One more cookbook:
Agent for self-correcting Text-to-SQL What if the query generated by your Text-to-SQL pipeline is correct SQL but returns wrong results? We need to add a critique step That's very simple with an agent!
Check out the notebook!
PROMPT ENGINEERING
-
AI Agent for Self-Correcting Text-to-SQL Queries
By
–
-
Using Custom GPTs for News Headline Writing
By
–
Headline writing is a very nice AI use case for news publishers. A Custom GPT works perfectly for this purpose I was experimenting with it as well. Works super well for me.
-
Project Names as Shorthand for Complex AI Concepts
By
–
To add to that, it’s awesome that you can use project names as short-hand for complex ideas. For example, you could ask for “a BabyAGI that uses Multi-On to execute tasks” which is a complex but clear idea in a few words.
-
Better Performance Through Right Customization
By
–
Seeing performance way better when customizing right now
-
Claude Sonnet 3.5 enables BabyAGI implementation without frameworks
By
–
Apparently Claude Sonnet 3.5 can code you your own implementation of BabyAGI Starting here and iterating on this with Claude should be a good start/exercise for anyone looking to build an autonomous agent without relying on external frameworks.
-
Yi-Large Excels in Creative Writing with Customized Prompts
By
–
With the right prompts, Yi-Large performs very well in various styles of creative writing from fiction to fantasy. We encourage developers to try with specific genre, style, length, tone and manner prompts. You may also ask Yi-Large to write like certain known authors/literary
-
Using custom prompts in Perplexity Collections
By
–
Perplexity “projects”? Not sure how new is this but you can add a custom prompt to your Collections on Perplexity. All new threads started from such collection will have it applied. I submitted it as a feature request 2 weeks ago but now not 100% if it was already there
-
ICL versus Fine-tuning: Cost-Latency Trade-offs in LLM Optimization
By
–
I agree actually, if a problem can be solved with ICL (in terms of cost, latency, etc. and not just accuracy), then it's perfect. But I want to point out that it also makes fine-tuning even more relevant in a lot of use cases.
-
Ctrl-G Framework: Logical Control for LLM Generation
By
–
7/ Adaptable Logical Control for LLMs – presents the Ctrl-G framework to facilitate control of LLM generations that reliably follow logical constraints; it combines LLMs and Hidden Markow Models to enable following logical constraints (represented as deterministic finite
-
RAG Best Practices: Multimodal Retrieval and Performance Optimization
By
–
3/ Searching for Best Practices in RAG – shows the best practices for building effective RAG workflows; proposes strategies that focus on performance and efficiency, including emerging multimodal retrieval techniques.