SDK oficial da Camile AI — plataforma de IA empresarial
Project description
Camile AI — SDK Python
SDK oficial da Camile AI — plataforma de IA empresarial com agentes autônomos, RAG, capacidades modulares e multi-tenancy.
Instalação
pip install camile-ai
Uso Básico
Chat
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
# 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
# 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)
# 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
# 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
Desenvolvimento
# 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
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
camile_ai-0.1.0.tar.gz
(10.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
camile_ai-0.1.0-py3-none-any.whl
(13.0 kB
view details)
File details
Details for the file camile_ai-0.1.0.tar.gz.
File metadata
- Download URL: camile_ai-0.1.0.tar.gz
- Upload date:
- Size: 10.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fe8bb42d82a8b7d7641aa1b308655eafb647720dd89624898afcf2d1bce67daa
|
|
| MD5 |
f89ffc4c92a34bdad0fdd80bbe056887
|
|
| BLAKE2b-256 |
54c5f34168a65c5344f9998e0040ef3f383136a6ea67777107f4f01fa2f78b4d
|
File details
Details for the file camile_ai-0.1.0-py3-none-any.whl.
File metadata
- Download URL: camile_ai-0.1.0-py3-none-any.whl
- Upload date:
- Size: 13.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d46aa96c34d1a688f2dcd57c8e0618b36d572879a30317f481207583aa7e2273
|
|
| MD5 |
73b49469cdb28136c1d2075b286db4c6
|
|
| BLAKE2b-256 |
464b2d713618eed1fc663b9eea0f42c5fc597087f946a9e4aedcb7b6c3eef078
|