Menu
SkillsMP has collected 95 skills from lebsral/DSPy-Programming-not-prompting-LMs-skills. Open a skill to review its source and details.
Showing 40 of 95 collected skills.
Describe your AI problem and get routed to the right skill with a ready-to-use prompt. Use when you are not sure which ai- skill to use, want help picking the right approach, or just want to describe what you need in plain language. Also use this when someone…
Legacy reference for dspy.Assert and dspy.Suggest, both removed in DSPy 3.x - use dspy.Refine or dspy.BestOfN instead. Use when maintaining a legacy DSPy 2.x codebase that uses dspy.Assert or dspy.Suggest, or migrating from Assert/Suggest to DSPy 3.x. Also…
Runs any DSPy module N times and returns the highest-scoring output via a reward function using dspy.BestOfN. Use when output quality varies across runs and you want to sample multiple completions and pick the best — trading latency for reliability on…
Jointly optimize prompts and model weights using dspy.BetterTogether for maximum accuracy. Use when you have already tried prompt-only optimization and want the next level — jointly tuning prompts and model weights for maximum quality. Common scenarios - you…
Automatically generate and select few-shot demonstrations for a DSPy program from labeled data using dspy.BootstrapFewShot - the simplest and fastest optimizer. Use when you have 50+ labeled examples and want a quick accuracy boost as your first optimization…
Generates training data from a teacher model and fine-tunes student model weights using dspy.BootstrapFinetune. Use when you need maximum quality from a smaller/cheaper model — distilling GPT-4 quality into a cheaper model, generating training data from a…
Optimize few-shot demos for a DSPy program by searching over multiple candidate demo sets using dspy.BootstrapFewShotWithRandomSearch. Use when basic BootstrapFewShot is not enough and you want better results at the cost of more LM calls. Common scenarios -…
Use when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math, or complex classification where direct prediction fails. Common scenarios - classification tasks where the model needs to reason about edge…
Deep dive into dspy.ChatAdapter -- the default adapter that formats DSPy signatures into multi-turn chat messages with field delimiters, parses LM responses back into typed Python objects, and falls back to JSONAdapter on failure. Use when you need to…
Build agents that write and execute Python code using dspy.CodeAct. Use when the task requires computation, data transformation, or multi-step logic better expressed as code than tool calls or natural language - data analysis, precise calculations, file…
Use when you want to optimize instructions by generating many candidates and picking the best — useful when few-shot demos alone are not enough and you want to tune the task description itself. Common scenarios - your current task instructions produce…
Prepare training and dev data for DSPy - loading from CSV/JSON/HuggingFace, creating dspy.Example objects, setting input keys, and building train/dev splits. Use when you need to prepare data for DSPy optimizers, load labeled examples, or convert dataset…
Combines multiple optimized DSPy programs into a single ensemble via majority voting, averaging, or custom reduce functions using dspy.Ensemble. Use when you have run multiple optimization passes and want to combine the best programs for more reliable…
Run dspy.Evaluate to score DSPy programs against labeled examples using custom or built-in metrics. Use when you need to measure how well your DSPy program performs — writing metrics, scoring against a dev set, or comparing before/after optimization. Common…
Optimize instructions in DSPy programs via reflective evolution using dspy.GEPA without adding few-shot examples. Use when you want to optimize instructions without few-shot examples — a lightweight alternative when you do not have or do not want to use…
Use when you want to extract interpretable decision logic from labeled examples — generating explicit rules that explain patterns in your data. Common scenarios - extracting business rules from labeled classification examples, understanding why a model makes…
Select the most relevant few-shot demonstrations for each input at runtime using dspy.KNNFewShot and dspy.KNN — embedding-based retrieval that adapts demos per query. Use when you want few-shot demos dynamically selected per input based on similarity, inputs…
Attach hand-curated labeled examples as few-shot demonstrations using dspy.LabeledFewShot — no bootstrapping, no metric, no LM calls at compile time. Use when you have hand-picked high-quality examples and want to inject them directly as prompt demos without…
Use when you need to configure which language model DSPy uses — setting up providers, API keys, model parameters, or assigning different models to different pipeline stages. Common scenarios - setting up OpenAI or Anthropic API keys, configuring model…
dspy.MIPROv2 jointly optimizes instructions and few-shot demos using Bayesian search - DSPy most powerful prompt optimizer. Use when you want the best possible accuracy from prompt optimization, jointly tuning instructions and few-shot demonstrations, using…
Build multi-step DSPy programs as composable, optimizable modules using dspy.Module and forward(). Use when composing Predict and ChainOfThought calls into a reusable pipeline, structuring a RAG pipeline as a class, creating nested DSPy modules, or designing…
Use when you want higher accuracy by generating multiple reasoning chains and selecting the best answer — trading speed for quality on critical outputs. Common scenarios - high-stakes decisions where you want multiple reasoning paths compared, classification…
Use when you have independent LM calls that can run concurrently — batch processing, fan-out patterns, or speeding up pipelines with no data dependencies between steps. Common scenarios - processing a batch of inputs through a DSPy module concurrently,…
Build fast direct LM calls with dspy.Predict - the atomic DSPy module for simple input-to-output mapping with no reasoning overhead. Use when the mapping from input to output is straightforward and does not need reasoning steps — simple classification,…
DSPy typed wrappers (dspy.Image, dspy.Audio, dspy.Code, dspy.History, dspy.File, dspy.Reasoning, dspy.Tool, dspy.ToolCalls, dspy.Example, dspy.Prediction) for multimodal data, files, and structured outputs in signatures. Use when working with non-text inputs…
Use when the task requires precise computation, math, or data manipulation — the LM writes Python code that executes in a sandbox instead of reasoning in natural language. Common scenarios - math word problems, data manipulation tasks, precise calculations…
Build tool-using agents with dspy.ReAct - the Reasoning-Action-Observation loop for interleaved thinking and action. Use when the task requires calling external tools or APIs to gather information - multi-step tool use with reasoning, like searching…
Iterative self-improvement with dspy.Refine -- wraps any module, scores each attempt with a reward function, generates feedback on failures, and retries until a quality threshold is met. Use when you want outputs to improve through self-critique, need…
DSPy retrieval modules (dspy.Retrieve, dspy.ColBERTv2, dspy.Embedder, dspy.retrievers.Embeddings) for searching documents, computing embeddings, and building RAG pipelines. Use when you need to search over documents, build a RAG pipeline, connect DSPy to a…
Recursive Language Model (dspy.RLM) that explores large contexts via a sandboxed Python REPL -- the LM writes code, queries sub-LMs, and iterates until it produces a final answer. Use when your input is too large for the context window, the model needs to…
Defines typed input/output contracts for LM calls using dspy.Signature, dspy.InputField, and dspy.OutputField. Use when you need to define the input/output contract for an LM call — choosing between inline and class-based signatures, adding type constraints,…
Optimize a DSPy program in small conservative steps using dspy.SIMBA (Stochastic Introspective Mini-Batch Ascent). Use when your program already works and you want to push accuracy higher without breaking what works, you need safe incremental improvement for…
Wraps Python functions as dspy.Tool objects and configures dspy.PythonInterpreter for sandboxed code execution in DSPy agents. Use when you need to give DSPy agents tool-calling abilities — wrapping Python functions as tools, building tool-using pipelines, or…
DSPy utility functions for caching control, debugging with inspect_history, saving/loading optimized programs, and runtime validation with Refine/BestOfN. Use when you need DSPy infrastructure - controlling the cache to avoid stale results, debugging with…
LLM observability for DSPy with Langfuse -- auto-trace every LM call, attach scores and evaluations, run annotation queues for human review, and track experiments across prompt versions. Use when you want to set up Langfuse, langfuse.com,…
Use Langtrace for DSPy observability and tracing with langtrace.init() auto-instrumentation. Use when you want to set up Langtrace, langtrace-python-sdk, auto-instrument DSPy, trace DSPy calls, LLM observability, app.langtrace.ai, or self-hosted tracing. Also…
Use LangWatch for DSPy auto-tracing and real-time optimizer progress. Use when you want to set up LangWatch, langwatch.dspy.init, auto-tracing DSPy, real-time optimization dashboard, optimizer progress tracking, app.langwatch.ai, or DSPy optimizer dashboard.…
Use MLflow for DSPy tracing, experiment tracking, and model registry. Use when you want to set up MLflow, mlflow.dspy.autolog, MLflow Tracing, MLflow experiment tracking, MLflow model registry, or full ML lifecycle management. Also used for mlflow setup, pip…
Run DSPy with local models via dspy.LM and Ollama — no API key needed. Use when you want to run DSPy locally, use Ollama, set up a local LLM, run offline, or configure local model parameters. Also used for ollama, local model, run LLM locally, llama local,…
Use Arize Phoenix for DSPy tracing and evaluation. Use when you want to set up Phoenix, arize-phoenix, openinference, DSPyInstrumentor, open-source trace viewer, localhost:6006, or LLM evals. Also used for phoenix setup, arize phoenix, pip install…