Art
05/06/2023, 7:20 PMattr_1:
type: number
minimum: 0
maximum: 30
attr_2:
type: string
enum: [value_1, value_2, etc]
and 50 more attributes like that.
How are you optimizing long-structured schema prompts? What are the potential workarounds? Would love to hear from the community 🤖Daniel Hsu
05/06/2023, 7:27 PMArt
05/06/2023, 7:56 PMThat said, are you sure you need to have the entirety of the schema in a single prompt?My goal is to evaluate products described in the documents against specific attributes and then rank products based those attributes in memory (for now). The same product might be mentioned in multiple documents and I am trying to get an aggregate of the attributes across multiple documents. if not passing the schema into the prompt, how would you get a structured data in the output, what are the options here? so the simplified pipeline is: documents (multiple products per document) -> products with attributes -> User input on attributes (structured) -> ranking of products based on the attributes that matter. I am not sure if that’s the best pipeline, but curios if you have any thoughts on that.
Daniel Hsu
05/06/2023, 7:58 PMArt
05/06/2023, 8:06 PMDaniel Hsu
05/07/2023, 7:52 PMArt
05/07/2023, 11:30 PMviksit
05/09/2023, 6:41 PMHarsha Sabbineni
05/11/2023, 11:12 PMDaniel Hsu
05/11/2023, 11:19 PMHarsha Sabbineni
05/12/2023, 5:06 PM