Skip to main content

IBM watsonx.ai

WatsonxLLM is a wrapper for IBM watsonx.ai foundation models.

This example shows how to communicate with watsonx.ai models using LangChain.

Setting up​

Install the package langchain-ibm.

!pip install -qU langchain-ibm

This cell defines the WML credentials required to work with watsonx Foundation Model inferencing.

Action: Provide the IBM Cloud user API key. For details, see documentation.

import os
from getpass import getpass

watsonx_api_key = getpass()
os.environ["WATSONX_APIKEY"] = watsonx_api_key

Additionaly you are able to pass additional secrets as an environment variable.

import os

os.environ["WATSONX_URL"] = "your service instance url"
os.environ["WATSONX_TOKEN"] = "your token for accessing the CPD cluster"
os.environ["WATSONX_PASSWORD"] = "your password for accessing the CPD cluster"
os.environ["WATSONX_USERNAME"] = "your username for accessing the CPD cluster"
os.environ["WATSONX_INSTANCE_ID"] = "your instance_id for accessing the CPD cluster"

Load the model​

You might need to adjust model parameters for different models or tasks. For details, refer to documentation.

parameters = {
"decoding_method": "sample",
"max_new_tokens": 100,
"min_new_tokens": 1,
"temperature": 0.5,
"top_k": 50,
"top_p": 1,
}

Initialize the WatsonxLLM class with previously set parameters.

Note:

  • To provide context for the API call, you must add project_id or space_id. For more information see documentation.
  • Depending on the region of your provisioned service instance, use one of the urls described here.

In this example, we’ll use the project_id and Dallas url.

You need to specify model_id that will be used for inferencing. All avaliable models you can find in documentation.

from langchain_ibm import WatsonxLLM

watsonx_llm = WatsonxLLM(
model_id="ibm/granite-13b-instruct-v2",
url="https://us-south.ml.cloud.ibm.com",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)

Alternatively you can use Cloud Pak for Data credentials. For details, see documentation.

watsonx_llm = WatsonxLLM(
model_id="ibm/granite-13b-instruct-v2",
url="PASTE YOUR URL HERE",
username="PASTE YOUR USERNAME HERE",
password="PASTE YOUR PASSWORD HERE",
instance_id="openshift",
version="4.8",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)

Instead of model_id, you can also pass the deployment_id of the previously tuned model. The entire model tuning workflow is described here.

watsonx_llm = WatsonxLLM(
deployment_id="PASTE YOUR DEPLOYMENT_ID HERE",
url="https://us-south.ml.cloud.ibm.com",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)

Create Chain​

Create PromptTemplate objects which will be responsible for creating a random question.

from langchain.prompts import PromptTemplate

template = "Generate a random question about {topic}: Question: "
prompt = PromptTemplate.from_template(template)

Provide a topic and run the LLMChain.

from langchain.chains import LLMChain

llm_chain = LLMChain(prompt=prompt, llm=watsonx_llm)
llm_chain.invoke("dog")
{'topic': 'dog', 'text': 'Why do dogs howl?'}

Calling the Model Directly​

To obtain completions, you can call the model directly using a string prompt.

# Calling a single prompt

watsonx_llm.invoke("Who is man's best friend?")
"Man's best friend is his dog. "
# Calling multiple prompts

watsonx_llm.generate(
[
"The fastest dog in the world?",
"Describe your chosen dog breed",
]
)
LLMResult(generations=[[Generation(text='The fastest dog in the world is the greyhound, which can run up to 45 miles per hour. This is about the same speed as a human running down a track. Greyhounds are very fast because they have long legs, a streamlined body, and a strong tail. They can run this fast for short distances, but they can also run for long distances, like a marathon. ', generation_info={'finish_reason': 'eos_token'})], [Generation(text='The Beagle is a scent hound, meaning it is bred to hunt by following a trail of scents.', generation_info={'finish_reason': 'eos_token'})]], llm_output={'token_usage': {'generated_token_count': 106, 'input_token_count': 13}, 'model_id': 'ibm/granite-13b-instruct-v2', 'deployment_id': ''}, run=[RunInfo(run_id=UUID('52cb421d-b63f-4c5f-9b04-d4770c664725')), RunInfo(run_id=UUID('df2ea606-1622-4ed7-8d5d-8f6e068b71c4'))])

Streaming the Model output​

You can stream the model output.

for chunk in watsonx_llm.stream(
"Describe your favorite breed of dog and why it is your favorite."
):
print(chunk, end="")
My favorite breed of dog is a Labrador Retriever. Labradors are my favorite because they are extremely smart, very friendly, and love to be with people. They are also very playful and love to run around and have a lot of energy.