Understand DSPy: Programming AI Pipelines

  Рет қаралды 3,307

code_your_own_AI

code_your_own_AI

Ай бұрын

The origin and evolution of DSPy: Programming AI Pipelines introduces the idea, its link to ColBERT v2, retriever models, modular pipeline generation, descriptive programming, the evolution and the use case of DSPy (DSPy == Declarative Self-improving Language Programs, pythonically).
Q answered: Is DSPy only a Prompt Engineering optimization?
Q answered: Is DSPy expensive for my AI pipeline optimization?
Q answered: Can I substitute DSPy with a simple many-shot In-Context Learning prompt?
#airesearch

Пікірлер: 9
@RentongGuo-cd2gq
@RentongGuo-cd2gq 20 сағат бұрын
Thanks for the presentation! it helps a lot for the milvus community
@JosepOriol24
@JosepOriol24 Ай бұрын
Top tier high-level presentation of the amazing DSPy vs ICL, this will help me a lot in my current line of work, keep it up!
@densonsmith2
@densonsmith2 Ай бұрын
You continue to stay one step ahead of me. Thank you so much!
@StoianAtanasov
@StoianAtanasov Ай бұрын
Thanks for the presentation! Any plans to make a demo?
@amirhosseinteymoori6537
@amirhosseinteymoori6537 Ай бұрын
Nice! please explain about ReAct and also having different modules. Like ReAct and ChainOfThoughts together,
@ruslan.vasylev
@ruslan.vasylev Ай бұрын
Good info, but a bit too much slide-reading and not enough graphs or going over the code. I've been meaning to replace pure RAG in my pipeline with DSPy, but I haven't found any examples of how to actually do this.... and I'm just a bit afraid of touching this can of worms just yet before seeing someone else do the same. :D
@DannyGerst
@DannyGerst 15 күн бұрын
What about release some code with your videos as well?
@code4AI
@code4AI 15 күн бұрын
Sure. can you be more specific? What have you been not able to discover?
@DannyGerst
@DannyGerst 14 күн бұрын
@@code4AI How you applied DSPY to optimize the prompt for the sample you meantioned in your video? Still struggle to find the first step into that. ;-)
New Discovery: Retrieval Heads for Long Context
30:50
code_your_own_AI
Рет қаралды 2,5 М.
New Discovery: LLMs have a Performance Phase
29:51
code_your_own_AI
Рет қаралды 12 М.
How to bring sweets anywhere 😋🍰🍫
00:32
TooTool
Рет қаралды 31 МЛН
Climbing to 18M Subscribers 🎉
00:32
Matt Larose
Рет қаралды 17 МЛН
Is it Cake or Fake ? 🍰
00:53
A4
Рет қаралды 16 МЛН
Structured Outputs with DSPy
28:54
Connor Shorten
Рет қаралды 6 М.
A Gentle Introduction to DSPy in Python Part 1
25:53
Learn By Building AI
Рет қаралды 4,5 М.
No more Fine-Tuning: Unsupervised ICL+
31:09
code_your_own_AI
Рет қаралды 4,6 М.
The Attention Mechanism in Large Language Models
21:02
Serrano.Academy
Рет қаралды 80 М.
Llama 3 Fine Tuning for Dummies (with 16k, 32k,... Context)
23:16
Nodematic Tutorials
Рет қаралды 19 М.
In-Context Learning: EXTREME vs Fine-Tuning, RAG
21:42
code_your_own_AI
Рет қаралды 3,4 М.
Unlimited AI Agents running locally with Ollama & AnythingLLM
15:21
Main filter..
0:15
CikoYt
Рет қаралды 3,2 МЛН
AI от Apple - ОБЪЯСНЯЕМ
24:19
Droider
Рет қаралды 84 М.
Хотела заскамить на Айфон!😱📱(@gertieinar)
0:21
Взрывная История
Рет қаралды 324 М.
Где раздвижные смартфоны ?
0:49
Не шарю!
Рет қаралды 793 М.
cool watercooled mobile phone radiator #tech #cooler #ytfeed
0:14
Stark Edition
Рет қаралды 9 МЛН