/explore
|
You are here 
|
mydeveloperplanet.com | ||
| | | | |
isthisit.nz
August 2024 Update: Now a solved problem. Use Structured Outputs. Large language models (LLMs) return unstructured output. When we prompt them they respond with one large string. This is fine for applications such as ChatGPT, but in others where we want the LLM to return structured data such as lists or key value pairs, a parseable response is needed. In Building A ChatGPT-enhanced Python REPL I used a technique to prompt the LLM to return output in a text format I could parse. |
|
| | | | | ||
| | | | |
hypernephelist.com
In recent projects, I've been exploring the potential of large language models (LLMs) not just to generate code snippets but also to execute them safely in i... |
|
| | | | | ||
| | | | |
passo.uno
If you've been following the AI space for a while, the MCP acronym might be a familiar sight: it's an open standard for connecting large language models (LLMs) to tools and data. Without the ability to use tools and get data, AI agents are powerless, their knowledge limited to their training set and the context at hand. Giving in to my curiosity, I created an MCP server to demystify this piece of tech and gain a better understanding of its potential. Not all is rosy, but if there's a place where doc tools need to grow, it's this. |
|
| | | | | ||
| | | | |
www.purplefrogsystems.com
Query Store is a fantastic feature of both SQL Server and Azure SQL DB. It allows you to monitor how queries execute against the database which is invaluable for troubleshooting performance issues. More than that though, it gives you the option to force an erratic query to use a particular execution plan, this helps avoid queries from running with inefficient plans and provides predictability and stability on the server. Here we can see an example of a query that hasn't been forced and the engine is free to execute it however it sees fit, as you can see, the variation... |
|
| | | |||
