Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

Update faqs.md

Omar Khattabeb5e87994f5c
diff --git a/docs/faqs.md b/docs/faqs.md
index 8bc0a74de..d330c4a30 100644
--- a/docs/faqs.md
+++ b/docs/faqs.md
@@ -10,7 +10,7 @@ The **DSPy** philosophy and abstraction differ significantly from other librarie
**DSPy vs. thin wrappers for prompts (OpenAI API, MiniChain, basic templating)** In other words: _Why can't I just write my prompts directly as string templates?_ Well, for extremely simple settings, this _might_ work just fine. (If you're familiar with neural networks, this is like expressing a tiny two-layer NN as a Python for-loop. It kinda works.) However, when you need higher quality (or manageable cost), then you need to iteratively explore multi-stage decomposition, improved prompting, data bootstrapping, careful finetuning, retrieval augmentation, and/or using smaller (or cheaper, or local) models. The true expressive power of building with foundation models lies in the interactions between these pieces. But every time you change one piece, you likely break (or weaken) multiple other components. **DSPy** cleanly abstracts away (_and_ powerfully optimizes) the parts of these interactions that are external to your actual system design. It lets you focus on designing the module-level interactions: the _same program_ expressed in 10 or 20 lines of **DSPy** can easily be compiled into multi-stage instructions for `GPT-4`, detailed prompts for `Llama2-13b`, or finetunes for `T5-base`. Oh, and you wouldn't need to maintain long, brittle, model-specific strings at the core of your project anymore.
-**DSPy vs. application development libraries like LangChain, LlamaIndex** LangChain and LlamaIndex are popular libraries that target high-level application development with LMs. They offer many _batteries-included_, pre-built application modules that plug in with your data or configuration. In practice, indeed, many usecases genuinely _don't need_ any special components. If you'd be happy to use someone's generic, off-the-shelf prompt for question answering over PDFs or standard text-to-SQL as long as it's easy to set up on your data, then you will probably find a very rich ecosystem in these libraries. Unlike these libraries, **DSPy** doesn't internally contain hand-crafted prompts that target specific applications you can build. Instead, **DSPy** introduces a very small set of much more powerful and general-purpose modules _that can learn to prompt (or finetune) your LM within your pipeline on your data_. **DSPy** offers a whole different degree of modularity: when you change your data, make tweaks to your program's control flow, or change your target LM, the **DSPy compiler** can map your program into a new set of prompts (or finetunes) that are optimized specifically for this pipeline. Because of this, you may find that **DSPy** obtains the highest quality for your task, with the least effort, provided you're willing to implement (or extend) your own short program. In short, **DSPy** is for when you need a lightweight but automatically-optimizing programming model — not a library of predefined prompts and integrations. If you're familiar with neural networks: This is like the difference between PyTorch (i.e., representing **DSPy**) and HuggingFace Transformers (i.e., representing the higher-level libraries). If you simply want to use off-the-shelf `BERT-base-uncased` or `GPT2-large` or apply minimal finetuning to them, HF Transformers makes it very straightforward. If, however, you're looking to build your own architecture (or extend an existing one significantly), you have to quickly drop down into something much more modular like PyTorch. Luckily, HF Transformers _is_ implemented in backends like PyTorch. We are similarly excited about high-level wrapper around **DSPy** for common applications. If this is implemented using **DSPy**, your high-level application can also adapt significantly to your data in a way that static prompt chains won't. Please [open an issue](https://github.com/stanfordnlp/dspy/issues/new) if this is something you want to help with.
+**DSPy vs. application development libraries like LangChain, LlamaIndex** LangChain and LlamaIndex target high-level application development; they offer _batteries-included_, pre-built application modules that plug in with your data or configuration. If you'd be happy to use a generic, off-the-shelf prompt for question answering over PDFs or standard text-to-SQL, you will find a rich ecosystem in these libraries. **DSPy** doesn't internally contain hand-crafted prompts that target specific applications. Instead, **DSPy** introduces a small set of much more powerful and general-purpose modules _that can learn to prompt (or finetune) your LM within your pipeline on your data_. when you change your data, make tweaks to your program's control flow, or change your target LM, the **DSPy compiler** can map your program into a new set of prompts (or finetunes) that are optimized specifically for this pipeline. Because of this, you may find that **DSPy** obtains the highest quality for your task, with the least effort, provided you're willing to implement (or extend) your own short program. In short, **DSPy** is for when you need a lightweight but automatically-optimizing programming model — not a library of predefined prompts and integrations. If you're familiar with neural networks: This is like the difference between PyTorch (i.e., representing **DSPy**) and HuggingFace Transformers (i.e., representing the higher-level libraries).
**DSPy vs. generation control libraries like Guidance, LMQL, RELM, Outlines** These are all exciting new libraries for controlling the individual completions of LMs, e.g., if you want to enforce JSON output schema or constrain sampling to a particular regular expression. This is very useful in many settings, but it's generally focused on low-level, structured control of a single LM call. It doesn't help ensure the JSON (or structured output) you get is going to be correct or useful for your task. In contrast, **DSPy** automatically optimizes the prompts in your programs to align them with various task needs, which may also include producing valid structured ouputs. That said, we are considering allowing **Signatures** in **DSPy** to express regex-like constraints that are implemented by these libraries.