Register Custom Metrics
Galileo GenAI Studio supports Custom Metrics (programmatic or GPT-based) for all your Evaluate and Observe projects. Depending on where, when, and how you want these metrics to be executed, you have the option to choose between Custom Scorers and Registered Scorers.
Registered Scorers
We support registering a scorer such that it can be reused across various runs, projects, modules, and users within your organization. Registered Scorers are run in the backend in an isolated environment that has access to a predefined set of libraries and packages.
Creating Your Registered Scorer
To define a registered scorer, create a Python file that has at least 2 functions and follow the function signatures as described below:
scorer_fn
: The scorer function is provided the row-wise inputs and is expected to generate outputs for each response. The expected signature for this function is:
def scorer_fn(*, index: Union[int, str], response: str, **kwargs: Any) -> Union[float, int, bool, str, None]:
...
We support output of a floating points, integers, boolean values, and strings. Your scorer_fn
must accept **kwargs
as the last parameter so that your registered scorer is forward-compatible.
-
aggregator_fn
: The aggregator function takes in an array of the row-wise outputs from your scorer and allows you to generate aggregates from those. The expected signature for the aggregator function is:def aggregator_fn(*, scores: List[Union[float, int, bool, str, None]]) -> Dict[str, Union[float, int, bool, str, None]]: ...
For aggregated values that you want to output from your scorer, return them as key-value pairs with the key corresponding to the label and the value.
-
(Optional, but recommended)
score_type
: The scorer_type function is used to define theType
of the score that your scorer generates. The expected signature for this function is:def score_type() -> Type[float] | Type[int] | Type[str] | Type[bool]: ...
Note that the return type is a
Type
object likefloat
, not the actual type itself. Defining this function is necessary for sorting and filtering by scores to work correctly. If you don’t define this function, the scorer is assumed to generatefloat
scores by default. -
(Optional)
scoreable_node_types_fn
: If you want to restrict your scorer to only run on specific node types, you can define this function which returns a list of node types that your scorer should run on. The expected signature for this function is:def scoreable_node_types_fn() -> List[str]: ...
If you don’t define this function, your scorer will run on
llm
andchat
nodes by default.
Registering Your Scorer
Once you’ve created your scorer file, you can register it with the name and the scorer file:
registered_scorer = pq.register_scorer(scorer_name="my-scorer", scorer_file="/path/to/scorer/file.py")
The name you choose here will be the name with which the values for this scorer appear in the UI later.
Using Your Registered Scorer
To use your scorer during a prompt run (or sweep), simply pass it in alongside any of the other scorers:
pq.run(..., scorers=[registered_scorer])
If you created your registered scorer in a previous session, you can also just pass in the name to the scorer instead of the object as:
pq.run(..., scorers=["my-scorer"])
Example
For example, let’s say we wanted to create a custom metric that measured the length of the response. In our Python environment, we would define an executor
function, an aggregator
function, and create a CustomScorer
object.
- Create a
scorer.py
file:
from typing import List, Dict, Type
def scorer_fn(*, response: str, **kwargs) -> int:
return len(response)
def aggregator_fn(*, scores: List[str]) -> Dict[str, int]:
return {
"Total Response Length": sum(scores),
"Average Response Length": sum(scores) / len(scores),
}
def score_type() -> Type:
return int
def scoreable_node_types_fn() -> List[str]:
return ["llm", "chat"]
-
Register the scorer:
pq.register_scorer("response_length", "scorer.py")
-
Use the scorer in your prompt run:
pq.run(..., scorers=["response_length"])
Note that registered scorer can only take response
as the input - if you want to pass in other fields in the custom metric, please use the custom scorer above
Execution Environment
Your scorer will be executed in a Python 3.10 environment. The Python libraries available for your use are:
numpy~=1.26.4
pandas~=2.2.2
pydantic~=2.7.1
scikit-learn~=1.4.2
tensorflow~=2.16.1
networkx
openai
Please note that we regularly update the minor and patch versions of these packages. Major version updates are infrequent but if a library is critical to your scorer, please let us know and we’ll provide 1+ week of warning before updating the major versions for those.
What if I need to use other libraries or packages?
If you need to use other libraries or packages, you may use ‘Custom Scorers’. Custom Scorers are run on your notebook environment. Because they run locally, they won’t be available for runs created from the UI or for Observe projects.
Registered Scorers | Custom Scorers | |
---|---|---|
Creating the custom metric | Created from the Python client, can be activated through the UI. | Created via the Python client |
Sharing across the organization | Accessible within the Galileo console across different projects and modules | Outside Galileo, accessible only to the current project |
Accessible modules | Evaluate and Observe | Evaluate |
Scorer Definition | As an independent Python file | Within the notebook |
Execution Environment | Server-side | Within your Python environment |
Python Libraries available | Limited to a Galileo provided execution environment | Any library within your virtual environment |
Execution Resources | Restricted by Galileo | Any resources available to your local instance |
How do I create a local “Custom Scorer”?
Custom scorers can be created from two Python functions (executor
and aggrator
function as defined below). Common types include:
-
Heuristics/custom rules: checking for regex matches or presence/absence of certain keywords or phrases.
-
model-guided: utilizing a pre-trained model to check for specific entities (e.g. PERSON, ORG), or asking an LLM to grade the quality of the output.
For example, for that registered scorer we created to calculate response length, here is the custom scorer equivalent:
Note that the naming of the functions are different: they are **executor**
and **aggregator**
instead of scorer_fn
and aggregator_fn
.
def executor(row) -> float:
return len(row.response)
def aggregator(scores, indices) -> dict:
return {'Total Response Length': sum(scores),
# You can have multiple aggregate summaries for your metric.
'Average Response Length': sum(scores)/len(scores)}
my_scorer = pq.CustomScorer(name='Response Length', executor=executor, aggregator=aggregator)
To register your scorer, you would just pass it through your scorers
parameter inside pq.run
or pq.run_sweep:
template = "Explain {topic} to me like I'm a 5 year old"
data = {"topic": ["Quantum Physics", "Politics", "Large Language Models"]}
pq.run(template = my_template, dataset = data, scorers=[my_scorer])
For more docs on custom metrics, visit our promptquality
docs.
Once you complete a run, your custom metric can be used to evaluate responses for that specific project.
Note that custom scorer can only be used in the Evaluate module - if you want to use a custom metric to evaluate live traffic (Observe module), you’ll need to use the registered scorers below.
Was this page helpful?