Examples - DSRs

Every example in this index is a complete, runnable program in crates/dspy-rs/examples/. Most need an OPENAI_API_KEY; a few run fully offline against the in-process test client and say so in their header comment. Run any of them with:

cargo run --example 01-simple

Some examples need a feature flag (noted in the file header), for example --features dataloaders for the HotpotQA ones.

The examples

Example	What it shows	Key APIs
01-simple.rs	Typed signatures, chain-of-thought via a `reasoning` field, and module composition	`Signature`, `Predict`, `Module`
02-module-iteration-and-updation.rs	Optimizing a module end to end with the typed optimizer API	`COPRO`, `Optimizer::compile`, `TypedMetric`
03-evaluate-hotpotqa.rs	Evaluating a typed QA predictor on a HotpotQA sample	`DataLoader`, `evaluate_trainset`, `Eval`
04-optimize-hotpotqa.rs	COPRO optimization of a QA module on HotpotQA, then saving the result	`COPRO`, `ModuleState`, `average_score`
05-heterogenous-examples.rs	Feeding a typed predictor from messy JSON rows; extra fields ignored, missing ones loud	serde boundary, generated input structs
06-other-providers-batch.rs	Batch inference across multiple providers via `provider:model` strings	`forward_all`, `LM::builder`
07-inspect-history.rs	Inspecting the LM’s message history after a call	`get_lm`, LM history
08-optimize-mipro.rs	MIPROv2 optimization with HuggingFace data loading and a baseline comparison	`MIPROv2`, `DataLoader`
09-gepa-sentiment.rs	GEPA with explicit textual feedback and a reflection LM	`GEPA`, `Eval::with_feedback`, `prompt_model`
10-gepa-llm-judge.rs	GEPA where a second LM judges outputs and its verdicts become the feedback	`GEPA`, judge `Predict`, `TypedMetric`
11-custom-client.rs	Plugging in a custom provider client (Azure)	`LMClient::from_custom`
12-tracing.rs	Scoped trace capture: one span per predictor call, sliceable by component	`trace::capture`, `Trace::for_component`
13-save-load-state.rs	Persisting optimized instructions and demos, then reloading them (offline)	`ModuleState::save` / `load`
14-functional.rs	The functional lane: pipelines as plain async functions, params injected ambiently (offline)	`fx::predict`, `fx::Params`, `fx::with_params`
15-tools.rs	Giving a typed predictor tools to call during generation	tool definitions, `Predict`
16-insurance-claim-prompt.rs	Printing the exact system prompt a nested extraction signature renders to	`ChatAdapter`, nested `Signature` types
17-pretty-tracing.rs	Human-readable tracing output against an offline canned LM	`init_tracing`, `TestCompletionModel`

The front desk examples

These nine exercise a small support-desk pipeline end to end. Each maps to a component page and is kept compiling by CI.

Example	Component page	What it shows
18-code-mode.rs	Tools & agents	Two tools collapsed into the `run_js` meta-tool via `ToolSet::code_mode`
19-react.rs	Tools & agents	`ReAct` with a closure tool and a step cap, trajectory read from metadata
20-frontdesk-contract.rs	Signatures	Enums, nested types, constraints, demos, per-predictor models, the printed prompt
21-frontdesk-pipeline.rs	Modules	The pipeline as a struct with a `Module` impl, plus the `fx` variant
22-frontdesk-module.rs	Module macro	`#[module]` with a hole; prints the real `.dsrs` artifact and `OPACITY` (offline)
23-frontdesk-agent.rs	Tools & agents	`#[tool]` + `#[agent]` + module `caps(...)` wiring (prints the caps block offline)
24-frontdesk-replay.rs	Traces	Capture to JSONL, strict replay with zero live calls, until-divergence under an overlay
25-frontdesk-evaluate.rs	Evaluation	A labeled trainset, a `TypedMetric`, `evaluate_trainset` + `average_score`
26-frontdesk-tune.rs	Optimizers	Overlay by param path, ambient overlay run, `bake` with lineage (offline path included)

The 9x- files (90 through 94, plus the 97-99 benches) are CI surfaces: smoke slices that exercise typed predict, chain of thought, module authoring, ReAct, and the optimizer interface, and a few performance benchmarks. They are kept deliberately boring and stable; read them as compatibility contracts rather than tutorials.