DSPy

DSPy (Declarative Self-improving Python) is a framework for programmatically building and optimizing language model pipelines. Instead of manually tuning brittle prompt strings, you define structured input/output Signatures and compose workflows using modules like Predict, ChainOfThought, or ReAct. DSPy automatically compiles and optimizes prompt instructions and few-shot demonstrations against your evaluation metrics.

Setup

Install the DSPy library:

pip install -U dspy

export NEOSANTARA_API_KEY="nsk_your_api_key_here"

NEOSANTARA_API_KEY=nsk_your_api_key_here

$env:NEOSANTARA_API_KEY="nsk_your_api_key_here"

Client Configuration

Initialize your language model using the dspy.LM class with the neosantara/<model> prefix.

import os
import dspy

lm = dspy.LM(
    "neosantara/deepseek-v4.1-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)

dspy.configure(lm=lm)

Basic Modules: Predict and ChainOfThought

import os
import dspy

lm = dspy.LM(
    "neosantara/gemini-3.8-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)
dspy.configure(lm=lm)

class BasicQA(dspy.Signature):
    """Answer technical questions concisely."""
    question = dspy.InputField(desc="User question")
    answer = dspy.OutputField(desc="Concise answer in 1-2 sentences")

qa = dspy.Predict(BasicQA)
response = qa(question="What is the primary difference between input and output tokens in an LLM gateway?")

print(response.answer)

import os
import dspy

lm = dspy.LM(
    "neosantara/deepseek-v4.1-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)
dspy.configure(lm=lm)

class MathProblem(dspy.Signature):
    """Solve math questions with step-by-step reasoning."""
    problem = dspy.InputField()
    solution = dspy.OutputField()

cot = dspy.ChainOfThought(MathProblem)
result = cot(problem="A server processes 120 requests per second. Each request consumes 400 input tokens. How many input tokens does the server receive per minute?")

print(result.solution)

ReAct Agent with Tools

Use dspy.ReAct to build autonomous agents that invoke Python tools before synthesizing a final answer.

import os
import dspy

lm = dspy.LM(
    "openai/deepseek-v4.1-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"],
    api_base="https://api.neosantara.xyz/v1"
)
dspy.configure(lm=lm)

def get_server_load(region: str) -> str:
    """Return simulated CPU load and active instances for a region."""
    return f"Region {region}: 34% average CPU utilization, 12 healthy pods."

react = dspy.ReAct(
    "question: str -> answer: str",
    tools=[get_server_load]
)

pred = react(question="What is the current server health in the jkt-1 region?")
print(pred.answer)

Frameworks

Tools & Widgets

Setup

Client Configuration

Basic Modules: Predict and ChainOfThought

ReAct Agent with Tools

Next Steps

​Setup

​Client Configuration

​Basic Modules: Predict and ChainOfThought

​ReAct Agent with Tools

​Next Steps

Setup

Client Configuration

Basic Modules: Predict and ChainOfThought

ReAct Agent with Tools

Next Steps