Paper —— DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

DSPy is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). DSPy unifies techniques for prompting and fine-tuning LMs — and approaches for reasoning, self-improvement, and augmentation with retrieval and tools. All of these are expressed through modules that compose and learn.

To make this possible:

• DSPy provides composable and declarative modules for instructing LMs in a familiar Pythonic syntax. It upgrades "prompting techniques" like chain-of-thought and self-reflection from hand-adapted string manipulation tricks into truly modular generalized operations that learn to adapt to your task.

• DSPy introduces an automatic compiler that teaches LMs how to conduct the declarative steps in your program. Specifically, the DSPy compiler will internally trace your program and then craft high-quality prompts for large LMs (or train automatic finetunes for small LMs) to teach them the steps of your task.

The DSPy compiler bootstraps prompts and finetunes from minimal data without needing manual labels for the intermediate steps in your program. Instead of brittle "prompt engineering" with hacky string manipulation, you can explore a systematic space of modular and trainable pieces.

For complex tasks, DSPy can routinely teach powerful models like GPT-3.5 and local models like T5-base or Llama2-13b to be much more reliable at tasks. DSPy will compile the same program into different few-shot prompts and/or finetunes for each LM.

If you want to see DSPy in action, open our intro tutorial notebook.

1. Installation
2. Framework Syntax
3. Compiling: Two Powerful Concepts
4. Tutorials & Documentation
5. FAQ: Is DSPy right for me?

When we build neural networks, we don't write manual for-loops over lists of hand-tuned floats. Instead, you might use a framework like PyTorch to compose declarative layers (e.g., Convolution or Dropout) and then use optimizers (e.g., SGD or Adam) to learn the parameters of the network.

Ditto! DSPy gives you the right general-purpose modules (e.g., ChainOfThought, Retrieve, etc.) and takes care of optimizing their prompts for your program and your metric, whatever they aim to do. Whenever you modify your code, your data, or your validation constraints, you can compile your program again and DSPy will create new effective prompts that fit your changes.

All you need is:

pip install dspy-ai

Or open our intro notebook in Google Colab:

Note: If you're looking for Demonstrate-Search-Predict (DSP), which is the previous version of DSPy, you can find it on the v1 branch of this repo.

For the optional Pinecone, Qdrant, chromadb, or marqo retrieval integration(s), include the extra(s) below:

pip install dspy-ai[pinecone]  # or [qdrant] or [chromadb] or [marqo]

DSPy hides tedious prompt engineering, but it cleanly exposes the important decisions you need to make: [1] what's your system design going to look like? [2] what are the important constraints on the behavior of your program?

You express your system as free-form Pythonic modules. DSPy will tune the quality of your program in whatever way you use foundation models: you can code with loops, if statements, or exceptions, and use DSPy modules within any Python control flow you think works for your task.

Suppose you want to build a simple retrieval-augmented generation (RAG) system for question answering. You can define your own RAG program like this:

class RAG(dspy.Module):
    def __init__(self, num_passages=3):
        super().__init__()
        self.retrieve = dspy.Retrieve(k=num_passages)
        self.generate_answer = dspy.ChainOfThought("context, question -> answer")
    
    def forward(self, question):
        context = self.retrieve(question).passages
        answer = self.generate_answer(context=context, question=question)
        return answer

A program has two key methods, which you can edit to fit your needs.

Your __init__ method declares the modules you will use. Here, RAG will use the built-in Retrieve for retrieval and ChainOfThought for generating answers. DSPy offers general-purpose modules that take the shape of your own sub-tasks — and not pre-built functions for specific applications.

Modules that use the LM, like ChainOfThought, require a signature. That is a declarative spec that tells the module what it's expected to do. In this example, we use the short-hand signature notation context, question -> answer to tell ChainOfThought it will be given some context and a question and must produce an answer. We will discuss more advanced signatures below.

Your forward method expresses any computation you want to do with your modules. In this case, we use the modules self.retrieve and self.generate_answer to search for some context and then use the context and question to generate the answer!

You can now either use this RAG program in zero-shot mode. Or compile it to obtain higher quality. Zero-shot usage is simple. Just define an instance of your program and then call it:

rag = RAG()  # zero-shot, uncompiled version of RAG
rag("what is the capital of France?").answer  # -> "Paris"

The next section will discuss how to compile our simple RAG program. When we compile it, the DSPy compiler will annotate demonstrations of its steps: (1) retrieval, (2) using context, and (3) using chain-of-thought to answer questions. From these demonstrations, the DSPy compiler will make sure it produces an effective few-shot prompt that works well with your LM, retrieval model, and data. If you're working with small models, it'll finetune your model (instead of prompting) to do this task.

If you later decide you need another step in your pipeline, just add another module and compile again. Maybe add a module that takes the chat history into account during search?

To make it possible to compile any program you write, DSPy introduces two simple concepts: Signatures and Teleprompters.

When we assign tasks to LMs in DSPy, we specify the behavior we need as a Signature. A signature is a declarative specification of input/output behavior of a DSPy module.

Instead of investing effort into how to get your LM to do a sub-task, signatures enable you to inform DSPy what the sub-task is. Later, the DSPy compiler will figure out how to build a complex prompt for your large LM (or finetune your small LM) specifically for your signature, on your data, and within your pipeline.

A signature consists of three simple elements:

• A minimal description of the sub-task the LM is supposed to solve.
• A description of one or more input fields (e.g., input question) that will we will give to the LM.
• A description of one or more output fields (e.g., the question's answer) that we will expect from the LM.

We support two notations for expressing signatures. The short-hand signature notation is for quick development. You just provide your module (e.g., dspy.ChainOfThought) with a string with input_field_name_1, ... -> output_field_name_1, ... with the fields separated by commas.

In the RAG class earlier, we saw:

self.generate_answer = dspy.ChainOfThought("context, question -> answer")

In many cases, this barebones signature is sufficient. However, sometimes you need more control. In these cases, we can use the full notation to express a more fully-fledged signature below.

class GenerateSearchQuery(dspy.Signature):
    """Write a simple search query that will help answer a complex question."""

    context = dspy.InputField(desc="may contain relevant facts")
    question = dspy.InputField()
    query = dspy.OutputField()

### inside your program's __init__ function
self.generate_answer = dspy.ChainOfThought(GenerateSearchQuery)

You can optionally provide a prefix and/or desc key for each input or output field to refine or constraint the behavior of modules using your signature. The description of the sub-task itself is specified as the docstring (i.e., """Write a simple...""").

After defining the RAG program, we can compile it. Compiling a program will update the parameters stored in each module. For large LMs, this is primarily in the form of creating and validating good demonstrations for inclusion in your prompt(s).

Compiling depends on three things: a (potentially tiny) training set, a metric for validation, and your choice of teleprompter from DSPy. Teleprompters are powerful optimizers (included in DSPy) that can learn to bootstrap and select effective prompts for the modules of any program. (The "tele-" in the name means "at a distance", i.e., automatic prompting at a distance.)

DSPy typically requires very minimal labeling. For example, our RAG pipeline may work well with just a handful of examples that contain a question and its (human-annotated) answer. Your pipeline may involve multiple complex steps: our basic RAG example includes a retrieved context, a chain of thought, and the answer. However, you only need labels for the initial question and the final answer. DSPy will bootstrap any intermediate labels needed to support your pipeline. If you change your pipeline in any way, the data bootstrapped will change accordingly!

my_rag_trainset = [
  dspy.Example(
    question="Which award did Gary Zukav's first book receive?",
    answer="National Book Award"
  ),
  ...
]

Second, define your validation logic, which will express some constraints on the behavior of your program or individual modules. For RAG, we might express a simple check like this:

def validate_context_and_answer(example, pred, trace=None):
    # check the gold label and the predicted answer are the same
    answer_match = example.answer.lower() == pred.answer.lower()

    # check the predicted answer comes from one of the retrieved contexts
    context_match = any((pred.answer.lower() in c) for c in pred.context)

    return answer_match and context_match

Different teleprompters offer various tradeoffs in terms of how much they optimize cost versus quality, etc. For RAG, we might use the simple teleprompter called BootstrapFewShot. To do so, we instantiate the teleprompter itself with a validation function my_rag_validation_logic and then compile against some training set my_rag_trainset.

from dspy.teleprompt import BootstrapFewShot

teleprompter = BootstrapFewShot(metric=my_rag_validation_logic)
compiled_rag = teleprompter.compile(RAG(), trainset=my_rag_trainset)

If we now use compiled_rag, it will invoke our LM with rich prompts with few-shot demonstrations of chain-of-thought retrieval-augmented question answering on our data.

While we work on new tutorials and documentation, please check out our intro notebook.

Or open it directly in free Google Colab:

The DSPy philosophy and abstraction differ significantly from other libraries and frameworks, so it's usually straightforward to decide when DSPy is (or isn't) the right framework for your usecase.

If you're a NLP/AI researcher (or a practitioner exploring new pipelines or new tasks), the answer is generally an invariable yes. If you're a practitioner doing other things, please read on.

DSPy is led by Omar Khattab at Stanford NLP with Chris Potts and Matei Zaharia.

Key contributors and team members include Arnav Singhvi, Paridhi Maheshwari, Keshav Santhanam, Sri Vardhamanan, Eric Zhang, Hanna Moazam, Thomas Joshi, Saiful Haq, and Ashutosh Sharma.

DSPy includes important contributions from Rick Battle and Igor Kotenkov. It reflects discussions with Lisa Li, David Hall, Ashwin Paranjape, Heather Miller, Chris Manning, Percy Liang, and many others.

The DSPy logo is designed by Chuyi Zhang.

To stay up to date or learn more, follow @lateinteraction on Twitter.

If you use DSPy or DSP in a research paper, please cite our work as follows:

@article{khattab2023dspy,
  title={DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines},
  author={Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher},
  journal={arXiv preprint arXiv:2310.03714},
  year={2023}
}
@article{khattab2022demonstrate,
  title={Demonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-Intensive {NLP}},
  author={Khattab, Omar and Santhanam, Keshav and Li, Xiang Lisa and Hall, David and Liang, Percy and Potts, Christopher and Zaharia, Matei},
  journal={arXiv preprint arXiv:2212.14024},
  year={2022}
}

You can also read more about the evolution of the framework from Demonstrate-Search-Predict to DSPy:

• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (Academic Paper, Oct 2023)
• Releasing DSPy, the latest iteration of the framework (Twitter Thread, Aug 2023)
• Releasing the DSP Compiler (v0.1) (Twitter Thread, Feb 2023)
• Introducing DSP (Twitter Thread, Jan 2023)
• Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP (Academic Paper, Dec 2022)