lebsral/dspy-programming-not-prompting-lms-skills

1

ai-choosing-architecture Pick the right DSPy module and architecture for your AI feature. Use when you are not sure whether to use Predict, Ch…

lebsral/dspy-programming-not-prompting-lms-skills

5

2

dspy-best-of-n Use when output quality varies across runs and you want to sample multiple completions and pick the best — trading la…

lebsral/dspy-programming-not-prompting-lms-skills

5

3

dspy-better-together Use when you have already tried prompt-only optimization and want the next level — jointly tuning prompts and model w…

lebsral/dspy-programming-not-prompting-lms-skills

5

4

dspy-bootstrap-few-shot Use when you have 50+ labeled examples and want a quick accuracy boost as your first optimization step — the simplest…

lebsral/dspy-programming-not-prompting-lms-skills

5

5

dspy-bootstrap-finetune Generates training data from a teacher model and fine-tunes student model weights using dspy.BootstrapFinetune. Use w…

lebsral/dspy-programming-not-prompting-lms-skills

5

6

dspy-bootstrap-rs Optimize few-shot demos for a DSPy program by searching over multiple candidate demo sets using dspy.BootstrapFewShot…

lebsral/dspy-programming-not-prompting-lms-skills

5

7

dspy-codeact Use when the agent task is best solved by writing and executing Python code — data manipulation, computation, file pr…

lebsral/dspy-programming-not-prompting-lms-skills

5

8

dspy-copro Use when you want to optimize instructions by generating many candidates and picking the best — useful when few-shot …

lebsral/dspy-programming-not-prompting-lms-skills

5

9

dspy-knn-few-shot Use when you want few-shot demos that are dynamically selected per input based on similarity — better than fixed demo…

lebsral/dspy-programming-not-prompting-lms-skills

5

10

dspy-weave Use W&B Weave for DSPy experiment tracking and observability. Use when you want to set up Weave, W&B, wandb, Weights …

lebsral/dspy-programming-not-prompting-lms-skills

5

11

dspy-ensemble Combines multiple optimized DSPy programs into a single ensemble via majority voting, averaging, or custom reduce fun…

lebsral/dspy-programming-not-prompting-lms-skills

4

12

dspy-infer-rules Use when you want to extract interpretable decision logic from labeled examples — generating explicit rules that expl…

lebsral/dspy-programming-not-prompting-lms-skills

4

13

dspy-langfuse LLM observability for DSPy with Langfuse -- auto-trace every LM call, attach scores and evaluations, run annotation q…

lebsral/dspy-programming-not-prompting-lms-skills

4

14

dspy-langtrace Use Langtrace for DSPy observability and tracing with langtrace.init() auto-instrumentation. Use when you want to set…

lebsral/dspy-programming-not-prompting-lms-skills

4

15

dspy-langwatch Use LangWatch for DSPy auto-tracing and real-time optimizer progress. Use when you want to set up LangWatch, langwatc…

lebsral/dspy-programming-not-prompting-lms-skills

4

16

dspy-miprov2 Use when you want the highest-quality prompt optimization DSPy offers — jointly optimizes instructions and few-shot d…

lebsral/dspy-programming-not-prompting-lms-skills

4

17

dspy-mlflow Use MLflow for DSPy tracing, experiment tracking, and model registry.

lebsral/dspy-programming-not-prompting-lms-skills

4

18

dspy-ollama Run DSPy with local models via dspy.LM and Ollama — no API key needed. Use when you want to run DSPy locally, use Oll…

lebsral/dspy-programming-not-prompting-lms-skills

4

19

dspy-phoenix Use Arize Phoenix for DSPy tracing and evaluation.

lebsral/dspy-programming-not-prompting-lms-skills

4

20

dspy-qdrant Use Qdrant as a vector database with DSPy, or connect any vector DB (Pinecone, ChromaDB, Weaviate) with custom retrie…

lebsral/dspy-programming-not-prompting-lms-skills

4

21

dspy-ragas Use Ragas to evaluate DSPy RAG pipelines with decomposed metrics. Use when you want to evaluate RAG quality, measure …

lebsral/dspy-programming-not-prompting-lms-skills

4

22

dspy-retrieval DSPy retrieval modules (dspy.Retrieve, dspy.ColBERTv2, dspy.Embedder, dspy.retrievers.Embeddings) for searching docum…

lebsral/dspy-programming-not-prompting-lms-skills

4

23

dspy-vizpy Use VizPy as a drop-in prompt optimizer for DSPy. Use when you want to try VizPy, vizops, ContraPromptOptimizer, Prom…

lebsral/dspy-programming-not-prompting-lms-skills

4

24

dspy-vllm Use vLLM for high-throughput production serving of self-hosted models with DSPy. Use when you want production LLM ser…

lebsral/dspy-programming-not-prompting-lms-skills

4

25

ai-auditing-code Review DSPy code for correctness and best practices. Use when you want a code review of your DSPy program, need to ch…

lebsral/dspy-programming-not-prompting-lms-skills

3

26

ai-planning Plan a multi-phase AI feature before building it. Use when you have a PRD or project idea and need to figure out the …

lebsral/dspy-programming-not-prompting-lms-skills

3

27

ai-rewriting-text Rewrite text to match a different tone, reading level, or audience using AI. Use when rewriting content in a differen…

lebsral/dspy-programming-not-prompting-lms-skills

3

28

ai-understanding-images Analyze images and extract structured data from visual content using AI.

lebsral/dspy-programming-not-prompting-lms-skills

3

29

ai-watching-optimization See what is happening during optimizer.compile() instead of waiting blind. Use when you want to watch optimization pr…

lebsral/dspy-programming-not-prompting-lms-skills

3

30

dspy-program-of-thought Use DSPy's ProgramOfThought module to solve problems by generating and executing code. Use when you want to use dspy.…

lebsral/dspy-programming-not-prompting-lms-skills

3

31

dspy-refine Use DSPy's Refine module for iterative self-improvement of outputs. Use when you want to use dspy.Refine, iteratively…

lebsral/dspy-programming-not-prompting-lms-skills

3

32

ai-cleaning-data Normalize and fix messy data fields using AI. Use when normalizing addresses, standardizing company names, fixing inc…

lebsral/dspy-programming-not-prompting-lms-skills

2

33

ai-detecting-anomalies Detect fraud, unusual behavior, and anomalies in events or transactions using AI. Use when detecting fraud, flagging …

lebsral/dspy-programming-not-prompting-lms-skills

2

34

ai-generating-notifications Generate smart notification messages from structured events using AI. Use when writing push notification copy, creati…

lebsral/dspy-programming-not-prompting-lms-skills

2

35

ai-matching-records Find and merge duplicate records across datasets using AI.

lebsral/dspy-programming-not-prompting-lms-skills

2

36

ai-recommending Build AI that recommends products, articles, or content based on user preferences.

lebsral/dspy-programming-not-prompting-lms-skills

2

37

ai-redacting-data Strip PII and sensitive data from text before processing with AI. Use when redacting personal information, GDPR compl…

lebsral/dspy-programming-not-prompting-lms-skills

2

38

ai-translating-content Translate text between languages with AI while preserving brand voice and terminology. Use when translating app copy …

lebsral/dspy-programming-not-prompting-lms-skills

2

39

dspy-assertions Legacy reference for dspy.Assert and dspy.Suggest, both removed in DSPy 3.x - use dspy.Refine or dspy.BestOfN instead…

lebsral/dspy-programming-not-prompting-lms-skills

2

40

dspy-async Use when you need to run DSPy modules asynchronously — FastAPI endpoints, concurrent LM calls, non-blocking execution…

lebsral/dspy-programming-not-prompting-lms-skills

2

41

dspy-chatadapter Deep dive into dspy.ChatAdapter -- the default adapter that formats DSPy signatures into multi-turn chat messages wit…

lebsral/dspy-programming-not-prompting-lms-skills

2

42

dspy-citations Use when you need structured source attribution in AI responses — verifiable citations that link claims to specific p…

lebsral/dspy-programming-not-prompting-lms-skills

2