DSPy (Demonstrate-Search-Predict)
http://www.semanlink.net/tag/dsp_demonstrate_search_predict
Documents tagged with DSPy (Demonstrate-Search-Predict)NER using DSPy
http://www.semanlink.net/doc/2024/04/ner_using_dspy
2024-04-12T09:34:33ZLeonie sur X : "Ollama allows you to run open source LLMs LOCALLY..."
http://www.semanlink.net/doc/2024/03/leonie_sur_x_what%E2%80%99s_the_deal
Ollama: good name, anyway
2024-03-30T01:39:42ZDSPy Cheatsheet | DSPy
http://www.semanlink.net/doc/2024/03/dspy_cheatsheet_%7C_dspy
2024-03-30T01:35:56ZKrista Opsahl-Ong sur X : "Got a pipeline with **multiple prompts**, like a DSPy program? ... Introducing MIPRO, a Multi-prompt Instruction Proposal Optimizer...."
http://www.semanlink.net/doc/2024/03/krista_opsahl_ong_sur_x_got_
2024-03-09T11:37:47ZIntro to DSPy: Goodbye Prompting, Hello Programming! | by Leonie Monigatti | Feb, 2024 | Towards Data Science
http://www.semanlink.net/doc/2024/03/intro_to_dspy_goodbye_promptin
2024-03-01T02:17:40ZOmar Khattab sur X : "...Let's use 30 lines of DSPy—without any hand-written prompts or any calls to OpenAI ($0)—to teach..."
http://www.semanlink.net/doc/2024/01/omar_khattab_sur_x_a_cool_th
2024-01-01T11:01:32ZInside DSPy: The New Language Model Programming Framework You Need… – Towards AI
http://www.semanlink.net/doc/2023/09/inside_dspy_the_new_language_m
2023-09-06T13:28:30ZOmar Khattab sur X : "Announcing 𝗗𝗦𝗣y..."
http://www.semanlink.net/doc/2023/08/omar_khattab_sur_x_%F0%9F%9A%A8announc
2023-08-24T19:28:45Z[2212.14024] Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
http://www.semanlink.net/doc/2023/06/2212_14024_demonstrate_search
2023-06-23T09:54:22ZJerry Liu sur Twitter : "The DSP project carries a lot of insights for improving RAG..."
http://www.semanlink.net/doc/2023/06/jerry_liu_sur_twitter_the_ds
> - value of few-shot ex’s
> - declarative modules
> - compile an optimized system with distilled LM’s
2023-06-18T10:27:05ZLangChain Retrieval Webinar - YouTube
http://www.semanlink.net/doc/2023/05/langchain_retrieval_webinar_y
[ColBERT](tag:colbert) retrieval model and the [DSP](doc:2023/02/stanfordnlp_dsp_𝗗𝗦𝗣_demons) programming model
2023-05-27T15:24:39Zstanfordnlp/dspy: 𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP.
http://www.semanlink.net/doc/2023/02/stanfordnlp_dsp_%F0%9D%97%97%F0%9D%97%A6%F0%9D%97%A3_demons
(initially called DSP, rebranded as DSPy)
> The DSP framework provides a programming abstraction for building grounded AI systems. In a few lines of code, a DSP program expresses rich interactions between retrieval models (RMs) and language models (LMs) to tackle difficult knowledge-intensive NLP tasks (e.g., complex question answering or conversational search).
> DSP discourages ["prompt engineering"](tag:prompted_models), which we view much the same way as hyperparameter tuning in traditional ML
[@matei_zaharia](https://twitter.com/matei_zaharia/status/1626705622585716737?s=20):
>Who are the World Cup champions? I knew ChatGPT would get it wrong when it launched, but it's surprising that all the new search+LLM engines do too.
>
> **Combining retrieval+LMs won't just be a matter of prompting**. That's why we've been building tools like DSP at Stanford to do it.
2023-02-18T11:32:46Z