Client.beta.chat.completions pass json schema rather than pydantic format

API
1

Using the python lib with structure outputs,
is there a way to pass the json schema, rather than a pydantic format?
(as I need to generate the schema dynamically)

Passing from:

from pydantic import BaseModel
from openai import OpenAI

doc = "Why did the chicken cross the road? To get to the other side. haha."
class Info(BaseModel):
	title: str
	tags: list[str]

completion = client.beta.chat.completions.parse(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "Extract the title and tags"},
        {"role": "user", "content": doc},
    ],
    response_format=MathResponse,
)
message = completion.choices[0].message
print(message.parsed.title, message.parsed.tags)

to something like this:

response_format = {
	"properties": {
	  "title": {
		"title": "Title",
		"type": "string"
	  },
	  "tags": {
		"items": {
		  "type": "string"
		},
		"title": "Tags",
		"type": "array"
	  }
	},
	"required": [
	  "title",
	  "tags"
	],
	"title": "Info",
	"type": "object"
}

completion = client.beta.chat.completions.parse(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "Extract title and tags"},
        {"role": "user", "content": doc},
    ],
    response_format=json.dumps(response_format),   # << what's the right way here?
)
message = completion.choices[0].message
print(message['title'], message['tags'])