Metadata-Version: 2.4
Name: camile-ai
Version: 0.1.0
Summary: SDK oficial da Camile AI — plataforma de IA empresarial
Author-email: Camile AI <dev@camile.ia.br>
License: MIT
Project-URL: Homepage, https://camile.ia.br
Project-URL: Documentation, https://docs.camile.ia.br
Project-URL: Repository, https://github.com/CamileAI/camile
Project-URL: Issues, https://github.com/CamileAI/camile/issues
Keywords: camile,ai,chatbot,agent,rag,llm
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.27.0

# Camile AI — SDK Python

[![PyPI](https://img.shields.io/pypi/v/camile-ai)](https://pypi.org/project/camile-ai/)
[![Python Versions](https://img.shields.io/pypi/pyversions/camile-ai)](https://pypi.org/project/camile-ai/)
[![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE)

SDK oficial da **Camile AI** — plataforma de IA empresarial com agentes autônomos, RAG, capacidades modulares e multi-tenancy.

## Instalação

```bash
pip install camile-ai
```

## Uso Básico

### Chat

```python
from camile import CamileAI

client = CamileAI(api_key="cml_live_sua_chave_aqui")

response = client.chat.completions.create(
    messages=[
        {"role": "system", "content": "Você é um assistente útil."},
        {"role": "user", "content": "Qual é a capital do Brasil?"},
    ],
    model="camile-v1",
)

print(response.choices[0]["message"]["content"])
# → Brasília
```

### Agentes

```python
# Listar agentes
agents = client.agents.list()
for agent in agents:
    print(f"{agent.id}: {agent.name}")

# Criar agente
agent = client.agents.create(
    name="Atendimento",
    description="Agente de atendimento ao cliente",
)

# Executar agente
result = client.agents.execute(
    agent_id=agent.id,
    input="Qual o horário de funcionamento?",
)
print(result["response"])
```

### Capacidades

```python
# Catálogo de capacidades
caps = client.capabilities.list()
for cap in caps:
    print(f"  {cap.icon or '🔧'} {cap.name} — {cap.description}")

# Vincular capacidade a um agente
client.capabilities.attach(agent_id="ag_xxx", slug="web-search")
```

### RAG (Busca Semântica)

```python
# Criar coleção de conhecimento
col = client.rag.create_collection(
    name="Base de conhecimento",
    description="Documentos da empresa",
)

# Buscar informações
results = client.rag.search(
    collection_id=col.id,
    query="Qual o prazo de entrega?",
    top_k=5,
)
for r in results:
    print(f"[{r.score:.2f}] {r.text[:100]}...")
```

### Memória do Agente

```python
# Salvar memória
client.memory.save(
    agent_id="ag_xxx",
    content="Cliente prefere atendimento via WhatsApp",
    type="long_term",
)

# Consultar
memories = client.memory.list(agent_id="ag_xxx")
for mem in memories:
    print(f"  • {mem.content} ({mem.type})")
```

## Documentação

Documentação completa: [docs.camile.ia.br](https://docs.camile.ia.br)

## Desenvolvimento

```bash
# Clone o monorepo
git clone https://github.com/CamileAI/camile.git
cd camile/api/sdk/python

# Instale em modo editável
pip install -e .

# Teste
python -c "from camile import CamileAI; print('SDK carregado com sucesso')"
```

## Licença

MIT © Camile AI
