​
Python SDK

Our SDK is designed to be developer-friendly and integrate with your existing infrastructure as well as the larger LLM ecosystem (Langchain, LlamaIndex, Pinecone, Chroma, etc.).

All features within the platform are programmatically accessible via the SDK.

​
Setup HoneyHive and get your API key

If you haven’t already done so, then the first thing you will need to do is create a HoneyHive project.

After creating the project, you can find your API key in the Settings page under Account.

Once you have created a HoneyHive project and got your API keys, you can now start tracing your custom pipeline.

​
Install the SDK & authenticate

We currently support a native Python SDK. For other languages, we encourage using HTTP request libraries to send requests.

pip3 install honeyhive -q

​
Start Logging your LLM Requests

import honeyhive as hh
from honeyhive.sdk.tracer import HoneyHiveTracer
import openai

HONEYHIVE_API_KEY = ""

# replace project and session name here
project_name = "New Project"
name = "Email Writer"

hh.api_key = HONEYHIVE_API_KEY
tracer = HoneyHiveTracer(project=project_name, name=name)

with tracer.model(name):
    # insert api call here

​
Congratulations! You just logged your first LLM response

Logging Traces

How to set up tracing for your AI applications.

Running Evaluations

How to run automated evaluations programmatically via the SDK.

Our documentation is a work in progress. If you have any questions, please reach out to us at dhruv@honeyhive.ai.