brainlid
Supporting structured JSON output for Google AI
Looks like Google supports structured JSON output by supplying a schema through model configuration:
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"contents": [{
"parts":[
{"text": "List 5 popular cookie recipes"}
]
}],
"generationConfig": {
"response_mime_type": "application/json",
"response_schema": {
"type": "ARRAY",
"items": {
"type": "OBJECT",
"properties": {
"recipe_name": {"type":"STRING"},
}
}
}
}
}' 2> /dev/null | head
Would you be interested in a PR that adds this ability, similar to ChatOpenAI implementation (which btw should be documented?)
Hi @vkryukov! Yes, I'd love help implementing and supporting Google Gemini support for structured output with a schema declaration. :smile:
Sounds good, I will try develop a PR to start as a discussion point.
Google's models are improving fast (both gemini-2.0-flash-exp and gemini-exp-1206 are pretty impressive), and they offer massive context windows - so I want to keep testing them. So we need to have a first-class support by LangChain.
That's cool. I've been so underwhelmed and disappointed by Google's past models that I wrote them off for personal use. Glad to hear they are improving!
Yeah, I can relate to that. I plan to post a comparison (eventually); for my use case (code generation), gemini-exp-1206 is not bad! But of course, Sonnet 3.5 New still seems to be the SOTA.
Seconding that this functionality would be very useful.
It looks like Ash AI (which uses this project) supports a StructuredOutput adapter (https://hexdocs.pm/ash_ai/AshAi.Actions.Prompt.Adapter.StructuredOutput.html) which only supports OpenAI for now, but first-class support for Gemini structured output (https://ai.google.dev/gemini-api/docs/structured-output) in Langchain would likely change that.
