Connor - you can pan in and out as much as you want IMO, shows your excitement about the subject. The quality of the content is awesome. Also appreciate the shoutouts to the broader community. Thanks for sharing!

@connorshorten6311

3 ай бұрын

Thank you so much!! Haha, appreciated! Although I see far less negative comments this time around without the zooming haha! Thank you so much! Beyond grateful for all the help the DSPy community has given me in learning about this!

great tutorial Connor, looking forward to more advanced stuff like Agent application!

Great tutorial! I'm looking forward to building on this! Thank you

DSPartY is bumpin’ Love your tutorials and the engagement you’ve been putting in within the DSPy community.

Great walkthrough, thanks so much!

Very exciting stuff, thanks Connor!

@connorshorten6311

3 ай бұрын

Thanks Daniel!

Great one Connor! good to see your progress that, naturally, help us all...

@connorshorten6311

3 ай бұрын

Thank you so much Jose, really happy to hear that! Learning a new tool is certainly quite the journey haha!

looking fresh my dude

@connorshorten6311

3 ай бұрын

Haha thank you!

Brilliant Connor, thanks so much for this video and looking forward to more about this subject!

@connorshorten6311

3 ай бұрын

Thank you so much Brad! Really happy to hear it! DSPy!

Thank you Connor. This is exactly what the world needed.

@connorshorten6311

3 ай бұрын

Thank you so much Clint, appreciate it as always!

Thank You. This particular vid motivated me to SUBSCRIBE !

Thanks for the detailed video Connor, This is a great help. I am working on the lang graph and multi agent models. I had to optimise some of my prompts manually to reduce the number of agent hops to llm model. With BaysianSignature optimizer, I believe every prompt can be optimised and it'll reduce the hops made by agents

@connorshorten6311

3 ай бұрын

Ah, I need to learn a little more about LangGraph and I think Crew AI as the latest Multi-Agent framework before I can really comment on this!

Thank you, Connor! Keep it up!

@connorshorten6311

3 ай бұрын

Thanks!

Awesome, super inspiring!

Thanks for the great content. One of the things I am missing is how to save the optimized program so I can use it after that without constantly re-training.

Nice video, Connor. Could you do a more in-depth video on the optimization process? In particular, looking at the series of prompts/examples selected throughout the optimization (analogous to doing a small lin. regression/backprop example by hand for intuition) and the overall token cost of these optimizations.

@connorshorten6311

3 ай бұрын

Ah indeed this is quite the test of my comprehension! Thank you so much, this is a fantastic idea! Give me a little bit of time to work through this though -- I will send this message through to the DSPy discord, I'm sure Omar, Michael, or Krista would be happy to walk us through this!

Conner - Thanks for the shoutout!! ❤

@connorshorten6311

3 ай бұрын

No thank *you*! Ollama in DSPy!! Amazing!

This was a fantastic walkthrough! Would love some insight into extracting structured data - I find this extremely useful, and being able to do this with a 7B/13B model (instead of GPT-4, for instance) would greatly decrease the cost of running my application. Thanks so much!

lets gooo

You should also make a video on each GPT call cost. I believe there are hundreds (if not thousands) of calls happening every execution. DSPy is best paired with local model like mistral 7b. Otherwise, it will be impossible to scale such a tool on hundreds of docs.

@neoxelox

3 ай бұрын

If you are not compiling the program there aren't that many calls happening... Just one call per module (ChainOfThough/Predict/ReAct..) actually. You can check every step in the pipeline with dspy-inspector for example

@connorshorten6311

3 ай бұрын

Yes this is exactly where my thinking is going after getting the bill for the video hahah, but more generally yeah my suspicion is that llamas connected in DSPy programs is where the value is -- need to test more to say for sure!

@connorshorten6311

3 ай бұрын

@@neoxelox Ah thank you! A new DSPy tool to try out haha `dspy-inspector`!

@user-bs6ih7ww8g

3 ай бұрын

@@connorshorten6311 Can you make a video about it? and also another video on some of the pros & cons of using DSPy in production (if any - wrt cost, latency, scalability, & flexibility)?

Thank you for fixing the zooming!

@connorshorten6311

3 ай бұрын

Haha you got it! Apologies for last time! The zooming has been fired!

Hay man, great video! I have a few questions tho. Can you use other vector DB as retriever like Milvus? Also, is it possible to use LLM that are less known like Baichuan, Kimi etc? Thank you!

So many haters wtf. Great video !! I been lazy in python bc of copy paste and langchain and llama-index. This video makes python more fun !

could we cover the creation of the schema from an empty database such that the notebook flow actually runs through

You tried with weaviem is there any way you could do with pinecone ?

How can I load and use my own data to Weaviate and start implementing DSpy's implementation of RAG?

Any idea why the bootstrap with random search performed worse on the eval set? @ 29:00

Is it possible to run DSPY on local windows environment, say with Mistral 7b model? It fails to for me because of default value of url param, which I do know how to avoid.

Can you apply DSPy RAG on PDF files?

Can I conclude that this framework is simply a prompt optimization framework? The rest is almost the same as llamaindex and langchain?

No offense but you took 4 min to get to the point. Time is the most valuable resource. And it is even more important with the plethora of information in the fast moving generative AI space. So please be ruthless in cutting down non-value add content. I'm not criticizing but I'm just voicing an opinion on great videos like this where you can be even more due diligent on our audience time

@edwardgao5388

2 ай бұрын

This comment took you longer than 4

@explorer945

2 ай бұрын

@@edwardgao5388 true. I did that to see if the OP can save me some time in the future

@ahmadzaimhilmi

Ай бұрын

Thanks. Saved my 4 minutes 😅

so for production, we'd just copy paste the optimized signature and few-shots into the system prompt? I'm a bit confused on how to wield this tool in production.