vitaai 0.4.0

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 — so migrating existing Gemini projects takes changing one import.

---

Install

pip install vitaai

---

Quick start

from vitaai import VitaAI

client = VitaAI(
    api_key="your-api-key",
    base_url="http://your-server-ip:8000"
)

response = client.models.generate_content(
    model="gemma-2b-it",
    contents="What is AI?",
    max_output_tokens=100
)
print(response.text)
print("Tokens:", response.usage_metadata.total_token_count)

---

All endpoints

1. Generate content

response = client.models.generate_content(
    model="gemma-2b-it",
    contents="What is machine learning?",
    max_output_tokens=150
)
print(response.text)
print(response.usage_metadata.total_token_count)

2. Generate with config

response = client.models.generate_content(
    model="gemma-2b-it",
    contents="Explain deep learning",
    config={
        "system_instruction": "You are a teacher. Explain simply.",
        "temperature": 0.7,
        "top_p": 0.9,
        "max_output_tokens": 200
    }
)
print(response.text)

3. Multi-turn conversation

response = client.models.generate_content(
    model="gemma-2b-it",
    contents=[
        {"role": "user",  "parts": [{"text": "My name is Alex."}]},
        {"role": "model", "parts": [{"text": "Nice to meet you, Alex!"}]},
        {"role": "user",  "parts": [{"text": "What is my name?"}]},
    ]
)
print(response.text)

4. Streaming

for chunk in client.models.generate_content_stream(
    model="gemma-2b-it",
    contents="Write a short poem about AI",
    max_output_tokens=100
):
    print(chunk.text, end="", flush=True)
print()

5. Embeddings

response = client.models.embed_content(
    contents="Artificial intelligence is transforming the world"
)
print("Dimensions:", len(response.embedding.values))
print("Values    :", response.embedding.values)

6. Summarize

response = client.models.summarize(
    contents="Long text you want to summarize...",
    format="bullets",       # "paragraph" or "bullets"
    max_output_tokens=150
)
print(response.summary)
print("Tokens:", response.usage_metadata.total_token_count)

7. List available models

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

---

Error handling

from vitaai.transport import AuthenticationError, RateLimitError, ServerError

try:
    response = client.models.generate_content(
        model="gemma-2b-it",
        contents="Hello"
    )
    print(response.text)

except AuthenticationError:
    print("Invalid API key")
except RateLimitError:
    print("Too many requests")
except ServerError:
    print("Server error")
except Exception as e:
    print(f"Error: {e}")

---

Client parameters

Parameter	Type	Default	Description
api_key	str	—	Your API key. Or set VITAAI_API_KEY env var
base_url	str	https://api.vitaai-api.com	Your server URL
timeout	int	120	Request timeout in seconds. Increase for slow CPU servers

client = VitaAI(
    api_key="your-key",
    base_url="http://your-server:8000",
    timeout=300
)

---

config options

Key	Type	Default	Description
system_instruction	str	None	Sets model behaviour
temperature	float	0.7	Randomness (0 = focused, 1 = creative)
top_p	float	0.9	Diversity of responses
max_output_tokens	int	100	Maximum length of response

---

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

---

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
POST	/v1/models/summarize	Summarization
GET	/v1/models/list	List models

---

Environment variables

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