DSPy ReAct Agent Builder

Goal

Build production-quality ReAct agents that use tools to solve complex multi-step tasks with reasoning, acting, and error handling.

When to Use

• Multi-step tasks requiring tool use
• Search + reasoning workflows
• Complex question answering with external data
• Tasks needing calculation, retrieval, or API calls

Related Skills

• Optimize agents: [dspy-gepa-reflective](../dspy-gepa-reflective/SKILL.md)
• Connect MCP tools: [dspy-mcp-tool-integration](../dspy-mcp-tool-integration/SKILL.md)
• Configure native tool calling: [dspy-adapters-multimodal](../dspy-adapters-multimodal/SKILL.md)
• Define signatures: [dspy-signature-designer](../dspy-signature-designer/SKILL.md)
• Evaluate performance: [dspy-evaluation-suite](../dspy-evaluation-suite/SKILL.md)

Inputs

Outputs

Workflow

Phase 1: Define Tools

Tools are Python functions with clear docstrings. The agent uses docstrings to understand tool capabilities:

import dspy

def search(query: str) -> list[str]:
    """Search knowledge base for relevant information.

    Args:
        query: Search query string

    Returns:
        List of relevant text passages
    """
    retriever = dspy.ColBERTv2(url='http://20.102.90.50:2017/wiki17_abstracts')
    results = retriever(query, k=3)
    return [r['text'] for r in results]

def calculate(expression: str) -> float:
    """Safely evaluate mathematical expressions.

    Args:
        expression: Math expression (e.g., "2 + 2", "sqrt(16)")

    Returns:
        Numerical result
    """
    try:
        with dspy.PythonInterpreter() as interpreter:
            return interpreter.execute(expression)
    except Exception as e:
        return f"Error: {e}"

Phase 2: Create ReAct Agent

# Configure LM
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))

# Create agent
agent = dspy.ReAct(
    signature="question -> answer",
    tools=[search, calculate],
    max_iters=5
)

# Use agent
result = agent(question="What is the population of Paris plus 1000?")
print(result.answer)

Phase 3: Production Agent with Error Handling

import dspy
import logging

logger = logging.getLogger(__name__)

class ResearchAgent(dspy.Module):
    """Production agent with error handling and logging."""

    def __init__(self, max_iters: int = 5):
        self.max_iters = max_iters
        self.agent = dspy.ReAct(
            signature="question -> answer",
            tools=[self.search, self.calculate, self.summarize],
            max_iters=max_iters
        )

    def search(self, query: str) -> list[str]:
        """Search for relevant documents."""
        try:
            retriever = dspy.ColBERTv2(
                url='http://20.102.90.50:2017/wiki17_abstracts'
            )
            results = retriever(query, k=5)
            return [r['text'] for r in results]
        except Exception as e:
            logger.error(f"Search failed: {e}")
            return [f"Search unavailable: {e}"]

    def calculate(self, expression: str) -> str:
        """Evaluate mathematical expressions safely."""
        try:
            with dspy.PythonInterpreter() as interpreter:
                return str(interpreter.execute(expression))
        except Exception as e:
            logger.error(f"Calculation failed: {e}")
            return f"Error: {e}"

    def summarize(self, text: str) -> str:
        """Summarize long text into key points."""
        try:
            summarizer = dspy.Predict("text -> summary: str")
            return summarizer(text=text[:1000]).summary
        except Exception as e:
            logger.error(f"Summarization failed: {e}")
            return "Summarization unavailable"

    def forward(self, question: str) -> dspy.Prediction:
        """Execute agent with error handling."""
        try:
            return self.agent(question=question)
        except Exception as e:
            logger.error(f"Agent failed: {e}")
            return dspy.Prediction(answer=f"Error: {e}")

# Usage
agent = ResearchAgent(max_iters=6)
response = agent(question="What is the capital of France and its population?")
print(response.answer)

Phase 4: Optimize with GEPA

ReAct agents benefit from reflective optimization:

from dspy.evaluate import Evaluate

def feedback_metric(example, pred, trace=None, pred_name=None, pred_trace=None):
    """Provide textual feedback for GEPA."""
    is_correct = example.answer.lower() in pred.answer.lower()
    score = 1.0 if is_correct else 0.0
    feedback = "Correct." if is_correct else f"Expected '{example.answer}'. Check tool selection."
    return dspy.Prediction(score=score, feedback=feedback)

# Optimize agent
optimizer = dspy.GEPA(
    metric=feedback_metric,
    reflection_lm=dspy.LM("openai/gpt-4o"),
    auto="medium"
)

compiled = optimizer.compile(agent, trainset=trainset)
compiled.save("research_agent_optimized.json", save_program=False)

Best Practices

1. Clear tool docstrings - Agent relies on docstrings to understand tool capabilities
2. Error handling - All tools should handle failures gracefully and return error messages
3. Tool independence - Test each tool separately before adding to agent
4. Logging - Track tool calls and agent reasoning for debugging
5. Limit iterations - Set reasonable max_iters to prevent infinite loops (default is 20, but 5-10 often sufficient for simpler tasks)

Limitations

• ReAct works best with 3-7 tools; too many tools confuse the agent
• Not all LMs support tool calling equally well (GPT-4 > GPT-3.5)
• Agent may call tools unnecessarily or miss necessary calls
• GEPA can improve production quality when a representative trainset and feedback metric are available
• Tool execution is sequential, not parallelized

Official Documentation

• DSPy Documentation: https://dspy.ai/
• DSPy GitHub: https://github.com/stanfordnlp/dspy
• ReAct Module: https://dspy.ai/api/modules/ReAct/
• Agents Tutorial: https://dspy.ai/tutorials/agents/