everyrow-sdk

# everyrow SDK

The everyrow SDK provides intelligent data processing utilities powered by AI agents. Use this skill when writing Python code that needs to:
- Rank/score rows based on qualitative criteria
- Deduplicate data using semantic understanding
- Merge tables using AI-powered matching
- Screen/filter rows based on research-intensive criteria
- Run AI agents over dataframe rows

## Installation

```bash
pip install everyrow
```

## Configuration

Before writing any everyrow code, check if `EVERYROW_API_KEY` is set. If not, prompt the user:

> everyrow requires an API key. Do you have one?
> - If yes, paste it here
> - If no, get one at https://everyrow.io/api-key and paste it back

Once the user provides the key, set it:

```bash
export EVERYROW_API_KEY=<their_key>
```

## Results

All operations return a result object. The data is available as a pandas DataFrame in `result.data`:

```python
result = await rank(...)
print(result.data.head())  # pandas DataFrame
```

## Operations

For quick one-off operations, sessions are created automatically.

### rank - Score and rank rows

Score rows based on criteria you can't put in a database field:

```python
from everyrow.ops import rank

result = await rank(
    task="Score by likelihood to need data integration solutions",
    input=leads_dataframe,
    field_name="integration_need_score",
)
print(result.data.head())
```

### dedupe - Deduplicate data

Remove duplicates using AI-powered semantic matching. The AI understands that "AbbVie Inc", "Abbvie", and "AbbVie Pharmaceutical" are the same company:

```python
from everyrow.ops import dedupe

result = await dedupe(
    input=crm_data,
    equivalence_relation="Two entries are duplicates if they represent the same legal entity",
)
print(result.data.head())
```

Results include `equivalence_class_id` (groups duplicates), `equivalence_class_name` (human-readable cluster name), and `selected` (the canonical record in each cluster).

### merge - Merge tables with AI