Gemini AI Wrapper

The Astralog Gemini wrapper transparently monitors all your interactions with the Gemini API. It captures token usage, prompts, completions, and latency.

View on GitHub

Installation

pip install astralog-gemini astralog google-generativeai

Setup

# agent.py
import google.generativeai as genai
from astralog import Client
from astralog_gemini import track_gemini

astralog_client = Client(api_key="ast_sk_live_xxxxxxxxxxxxx")
genai.configure(api_key="AIza...")

model = genai.GenerativeModel('gemini-1.5-flash')

# Seamlessly wrap the Gemini model
tracked_model = track_gemini(model, astralog_client, model_name="gemini-1.5-flash")

# Use it normally. The wrapper will automatically extract:
# - Total tokens consumed
# - Model used
# - Call latency
# - Full prompts and responses
response = tracked_model.generate_content("Hello!")

Cost Control & Visibility

By wrapping your LLM clients, Astralog generates specific ai_inference events in ClickHouse. You can use our Query Interface to instantly calculate your total token usage costs by model and detect prompt injections or hallucination anomalies.