Skip to content

DSPy Modules

This page is outdated and may not be fully accurate in DSPy 2.5

Quick Recap

This guide assumes you followed the intro tutorial to build your first few DSPy programs.

Remember that DSPy program is just Python code that calls one or more DSPy modules, like dspy.Predict or dspy.ChainOfThought, to use LMs.

1) What is a DSPy Module?

A DSPy module is a building block for programs that use LMs.

  • Each built-in module abstracts a prompting technique (like chain of thought or ReAct). Crucially, they are generalized to handle any DSPy Signature.

  • A DSPy module has learnable parameters (i.e., the little pieces comprising the prompt and the LM weights) and can be invoked (called) to process inputs and return outputs.

  • Multiple modules can be composed into bigger modules (programs). DSPy modules are inspired directly by NN modules in PyTorch, but applied to LM programs.

2) What DSPy Modules are currently built-in?

  1. dspy.Predict:

  2. dspy.ChainOfThought:

  3. dspy.ProgramOfThought:

  4. dspy.ReAct:

  5. dspy.MultiChainComparison:

3) How do I use a built-in module, like dspy.Predict or dspy.ChainOfThought?

Let's start with the most fundamental one, dspy.Predict. Internally, all of the others are just built using it!

We'll assume you are already at least a little familiar with DSPy signatures, which are declarative specs for defining the behavior of any module we use in DSPy. To use a module, we first declare it by giving it a signature. Then we call the module with the input arguments, and extract the output fields!

sentence = "it's a charming and often affecting journey."  # example from the SST-2 dataset.

# 1) Declare with a signature.
classify = dspy.Predict('sentence -> sentiment')

# 2) Call with input argument(s). 
response = classify(sentence=sentence)

# 3) Access the output.
print(response.sentiment)

Positive

When we declare a module, we can pass configuration keys to it.

Below, we'll pass n=5 to request five completions. We can also pass temperature or max_len, etc.

Let's use dspy.ChainOfThought. In many cases, simply swapping dspy.ChainOfThought in place of dspy.Predict improves quality.

question = "What's something great about the ColBERT retrieval model?"

# 1) Declare with a signature, and pass some config.
classify = dspy.ChainOfThought('question -> answer', n=5)

# 2) Call with input argument.
response = classify(question=question)

# 3) Access the outputs.
response.completions.answer

['One great thing about the ColBERT retrieval model is its superior efficiency and effectiveness compared to other models.',
 'Its ability to efficiently retrieve relevant information from large document collections.',
 'One great thing about the ColBERT retrieval model is its superior performance compared to other models and its efficient use of pre-trained language models.',
 'One great thing about the ColBERT retrieval model is its superior efficiency and accuracy compared to other models.',
 'One great thing about the ColBERT retrieval model is its ability to incorporate user feedback and support complex queries.']

Let's discuss the output object here.

The dspy.ChainOfThought module will generally inject a reasoning before the output field(s) of your signature.

Let's inspect the (first) reasoning and answer!

print(f"Reasoning: {response.reasoning}")
print(f"Answer: {response.answer}")

Reasoning: ColBERT (Contextualized Late Interaction over BERT) is a retrieval model that effectively combines the strengths of dense retrieval and traditional BM25 methods. One of its great features is that it allows for efficient and scalable retrieval by using late interaction techniques, which enables the model to leverage the contextual embeddings generated by BERT while still maintaining a fast retrieval speed. This means that it can handle large document collections more effectively than many other models, providing both high relevance in search results and efficiency in processing time.
Answer: A great feature of the ColBERT retrieval model is its ability to efficiently combine contextualized embeddings from BERT with a late interaction mechanism, allowing for scalable and high-performance document retrieval.

This is accessible whether we request one or many completions.

We can also access the different completions as a list of Predictions or as several lists, one for each field.

response.completions[3].reasoning == response.completions.reasoning[3]

True

4) How do I use more complex built-in modules?

The others are very similar, dspy.ReAct and dspy.ProgramOfThought etc. They mainly change the internal behavior with which your signature is implemented!

Check out further examples in each module's respective guide.

5) How do I compose multiple modules into a bigger program?

DSPy is just Python code that uses modules in any control flow you like. (There's some magic internally at compile time to trace your LM calls.)

What this means is that, you can just call the modules freely. No weird abstractions for chaining calls.

This is basically PyTorch's design approach for define-by-run / dynamic computation graphs. Refer to the intro tutorials for examples.