Python SDK

Installation

pip install beep-ai-sdk

Basic Usage

from beep_ai_sdk import BeepClient

client = BeepClient(
    base_url="http://localhost:5000",
    api_key="YOUR_API_TOKEN"
)

# Chat completions
response = client.chat.completions.create(
    model="phi-2",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

# Streaming
async for chunk in client.chat.completions.create_stream(
    model="phi-2",
    messages=[{"role": "user", "content": "Tell me a story"}]
):
    print(chunk.choices[0].delta.content, end="")

# Embeddings
embedding = client.embeddings.create(
    model="all-MiniLM-L6-v2",
    input="Hello world"
)

# RAG
results = client.rag.query(
    collection_id="my-docs",
    query="What is RAG?",
    top_k=5
)

# Agents
result = client.agents.execute(
    agent_id="code_reviewer",
    input={"code": "def foo(): pass"}
)

Features

• Full async/await support via httpx
• OpenAI-compatible client interface (drop-in replacement)
• Streaming with async iterators
• Automatic /v1/* URL prefix handling
• Type hints everywhere
• Connection pooling and retry