach("question,answer", dataset)
def eval_math(question, answer):
    response = model(question)
    return numeric_match(response, answer)
```

### 4. Run interactively (notebooks/scripts)

```python
from dotevals import run

# Run evaluation and get immediate results
results = run(eval_math)

# View summary
print(results.summary())
# {'total': 2, 'errors': 0, 'metrics': {'numeric_match': {'accuracy': 1.0}}}
```

### 5. Run with pytest (CI/CD)

```bash
pytest eval_math.py --experiment my_evaluation
dotevals show my_evaluation  # View results
```

## Examples

Here are some examples that show how dotevals solves common problems:

<details><summary><b>🧮 Evaluate GPT-5 on GSM8K</b></summary>

``` python
import outlines
from openai import AsyncOpenAI
import pytest

@pytest.fixture()
def gpt5():
    model = outlines.from_openai(AsyncOpenAI(), "gpt-5")
    return model


@foreach.gsm8k("test")
async def eval_gsm8k(question, reasoning, answer, gpt5):
    result = model(prompt)
    result = extract_answer(result)

    return numeric_match(result, answer)
```
</details>

<details><summary><b>📊 Compare GPT-5 with Opus-4.1 on GSM8K</b></summary>

``` python
import outlines
from transformers import AutoTokenizer, AutoModelForCausalLM
import pytest

@pytest.fixture()
def models(request):
    provider_name, model_name = request.param.split(":")

    if provider_name == "openai":
        from openai import AsyncOpenAI
        return outlines.from_openai(AsyncOpenAI(), model_name)
    elif provider_name == "anthropic":
        from anthropic import AsyncAnthropic
        return outlines.from_anthropic(AsyncAnthropic(), model_name)
    else:
        raise ValueError(f"Model {model_name} for {provider_name} is not available")


@pytest.mark.parametrize("model_names", ["openai:gpt-5", "anthropic:opus-4.1"], indirect=True)
@foreach.gsm8k("test")
def eval_gsm8k(question, schema, model_names, models):
    result = model(prompt, schema)
    result = extract_answer(result)

    return numeric_match(result, answer)
```
</details>


<details><summary><b>🏗️ Evaluate Phi-3.5 with structured outputs on BFCL simple</b></summary>

``` python
import outlines
from transformers import AutoTokenizer, AutoModelForCausalLM
import pytest

@pytest.fixture()
def phi():
    tf_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-mini-Instruct")
    tf_tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-Instruct")
    model = outlines.from_transformers(tf_model, hf_tokenizer)
    return model


@foreach.bfcl("simple")
def eval_gsm8k(question, schema, phi):
    result = model(prompt, schema)
    result = extract_answer(result)

    return numeric_match(result, answer
```
</details>

<details><summary><b>⚡ Maximize throughput on a vLLM instance</b></summary>

Start by installing the vLLM plugin:

``` bash
pip install dotevals-vllm
```

``` python
import outlines
from transformers import AutoTokenizer, AutoModelForCausalLM
import pytest

@pytest.fixture()
def phi(vllm):
    """
    The vLLM plugin provides a fixture that allows you to spin, use and shut down a vLLM instance locally.

    """
    handle = vllm.setup("Phi-3.5.-mini-instruct")
    yield handle.client
    handle.shutdown()


foreach = ForEach(concurrency=Adaptive())

@foreach.bfcl("simple")
def eval_gsm8k(question, schema, phi):
    result = model(prompt, schema)
    result = extract_answer(result)

    return numeric_match(result, answer)
```
</details>

<details><summary><b>📦 Store results in S3</b></summary>

You don't need to change your experiment's implementation, just install the S3 plugin and run the experiment with the `storage` option set to `s3`. The S3 plugin also provides other options to parametrize the storage.

``` bash
pip install dotevals-s3
```

``` bash
pytest --experiment experiment_name --storage s3 --bucket xxx
```
</details>


<details><summary><b>🧑‍⚖️ Use LLM-as-a-judge evaluators</b></summary>

You can define custom evaluators. We encourage you to develop a plugin to make it as easy as

``` bash
pip install dotevals-llm-as-a-judge
```

</details>


## Extensible by Design

dotevals is built with a plugin architecture that lets you extend every component:

<details><summary><b>🔌 Use Any LLM</b></summary>

```python
# Models are provided via pytest fixtures
@pytest.fixture
def model():
    """Your model as a pytest fixture."""
    return load_your_model()  # OpenAI, Anthropic, HuggingFace, etc.

@foreach("prompt,expected", dataset)
def eval_with_model(prompt, expected, model):
    response = model.generate(prompt)
    return exact_match(response, expected)

# For Modal deployment (pip install dotevals-modal)
# The vllm_client fixture is automatically provided
@foreach("prompt,expected", dataset)
async def eval_modal(prompt, expected, vllm_client):
    response = await vllm_client.agenerate(prompt)
    return exact_match(response, expected)
```
</details>


<details><summary><b>💾 Store Anywhere</b></summary>

```bash
# JSON files (default)
pytest eval.py --storage json://.dotevals

# SQLite with SQL queries
pytest eval.py --storage sqlite://results.db

# Your custom backend
pytest eval.py --storage s3://bucket/path
```
</details>


<details><summary><b>🚀 Run Anywhere</b></summary>

```python
# Local execution (default)
@foreach("input,output", dataset)
def eval_local(input, output, model):
    return exact_match(model(input), output)

# Distributed on Modal (pip install dotevals-modal)
@foreach("question,answer", dataset)
async def eval_distributed(question, answer, vllm_client):
    # vllm_client automatically injected by Modal runner
    response = await vllm_client.agenerate(question)
    return exact_match(response, answer)

# Run with: pytest eval.py --runner modal --modal-model meta-llama/Llama-3-8b
```
</details>


<details><summary><b>📊 Evaluate Anything</b></summary>

```python
from dotevals.evaluators import evaluator
from dotevals.metrics import accuracy

# Built-in evaluators
from dotevals.evaluators import (
    exact_match,      # String equality
    numeric_match,    # Numeric comparison
    valid_json,       # JSON validation
    ast_evaluation,   # Function call validation
)

# Create custom evaluators in 4 lines
@evaluator(metrics=accuracy())
def domain_specific_match(response, expected):
    # Your evaluation logic
    return your_validation(response, expected)

# LLM-based evaluators (pip install dotevals-evaluators-llm)
from dotevals.evaluators import (
    llm_judge,           # LLM-based evaluation
    semantic_similarity, # Embedding similarity
    factual_consistency, # Fact checking
)
```
</details>


<details><summary><b>🔧 Execute however you want</b></summary>

When `@foreach` and `@batch` aren't enough, create your own execution strategy:

```python
# Custom executor for async batch APIs (e.g., OpenAI Batch API)
@async_batch("question", dataset, model=gpt4_batch)
def eval_reasoning(question: list[str]) -> list[Result]:
    responses = model.generate(question)
    return [judge_reasoning(r) for r in responses]

# Returns immediately, processes in background
handle = eval_reasoning(session_manager)
results = handle.wait()  # Get results when ready
```

Build executors for:
- **Async APIs**: Submit jobs and poll for results
- **Streaming endpoints**: Process data as it arrives
- **Custom infrastructure**: GPU batching, distributed workers
- **Special workflows**: Checkpointing, caching, fallback strategies

Switch execution without changing evaluation logic - debug with `@foreach`, scale with `@async_batch`.
</details>


## About .txt

<div align="center">
<img src="./docs/assets/images/dottxt-light.svg#gh-light-mode-only" alt="dottxt logo" width=100></img>
<img src="./docs/assets/images/dottxt-dark.svg#gh-dark-mode-only" alt="dottxt logo" width=100></img>
</div>

Dotevals is developed and maintained by [.txt](https://dottxt.co), a company dedicated to making LLMs more reliable for production applications.

Our focus is on advancing structured generation technology through:

- 🧪 **Cutting-edge Research**: We publish our findings on [structured generation](http://blog.dottxt.co/performance-gsm8k.html)
- 🚀 **Enterprise-grade solutions**: You can license [our enterprise-grade libraries](https://docs.dottxt.co).
- 🧩 **Open Source Collaboration**: We believe in building in public and contributing to the community

Follow us on [Twitter](https://twitter.com/dottxtai) or check out our [blog](https://blog.dottxt.co/) to stay updated on our latest work in making LLMs more reliable.

## Contributing

We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details.

## License

MIT License - see [LICENSE](LICENSE) for details.
