DSPy: The framework for programming—not prompting—language models
Python
Merge branch 'main' into feature/knn-demonstrations-sampler
Igor Kotenkov7ba5bea13ea6
diff --cc README.mdindex 9bc27c459,5c3a79398..07f264af3--- a/README.md+++ b/README.md@@@ -22,10 -44,16 +44,19 @@@ Our [compiler notebook](compiler.ipynbYou can [open the compiler notebook in Google Colab](https://colab.research.google.com/github/stanfordnlp/dsp/blob/main/compiler.ipynb). You don't even need an API key to get started with it.- ## [NEW!] Picking in-context examples using KNN/ANN methods++## Picking in-context examples using KNN/ANN methods [NEW!]++Our [knn demo notebook](tests/knn_demonstrations_test.ipynb) provides examples of adding the KNN stage, as described in the paper. This improvement in the Demonstrate stage of DSP allows you not to sample Examples randomly but instead search for better and similar options. You can get an idea from [this paper](https://arxiv.org/abs/2101.06804).+ ## 📜 Reading More++ You can get an overview via our Twitter threads:+ * [**Introducing DSP**](https://twitter.com/lateinteraction/status/1617953413576425472) (Jan 24, 2023)+ * [**Releasing the DSP Compiler (v0.1)**](https://twitter.com/lateinteraction/status/1625231662849073160) (Feb 13, 2023)++ And read more in the academic paper:+ * [**Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP**](https://arxiv.org/abs/2212.14024.pdf)+## ✍️ ReferenceIf you use DSP in a research paper, please cite our work as follows: