vitaai 0.2.0

Python SDK for VitaAI self-hosted LLM endpoints — drop-in Gemini API replacement

vitaai · Python SDK

Drop-in Python SDK for VitaAI self-hosted LLM endpoints.
Designed to mirror the Google Gemini SDK interface exactly — so migrating existing Gemini projects takes changing one import.

Base URL: https://api.vitaai-api.com

---

Install

pip install vitaai            # stdlib only (urllib)
pip install vitaai[requests]  # recommended — better streaming

---

Quick start

from vitaai import VitaAI

client = VitaAI(api_key="your-key")
# or set VITAAI_API_KEY env var and just call VitaAI()

response = client.models.generate_content(
    model="gemma3-27b",
    contents="Explain how AI works in a few words",
)
print(response.text)

---

Usage

Generate content

response = client.models.generate_content(
    model="gemma3-27b",
    contents="What is the capital of France?",
)
print(response.text)                          # "Paris"
print(response.usage_metadata.total_token_count)

Multi-turn conversation

response = client.models.generate_content(
    model="gemma3-27b",
    contents=[
        {"role": "user",  "parts": [{"text": "My name is Alex."}]},
        {"role": "model", "parts": [{"text": "Nice to meet you, Alex!"}]},
        {"role": "user",  "parts": [{"text": "What's my name?"}]},
    ],
)
print(response.text)   # "Your name is Alex."

System instruction

response = client.models.generate_content(
    model="gemma3-27b",
    contents="Tell me a joke.",
    system_instruction="You are a dry, deadpan comedian. Keep it under 2 sentences.",
)
print(response.text)

Generation config

response = client.models.generate_content(
    model="gemma3-27b",
    contents="Write a product description for a smart water bottle.",
    generation_config={
        "temperature": 0.8,
        "max_output_tokens": 256,
        "top_p": 0.95,
    },
)
print(response.text)

Streaming

for chunk in client.models.generate_content_stream(
    model="gemma3-27b",
    contents="Write a short story about a robot who learns to paint.",
):
    print(chunk.text, end="", flush=True)
    if chunk.is_final:
        print()   # newline after stream ends

Embeddings

result = client.models.embed_content(
    model="nomic-embed-text",
    contents="The quick brown fox jumps over the lazy dog",
    task_type="RETRIEVAL_DOCUMENT",
)
vector = result.embedding.values   # List[float]
print(f"Embedding dim: {len(vector)}")

List available models

for model in client.models.list():
    print(model["name"], model.get("displayName", ""))

---

Custom endpoint (GCP deployment)

When you deploy your own model on Google Cloud Run or Vertex AI:

client = VitaAI(
    api_key="your-key",
    base_url="https://your-cloud-run-service-xyz.a.run.app",
)

Or set the env var:

export VITAAI_BASE_URL="https://your-cloud-run-service-xyz.a.run.app"
export VITAAI_API_KEY="your-key"

---

Migration from Google Gemini

Before (google.genai)	After (vitaai)
from google import genai	from vitaai import VitaAI
client = genai.Client()	client = VitaAI()
client.models.generate_content(...)	client.models.generate_content(...)
response.text	response.text ✅ same
response.usage_metadata	response.usage_metadata ✅ same

---

Expected endpoint contract

Your self-hosted backend must expose these routes:

Method	Path	Purpose
POST	/v1/models/generate	Text generation
POST	/v1/models/generate (stream: true)	Streaming
POST	/v1/models/embed	Embeddings
GET	/v1/models/list	List models

See docs/endpoint-spec.md for the full request/response schema.

---

Environment variables

Variable	Description
VITAAI_API_KEY	API key (alternative to passing api_key=)
VITAAI_BASE_URL	Override base URL