IBM watsonx is a comprehensive, integrated AI platform designed to facilitate end-to-end AI application development. It provides access to a diverse range of enterprise-grade models that are not only performant and trusted but also cost-effective. Users can leverage IBM Granite models, select open-source models from Hugging Face, third-party models from strategic partners, and even custom foundation models, making it a versatile solution for various AI needs.

With HoneyHive, you can trace all your operations using a single line of code. Find a list of all supported integrations here.

​
HoneyHive Setup

Follow the HoneyHive Installation Guide to get your API key and initialize the tracer.

​
watsonx Setup

Go to your Profile in IBM Cloud to get your IBM watsonx IAM API key. Then, go to your Project and get your IBM project ID, which is a UUID.

​
Example

Here is an example of how to trace your code in HoneyHive.

from ibm_watson_machine_learning.foundation_models import Model
from honeyhive import HoneyHiveTracer

HoneyHiveTracer.init(
    api_key="MY_HONEYHIVE_API_KEY",
    project='MY_HONEYHIVE_PROJECT_NAME',
)


def get_credentials():
    return {
        "url": "https://us-south.ml.cloud.ibm.com", # or another region
        "apikey": "MY_IBM_IAM_API_KEY",
    }

model_id = "ibm/granite-3-2b-instruct"
parameters = {
    "decoding_method": "sample",
    "max_new_tokens": 60,
    "min_new_tokens": 10,
    "random_seed": 42,
    "temperature": 0.9,
    "top_k": 50,
    "top_p": 1,
    "repetition_penalty": 2
}

model = Model(
    model_id=model_id,
    params=parameters,
    credentials=get_credentials(),
    project_id="MY_IBM_PROJECT_ID",
)

prompt_input = "Which IBM model beat Gary Kasparov in chess?"
generated_response = model.generate(prompt=prompt_input)

print(generated_response['results'][0]['generated_text'])

​
View your Traces

Once you run your code, you can view your execution trace in the HoneyHive UI by clicking the Data Store tab on the left sidebar.