NeatlogsGemini
Neatlogs offers seamless integration with Gemini, Google's AI platform for large language models.
Installation
To get started with Gemini, you'll need to install the package:
pip install neatlogs google-genaiSetting Up API Keys
Before using Gemini with Neatlogs, you need to set up your API keys. You can obtain:
GEMINI_API_KEY: From your Google AI Studio
Then to set them up, you can either export them as environment variables or set them in a .env file:
GEMINI_API_KEY="your_gemini_api_key_here"Then load the environment variables in your Python code:
from dotenv import load_dotenv
import os
# Load environment variables from .env file
load_dotenv()
os.getenv("GEMINI_API_KEY")Usage
Once you've set up your Gemini integration, integrating Neatlogs takes just two lines of code:
import neatlogs
neatlogs.init(api_key="<YOUR_API_KEY>")Examples
Here's a simple example of how to use Gemini with Neatlogs:
from google import genai
from dotenv import load_dotenv
import os
import neatlogs
import agentops
agentops.init("api_key", )
# Load environment variables from .env file
load_dotenv()
neatlogs.init(
api_key="<PROJECT_API_KEY>")
# Initialize the GenAI client with the API key
client = genai.Client(api_key=os.getenv('GEMINI_API_KEY'))
# Function to generate content using the GenAI client
def generate_response(prompt, model_name):
response = client.models.generate_content(
model="gemini-2.5-flash",
contents=[{
"role": "user",
"parts": [{"text": prompt}]
}])
return response.text
# Main loop for interacting with the user
while True:
# Get user input
query = input("> ")
# Generate the response
response = generate_response(query, model_name='gemini-2.5-flash')
# Print the response
print(f"🤖: {response}")
After that, every API call is automatically traced and visualized in Neatlogs, perfect for debugging, evaluating and collaborating.
For more information on Gemini, check out their comprehensive documentation.