> ## Documentation Index
> Fetch the complete documentation index at: https://fairforge.alquimia.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# API Reference Overview
> Complete API reference for Fair Forge
# API Reference
Complete API documentation for all Fair Forge modules.
## Modules
Toxicity, Bias, Context, Conversational, Humanity, BestOf
BaseGenerator, context loaders, strategies
AlquimiaRunner, BaseRunner interface
Dataset, Batch, metric-specific schemas
## Import Patterns
### Metrics
```python theme={null}
from fair_forge.metrics.toxicity import Toxicity
from fair_forge.metrics.bias import Bias
from fair_forge.metrics.context import Context
from fair_forge.metrics.conversational import Conversational
from fair_forge.metrics.humanity import Humanity
from fair_forge.metrics.best_of import BestOf
```
### Core
```python theme={null}
from fair_forge.core.retriever import Retriever
from fair_forge.core.base import FairForge
from fair_forge.core.guardian import Guardian
from fair_forge.core.sentiment import SentimentAnalyzer
```
### Schemas
```python theme={null}
from fair_forge.schemas.common import Dataset, Batch
from fair_forge.schemas.toxicity import ToxicityMetric
from fair_forge.schemas.bias import BiasMetric, GuardianLLMConfig
```
### Statistical
```python theme={null}
from fair_forge.statistical import FrequentistMode, BayesianMode
from fair_forge.statistical.base import StatisticalMode
```
### Generators
```python theme={null}
from fair_forge.generators import (
BaseGenerator,
create_markdown_loader,
SequentialStrategy,
RandomSamplingStrategy,
)
```
### Runners
```python theme={null}
from fair_forge.runners import AlquimiaRunner
from fair_forge.schemas.runner import BaseRunner
```
### Storage
```python theme={null}
from fair_forge.storage import (
create_local_storage,
create_lakefs_storage,
)
```
### Guardians
```python theme={null}
from fair_forge.guardians import LLamaGuard, IBMGranite
from fair_forge.guardians.llms.providers import OpenAIGuardianProvider
```
## Quick Reference
### Run a Metric
```python theme={null}
results = Metric.run(
RetrieverClass,
**metric_parameters,
verbose=True,
)
```
### Create a Retriever
```python theme={null}
class MyRetriever(Retriever):
def load_dataset(self) -> list[Dataset]:
return [Dataset(...)]
```
### Generate Test Data
```python theme={null}
datasets = await generator.generate_dataset(
context_loader=loader,
source="./docs",
assistant_id="my-assistant",
num_queries_per_chunk=3,
)
```
### Execute Tests
```python theme={null}
updated_dataset, summary = await runner.run_dataset(dataset)
```
## Next Steps
Detailed metrics reference
Data structure reference