Find answers from the community

Updated 2 months ago

Anyone have this problem where using a

Anyone have this problem where using a pydantic output parser with a LLMProgram and local Ollama returns escaped underscores for field names and messes up the json parsing ?
Plain Text
{
"type": "PLAY\_CARD",
"card\_id": "b473cd1a-0370-4971-8db5-c5a7f007fee1",
"end\_turn": false
}

this is what the LLM returns
T
M
3 comments
Which LLM are you using? Open source models usually struggle with structured outputs
I actually switched it to Gemma and its working great, and even faster than Mistral
Add a reply
Sign up and join the conversation on Discord