openai function call + langchain for SQL query with vector search:
https://docs.myscale.com/en/sample-applications/openai-funct... https://github.com/myscale/examples/blob/main/openai_functio...
Function calling and other API updates
171–174 of 174 posts
Re: Function calling and other API updates
#172GPT3.5 has been undergoing constant improvements, this price decrease (and context length increase) is great news! The main problem I see with people using GPT3.5 is they try and ask it to "write a short story about aliens" and then they get back a crap boring response that sounds like it was written by an AI that was asleep at the wheel. Good creative prompts are long and detailed, and to get the best results you re…
I just tell it how to write a good story before asking for a story (show, don't tell. Don't list descriptions each time a new thing appears, instead let it become apparent. Withhold information from the reader to build tension, hint and further lore and be creative with your world building) etc, maybe I'll come back and publish some of my prompts in full but I'm getting great results
Re: Function calling and other API updates
#173I was playing with this today made a simple add function that just takes two arguments and adds them and asked it "what is 10+5" and it called my function as you would expect. Then I made my function multiple the numbers. Weirdly gpt called my function twice then simply ignored the functions data and returned the correct answer. Pretty impressive.
Not sure I like the "I know better" attitude of the LLM in this case. What other function response the LLM is likely to discard?
I updated a slack bot to support calling dalle but none of the images work because it striped the query parameters from the URLs. Very annoying
Re: Function calling and other API updates
#174I was playing with this today made a simple add function that just takes two arguments and adds them and asked it "what is 10+5" and it called my function as you would expect. Then I made my function multiple the numbers. Weirdly gpt called my function twice then simply ignored the functions data and returned the correct answer. Pretty impressive.
Not sure I like the "I know better" attitude of the LLM in this case. What other function response the LLM is likely to discard?
This one isn't new at least.