Files
skills/public/dspy-signatures.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

523 lines
26 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>dspy-signatures</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/dspy-signatures.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/dspy-signatures">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/dspy-signatures.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>dspy-signatures</h1><p class="lede">Defining input/output signatures for DSPy modules and language model tasks</p><h1>DSPy Signatures</h1>
<p><strong>Scope</strong>: Signature syntax, field types, typed signatures, inline vs class-based <strong>Lines</strong>: ~380 <strong>Last Updated</strong>: 2025-10-25</p>
<h2>When to Use This Skill</h2>
<p>Activate this skill when:</p>
<ul><li>Defining task structure for DSPy modules</li><li>Specifying input and output fields for LM calls</li><li>Creating typed signatures with field constraints</li><li>Adding descriptions and hints to guide LM behavior</li><li>Troubleshooting signature parsing errors</li><li>Designing multi-field inputs or outputs</li></ul>
<h2>Core Concepts</h2>
<h3>What are Signatures?</h3>
<p><strong>Definition</strong>: Signatures specify the input/output interface for a language model task</p>
<p><strong>Purpose</strong>:</p>
<ul><li><strong>Abstract prompts</strong>: Define &quot;what&quot; not &quot;how&quot;</li><li><strong>Type safety</strong>: Specify expected field types</li><li><strong>Documentation</strong>: Describe field semantics</li><li><strong>Composability</strong>: Reuse signatures across modules</li></ul>
<p><strong>Key insight</strong>: Signatures are like function signatures, but for LM tasks</p>
<h3>Signature Syntax</h3>
<p><strong>Three formats</strong>:</p>
<ol><li><strong>String format</strong>: <code>&quot;input1, input2 -&gt; output&quot;</code></li></ol>
<ul><li>Quick and simple</li><li>No type annotations</li><li>Good for prototyping</li></ul>
<ol><li><strong>Expanded string</strong>: <code>&quot;question: str, context: str -&gt; answer: str, confidence: float&quot;</code></li></ol>
<ul><li>Includes type hints</li><li>More explicit</li><li>Better for complex tasks</li></ul>
<ol><li><strong>Class-based</strong>: Python class with <code>dspy.InputField</code> and <code>dspy.OutputField</code></li></ol>
<ul><li>Maximum control</li><li>Field descriptions and constraints</li><li>Best for production</li></ul>
<h3>Field Types and Constraints</h3>
<p><strong>Supported types</strong>:</p>
<ul><li><code>str</code> - Text fields (most common)</li><li><code>int</code> - Integer values</li><li><code>float</code> - Floating point numbers</li><li><code>bool</code> - Boolean values</li><li><code>list[str]</code> - Lists of strings</li><li>Custom types (validated with Pydantic)</li></ul>
<p><strong>Field metadata</strong>:</p>
<ul><li><code>desc</code> - Description shown to LM</li><li><code>prefix</code> - Custom field label</li><li><code>format</code> - Output formatting hints</li></ul>
<hr>
<h2>Patterns</h2>
<h3>Pattern 1: Simple String Signatures</h3>
<pre><code class="lang-python">import dspy
# Basic question answering
signature = &quot;question -&gt; answer&quot;
# Classification
signature = &quot;text -&gt; category&quot;
# Summarization
signature = &quot;document -&gt; summary&quot;
# Use with Predict module
qa = dspy.Predict(&quot;question -&gt; answer&quot;)
result = qa(question=&quot;What is DSPy?&quot;)
print(result.answer)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Quick prototyping</li><li>Simple single-input, single-output tasks</li><li>Exploratory development</li></ul>
<h3>Pattern 2: Multi-Field Signatures</h3>
<pre><code class="lang-python">import dspy
# Multiple inputs
signature = &quot;question, context -&gt; answer&quot;
# Multiple outputs
signature = &quot;text -&gt; category, confidence&quot;
# Complex task
signature = &quot;title, author, year -&gt; summary, genre, rating&quot;
# Example usage
classifier = dspy.Predict(&quot;text, hint -&gt; label, confidence&quot;)
result = classifier(
text=&quot;This is a great product!&quot;,
hint=&quot;Classify sentiment as positive, negative, or neutral&quot;
)
print(f&quot;Label: {result.label}, Confidence: {result.confidence}&quot;)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Tasks requiring multiple inputs (context + question)</li><li>Structured outputs (category + confidence)</li><li>Rich information extraction</li></ul>
<h3>Pattern 3: Typed Signatures</h3>
<pre><code class="lang-python">import dspy
# Explicit type annotations
signature = &quot;question: str, context: str -&gt; answer: str, confidence: float&quot;
# Using with module
rag = dspy.Predict(&quot;question: str, context: str -&gt; answer: str&quot;)
# Types help DSPy format outputs correctly
result = rag(
question=&quot;What is the capital of France?&quot;,
context=&quot;France is a country in Europe. Paris is its capital.&quot;
)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Need numeric outputs (scores, ratings)</li><li>Want type validation</li><li>Building production systems</li><li>Working with structured data</li></ul>
<h3>Pattern 4: Class-Based Signatures</h3>
<pre><code class="lang-python">import dspy
class QASignature(dspy.Signature):
&quot;&quot;&quot;Answer questions based on provided context.&quot;&quot;&quot;
# Input fields
question = dspy.InputField(desc=&quot;User&#x27;s question&quot;)
context = dspy.InputField(desc=&quot;Relevant context for answering&quot;)
# Output fields
answer = dspy.OutputField(desc=&quot;Concise answer to the question&quot;)
confidence = dspy.OutputField(
desc=&quot;Confidence score between 0 and 1&quot;,
prefix=&quot;Confidence:&quot;
)
# Use class-based signature
qa = dspy.ChainOfThought(QASignature)
result = qa(
question=&quot;What is DSPy?&quot;,
context=&quot;DSPy is a framework for programming language models.&quot;
)
print(result.answer)
print(result.confidence)</code></pre>
<p><strong>Benefits</strong>:</p>
<ul><li>Clear field descriptions (guide LM behavior)</li><li>Docstring provides task context</li><li>Reusable across modules</li><li>Better IDE support</li></ul>
<h3>Pattern 5: Signatures with Hints and Constraints</h3>
<pre><code class="lang-python">import dspy
class SentimentAnalysis(dspy.Signature):
&quot;&quot;&quot;Analyze sentiment of text with confidence scoring.&quot;&quot;&quot;
text = dspy.InputField(desc=&quot;Text to analyze for sentiment&quot;)
# Provide hint about expected values
sentiment = dspy.OutputField(
desc=&quot;Sentiment label: positive, negative, or neutral&quot;
)
# Constrain output format
score = dspy.OutputField(
desc=&quot;Sentiment score from -1.0 (negative) to 1.0 (positive)&quot;,
prefix=&quot;Score (between -1.0 and 1.0):&quot;
)
explanation = dspy.OutputField(
desc=&quot;Brief explanation of the sentiment classification&quot;
)
# Use signature
analyzer = dspy.Predict(SentimentAnalysis)
result = analyzer(text=&quot;This product exceeded my expectations!&quot;)
print(f&quot;Sentiment: {result.sentiment}&quot;)
print(f&quot;Score: {result.score}&quot;)
print(f&quot;Explanation: {result.explanation}&quot;)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Need to guide LM output format</li><li>Want explanations alongside predictions</li><li>Complex structured outputs</li><li>Quality-critical applications</li></ul>
<h3>Pattern 6: Signatures for Multi-Step Reasoning</h3>
<pre><code class="lang-python">import dspy
class ComplexQA(dspy.Signature):
&quot;&quot;&quot;Answer complex questions that require reasoning.&quot;&quot;&quot;
question = dspy.InputField(desc=&quot;Complex question requiring reasoning&quot;)
context = dspy.InputField(desc=&quot;Background context&quot;, prefix=&quot;Context:&quot;)
# Intermediate reasoning step
reasoning = dspy.OutputField(
desc=&quot;Step-by-step reasoning process&quot;,
prefix=&quot;Let&#x27;s think step by step:&quot;
)
# Final answer
answer = dspy.OutputField(desc=&quot;Final answer based on reasoning&quot;)
# Use with ChainOfThought module
cot = dspy.ChainOfThought(ComplexQA)
result = cot(
question=&quot;If it takes 5 machines 5 minutes to make 5 widgets, how long would it take 100 machines to make 100 widgets?&quot;,
context=&quot;Each machine works independently at a constant rate.&quot;
)
print(&quot;Reasoning:&quot;, result.reasoning)
print(&quot;Answer:&quot;, result.answer)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Complex reasoning tasks</li><li>Need to show work/explanation</li><li>Debugging LM behavior</li><li>Educational applications</li></ul>
<h3>Pattern 7: List-Based Signatures</h3>
<pre><code class="lang-python">import dspy
class MultipleChoice(dspy.Signature):
&quot;&quot;&quot;Select best answer from multiple choices.&quot;&quot;&quot;
question = dspy.InputField(desc=&quot;Question to answer&quot;)
choices = dspy.InputField(desc=&quot;List of possible answers&quot;)
selected = dspy.OutputField(desc=&quot;Selected answer from choices&quot;)
reasoning = dspy.OutputField(desc=&quot;Why this answer was chosen&quot;)
# Usage
mc = dspy.Predict(MultipleChoice)
result = mc(
question=&quot;What is the capital of France?&quot;,
choices=[&quot;London&quot;, &quot;Paris&quot;, &quot;Berlin&quot;, &quot;Madrid&quot;]
)
print(f&quot;Selected: {result.selected}&quot;)
print(f&quot;Reasoning: {result.reasoning}&quot;)</code></pre>
<p><strong>When to use</strong>:</p>
<ul><li>Multiple choice questions</li><li>Selection from constrained set</li><li>Ranking tasks</li></ul>
<h3>Pattern 8: Custom Formatting with Prefix</h3>
<pre><code class="lang-python">import dspy
class CodeReview(dspy.Signature):
&quot;&quot;&quot;Review code and provide structured feedback.&quot;&quot;&quot;
code = dspy.InputField(desc=&quot;Code to review&quot;)
language = dspy.InputField(desc=&quot;Programming language&quot;)
# Custom prefixes for clear output structure
bugs = dspy.OutputField(
desc=&quot;List of potential bugs&quot;,
prefix=&quot;BUGS:&quot;
)
improvements = dspy.OutputField(
desc=&quot;Suggested improvements&quot;,
prefix=&quot;IMPROVEMENTS:&quot;
)
rating = dspy.OutputField(
desc=&quot;Code quality rating (1-10)&quot;,
prefix=&quot;RATING:&quot;
)
# Use signature
reviewer = dspy.ChainOfThought(CodeReview)
result = reviewer(
code=&quot;def add(a,b): return a+b&quot;,
language=&quot;Python&quot;
)</code></pre>
<p><strong>Benefits</strong>:</p>
<ul><li>Clear output structure</li><li>Easy parsing</li><li>Better LM understanding of desired format</li></ul>
<hr>
<h2>Quick Reference</h2>
<h3>Signature Format Comparison</h3>
<p>| Format | Syntax | Use Case | |--------|--------|----------| | Simple | <code>&quot;input -&gt; output&quot;</code> | Prototyping, simple tasks | | Multi-field | <code>&quot;in1, in2 -&gt; out1, out2&quot;</code> | Multiple inputs/outputs | | Typed | <code>&quot;in: str -&gt; out: float&quot;</code> | Type validation | | Class-based | <code>class Sig(dspy.Signature)</code> | Production, complex tasks |</p>
<h3>Common Field Types</h3>
<pre><code class="lang-python"># Text
question = dspy.InputField(desc=&quot;Question text&quot;)
# Numeric
score: float = dspy.OutputField(desc=&quot;Score from 0 to 1&quot;)
# Boolean
is_valid: bool = dspy.OutputField(desc=&quot;True if valid&quot;)
# List
options: list[str] = dspy.InputField(desc=&quot;List of choices&quot;)</code></pre>
<h3>Signature Best Practices</h3>
<pre><code>✅ DO: Use descriptive field names (question, not q)
✅ DO: Add field descriptions for clarity
✅ DO: Use class-based signatures for production
✅ DO: Include type hints for structured outputs
✅ DO: Provide examples in descriptions when needed
❌ DON&#x27;T: Use vague field names (input, output)
❌ DON&#x27;T: Omit descriptions for complex tasks
❌ DON&#x27;T: Mix too many unrelated outputs in one signature
❌ DON&#x27;T: Forget to specify expected output format</code></pre>
<h3>Quick Signature Templates</h3>
<pre><code class="lang-python"># Classification
&quot;text -&gt; category, confidence: float&quot;
# QA
&quot;question, context -&gt; answer&quot;
# Summarization
&quot;document: str -&gt; summary: str, key_points: list[str]&quot;
# Sentiment
&quot;text -&gt; sentiment, score: float, explanation&quot;
# Extraction
&quot;text, entity_type -&gt; entities: list[str]&quot;</code></pre>
<hr>
<h2>Anti-Patterns</h2>
<p>❌ <strong>Vague signatures</strong>: LM doesn&#x27;t know what to do</p>
<pre><code class="lang-python"># Bad
signature = &quot;input -&gt; output&quot;</code></pre>
<p>✅ Use descriptive names:</p>
<pre><code class="lang-python"># Good
signature = &quot;customer_review -&gt; sentiment_label, confidence_score: float&quot;</code></pre>
<p>❌ <strong>Missing field descriptions</strong>: LM guesses intent</p>
<pre><code class="lang-python"># Bad
class BadSig(dspy.Signature):
text = dspy.InputField()
result = dspy.OutputField()</code></pre>
<p>✅ Add clear descriptions:</p>
<pre><code class="lang-python"># Good
class GoodSig(dspy.Signature):
&quot;&quot;&quot;Classify text into categories.&quot;&quot;&quot;
text = dspy.InputField(desc=&quot;Text to classify&quot;)
category = dspy.OutputField(desc=&quot;Category: news, sports, or tech&quot;)</code></pre>
<p>❌ <strong>Too many outputs</strong>: Unfocused task</p>
<pre><code class="lang-python"># Bad - asking for too much at once
signature = &quot;text -&gt; sentiment, category, summary, keywords, language, toxicity&quot;</code></pre>
<p>✅ Split into focused signatures:</p>
<pre><code class="lang-python"># Good - focused tasks
classify_sig = &quot;text -&gt; category, confidence: float&quot;
sentiment_sig = &quot;text -&gt; sentiment, score: float&quot;</code></pre>
<p>❌ <strong>No type hints for structured data</strong>: Parsing issues</p>
<pre><code class="lang-python"># Bad - LM might return text instead of number
signature = &quot;text -&gt; score&quot;</code></pre>
<p>✅ Specify types:</p>
<pre><code class="lang-python"># Good
signature = &quot;text -&gt; score: float, max_score: int&quot;</code></pre>
<hr>
<h2>Related Skills</h2>
<ul><li><code>dspy-setup.md</code> - Setting up DSPy and LM configuration</li><li><code>dspy-modules.md</code> - Using signatures with Predict, ChainOfThought, ReAct</li><li><code>dspy-assertions.md</code> - Adding constraints and validation to signatures</li><li><code>dspy-optimizers.md</code> - Optimizing signatures with demonstrations</li><li><code>dspy-evaluation.md</code> - Evaluating signature-based programs</li></ul>
<hr>
<p><strong>Last Updated</strong>: 2025-10-25 <strong>Format Version</strong>: 1.0 (Atomic)</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/dspy-signatures.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>