DSPy

Instrument and observe your DSPy application via the DSPyInstrumentor

DSPy is a framework for automatically prompting and fine-tuning language models. It provides composable and declarative APIs that allow developers to describe the architecture of their LLM application in the form of a "module" (inspired by PyTorch's nn.Module). It them compiles these modules using "teleprompters" that optimize the module for a particular task. The term "teleprompter" is meant to evoke "prompting at a distance," and could involve selecting few-shot examples, generating prompts, or fine-tuning language models.

Phoenix makes your DSPy applications observable by visualizing the underlying structure of each call to your compiled DSPy module.

Launch Phoenix

Install packages:

pip install arize-phoenix

Launch Phoenix:

import phoenix as px
px.launch_app()

Connect your notebook to Phoenix:

from phoenix.otel import register

tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
)

By default, notebook instances do not have persistent storage, so your traces will disappear after the notebook is closed. See Persistence or use one of the other deployment options to retain traces.

If you don't want to host an instance of Phoenix yourself or use a notebook instance, you can use a persistent instance provided on our site. Sign up for an Arize Phoenix account athttps://app.phoenix.arize.com/login

Install packages:

pip install arize-phoenix-otel

Connect your application to your cloud instance:

from phoenix.otel import register

tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  endpoint="http://localhost:6006",
)

Your Phoenix API key can be found on the Keys section of your dashboard.

Pull latest Phoenix image from Docker Hub:

docker pull arizephoenix/phoenix:latest

Run your containerized instance:

docker run -p 6006:6006 arizephoenix/phoenix:latest

This will expose the Phoenix on localhost:6006

Install packages:

pip install arize-phoenix-otel

Connect your application to your instance using:

from phoenix.otel import register

tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  endpoint="http://localhost:6006",
)

For more info on using Phoenix with Docker, see Docker

Install packages:

pip install arize-phoenix-otel

Connect your application to your cloud instance:

import os
from phoenix.otel import register

# Add Phoenix API Key for tracing
os.environ["PHOENIX_CLIENT_HEADERS"] = "api_key=...:..."

# configure the Phoenix tracer
register(
  project_name="my-llm-app", # Default is 'default'
  endpoint="https://app.phoenix.arize.com/v1/traces",
)

Your Phoenix API key can be found on the Keys section of your dashboard.

Install

pip install openinference-instrumentation-dspy dspy

Setup

Initialize the DSPyInstrumentor before your application code.

from openinference.instrumentation.dspy import DSPyInstrumentor

DSPyInstrumentor().instrument(tracer_provider=tracer_provider)

Run DSPy

Now run invoke your compiled DSPy module. Your traces should appear inside of Phoenix.

class BasicQA(dspy.Signature):
    """Answer questions with short factoid answers."""

    question = dspy.InputField()
    answer = dspy.OutputField(desc="often between 1 and 5 words")


if __name__ == "__main__":
    turbo = dspy.OpenAI(model="gpt-3.5-turbo")

    dspy.settings.configure(lm=turbo)

    with using_attributes(
        session_id="my-test-session",
        user_id="my-test-user",
        metadata={
            "test-int": 1,
            "test-str": "string",
            "test-list": [1, 2, 3],
            "test-dict": {
                "key-1": "val-1",
                "key-2": "val-2",
            },
        },
        tags=["tag-1", "tag-2"],
        prompt_template_version="v1.0",
        prompt_template_variables={
            "city": "Johannesburg",
            "date": "July 11th",
        },
    ):
        # Define the predictor.
        generate_answer = dspy.Predict(BasicQA)

        # Call the predictor on a particular input.
        pred = generate_answer(
            question="What is the capital of the united states?"  # noqa: E501
        )  # noqa: E501
        print(f"Predicted Answer: {pred.answer}")

Observe

Now that you have tracing setup, all predictions will be streamed to your running Phoenix for observability and evaluation.

Resources

PreviousGroq NextVertexAI

Last updated 8 days ago