Metadata-Version: 2.4
Name: bibliotheca-client
Version: 0.1.0
Summary: Python client library for Bibliotheca data exploration platform
Home-page: https://pantology.io/anthology
Author: Pantology Team
Author-email: Pantology Team <hi@pantology.io>
License: Apache-2.0
Project-URL: Homepage, https://pantology.io/anthology
Project-URL: Documentation, https://pantology.io/anthology
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.28.0
Requires-Dist: pandas>=1.5.0
Requires-Dist: sqlglot>=20.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: mypy>=0.990; extra == "dev"
Dynamic: author
Dynamic: home-page
Dynamic: requires-python

# Bibliotheca Client SDK

Python client library for interacting with the Bibliotheca data exploration platform.

## Installation

```bash
pip install bibliotheca-client
```

Or install from source:

```bash
cd client-sdk
pip install -e .
```

## Quick Start

```python
from bibliotheca_client import BibliothecaClient

# Initialize the client with your API key
client = BibliothecaClient(
    base_url="https://anthology.pantology.io/apis",
    api_key="bib_xxxxxxxxxx..."  # Get from https://anthology.pantology.io/api-keys
)

# Check your usage and tier
usage = client.get_usage()
print(f"Tier: {usage['tier_name']}")
print(f"Tokens Used: {usage['tokens_used_today']} / {usage['daily_limit']}")

# Generate hypotheses for data exploration
hypotheses = client.generate_hypotheses(
    user_grouping="my-database",
    user_context="I want to understand sales trends"
)

for hypothesis in hypotheses:
    print(f"{hypothesis['title']}: {hypothesis['question']}")

# Generate SQL from natural language
result = client.generate_sql(
    session_id="my-session-123",
    user_question="What are the top 10 products by revenue?",
    user_grouping="my-database",
    run_debugger=True,
    debugging_rounds=2
)

print(result['GeneratedSQL'])
```

## Authentication

The Bibliotheca API uses API key authentication. Here's how to get your API key:

### Getting Your API Key

1. Log in to Bibliotheca at https://anthology.pantology.io
2. Click **"API Keys"** in the left sidebar (🔑 icon)
3. Click **"Create New API Key"**
4. Copy your API key (shown only once!)
5. Use it in your code or set as environment variable

### Using API Keys

```python
from bibliotheca_client import BibliothecaClient

# Option 1: Direct initialization
client = BibliothecaClient(
    base_url="https://anthology.pantology.io/apis",
    api_key="bib_xxxxxxxxxx..."
)

# Option 2: From environment variable (recommended)
import os
client = BibliothecaClient(
    base_url=os.getenv('BIBLIOTHECA_BACKEND_URL', 'https://anthology.pantology.io/apis'),
    api_key=os.getenv('BIBLIOTHECA_API_KEY')
)
```

### API Key Security Best Practices

- **Never commit API keys to version control**
- Use environment variables: `export BIBLIOTHECA_API_KEY='bib_xxx'`
- Revoke keys immediately if compromised
- Manage keys in the UI at https://anthology.pantology.io/api-keys

### Rate Limits

API keys have different tiers:
- **Free**: 10,000 tokens/day (~12-13 queries)
- **Plus**: 100,000 tokens/day (~125 queries)
- **Premium**: Custom limits

Check your usage:
```python
usage = client.get_usage()
print(f"Tokens remaining: {usage['tokens_remaining']}")
```

## API Reference

### BibliothecaClient

#### `__init__(base_url: str, api_key: str = None, id_token: str = None)`
Initialize the client with backend URL and API key.

**Parameters:**
- `base_url`: Backend API endpoint URL
- `api_key`: API key from https://anthology.pantology.io/api-keys (recommended)
- `id_token`: Firebase ID token (legacy, for backward compatibility)

#### `generate_hypotheses(user_grouping: str, hypothesis_model: str = 'gemini-2.5-pro', user_context: str = "") -> List[Dict]`
Generate data exploration hypotheses based on database schema.

**Parameters:**
- `user_grouping`: Database grouping identifier
- `hypothesis_model`: LLM model for hypothesis generation
- `user_context`: Optional context about exploration goals

**Returns:** List of hypothesis dictionaries with `title`, `description`, and `question` fields.

#### `generate_sql(session_id: str, user_question: str, user_grouping: str, **kwargs) -> Dict`
Generate SQL query from natural language question.

**Parameters:**
- `session_id`: Session identifier for conversation tracking
- `user_question`: Natural language question
- `user_grouping`: Database grouping identifier
- Additional optional parameters for model configuration

**Returns:** Dictionary with `ResponseCode`, `GeneratedSQL`, `SessionId`, and `Error` fields.

#### `get_available_databases() -> List[Dict]`
Get list of available databases/groupings.

**Returns:** List of database schema information.

#### `get_usage() -> Dict`
Get current API key usage and tier information.

**Returns:** Dictionary with `tier_name`, `tokens_used_today`, `daily_limit`, `tokens_remaining`, and `resets_at` fields.

#### `list_api_keys() -> Dict`
List all API keys associated with your account.

**Returns:** Dictionary with `keys` list and `tier` information.

#### `revoke_api_key(key_id: str) -> Dict`
Revoke an API key (useful if compromised).

**Parameters:**
- `key_id`: The key ID to revoke

**Returns:** Success/error response.

#### `translate_sql(sql: str, target_dialect: str) -> str`
Translate SQL between different database dialects (e.g., PostgreSQL to BigQuery).

**Parameters:**
- `sql`: Source SQL query
- `target_dialect`: Target SQL dialect (e.g., 'bigquery', 'postgres', 'spark')

**Returns:** Translated SQL query string.

#### `update_token(id_token: str)`
Update the authentication token (legacy method for Firebase tokens).

## Development

### Setup Development Environment

```bash
cd client-sdk
pip install -e ".[dev]"
```

### Running Tests

```bash
pytest
```

### Code Formatting

```bash
black bibliotheca_client/
```

## License

Apache License 2.0

## Support

For issues and questions, please email us at hi@pantology.io
