LiteLLM

Neatlogs offers seamless integration with LiteLLM, a lightweight library that provides a unified interface to call any LLM API.

Installation

To get started with LiteLLM, you'll need to install the package:

pip install neatlogs litellm

Setting Up API Keys

Before using LiteLLM with Neatlogs, you need to set up your API keys. You can obtain:

• LITELLM_API_KEY: From your LiteLLM Dashboard
• PROJECT_API_KEY: From your Neatlogs Dashboard
• Provider-specific keys (e.g., OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)

Then to set them up, you can either export them as environment variables or set them in a .env file:

LITELLM_API_KEY="your_litellm_api_key_here"
OPENAI_API_KEY="your_openai_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("LITELLM_API_KEY")
os.getenv("OPENAI_API_KEY")

Usage

Once you've set up your LiteLLM 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 LiteLLM with Neatlogs:

import neatlogs
import litellm
from dotenv import load_dotenv
import os

# Load environment variables from .env file
load_dotenv()

# Initialize Neatlogs
neatlogs.init(api_key="YOUR_API_KEY")

# Set your API keys
litellm.api_key = os.getenv("OPENAI_API_KEY")  # or other provider key

# Make a completion request
response = litellm.completion(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ]
)

print(response.choices[0].message.content)

After that, every API call is automatically traced and visualized in Neatlogs, perfect for debugging, evaluating and collaborating.

For more information on LiteLLM, check out their comprehensive documentation.