| Note the "Sign in with Hugging Face" button that is added with my page, can I just auto | |
| <iframe src="https://fraser-piclets.static.hf.space/index.html?embed=true&__sign=eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sIm9uQmVoYWxmT2YiOnsia2luZCI6InVzZXIiLCJfaWQiOiI1ZjE5NTc4NDkyNWI5ODYzZTI4YWQ2MTAiLCJ1c2VyIjoiRnJhc2VyIiwic2Vzc2lvbklkIjoiNjg3NjU0ZjZhYmI2ZWE2ZTk0OThkNjVmIn0sImlhdCI6MTc1MjY1NzYxMiwic3ViIjoiL3NwYWNlcy9GcmFzZXIvcGljbGV0cyIsImV4cCI6MTc1Mjc0NDAxMiwiaXNzIjoiaHR0cHM6Ly9odWdnaW5nZmFjZS5jbyJ9.vH_qEMDwpCpEapX36n-JPgfj6P7jxGdpwomhT6MIpY-r2OS9Wc1bFsQq0USfbQqKxif2rR9XL7sB8f0ximxCDA" aria-label="static space app" class="space-iframe outline-hidden grow bg-white p-0" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; clipboard-read; clipboard-write; display-capture; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; serial; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-downloads allow-forms allow-modals allow-pointer-lock allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-storage-access-by-user-activation" scrolling="yes" id="iFrameResizer0" style="overflow: auto;"></iframe> | |
| --- | |
| Now I would also like the text generator to produce a JSON object based on the monster concept. | |
| This will be created with the following schema: | |
| - name: string | |
| - description: string | |
| - rarity: likert (very-low, low, medium, high, very-high) | |
| - HP: likert | |
| - defence: likert | |
| - attack: likert | |
| - speed: likert | |
| - special ability: string (passive trait that gives the monster a unique advantage in battle) | |
| - attack action description: string (deals damage) | |
| - boost action description: string (buff monsters own stats/status) | |
| - disparage action description: string (lowers enemy stats/status) | |
| - special action description: string (powerful action with single use per battle) | |
| Also update the DB to use this JSON data in its schema. | |
| --- | |
| ```python | |
| import json | |
| from pydantic import BaseModel | |
| STRUCTURED_OUTPUT_FORMAT_INSTRUCTIONS = """The output should be formatted as a JSON instance that conforms to the JSON schema below. | |
| As an example, for the schema {{"properties": {{"foo": {{"title": "Foo", "description": "a list of strings", "type": "array", "items": {{"type": "string"}}}}}}, "required": ["foo"]}} | |
| the object {{"foo": ["bar", "baz"]}} is a well-formatted instance of the schema. The object {{"properties": {{"foo": ["bar", "baz"]}}}} is not well-formatted. | |
| Here is the output schema: | |
| ``` | |
| {schema} | |
| ```""" | |
| class StructuredOutputParser(BaseModel): | |
| pydantic_class: type[BaseModel] | |
| def get_schema(self, indent: int = 2) -> str: | |
| # Copy schema to avoid altering original Pydantic schema. | |
| schema = self.pydantic_class.model_json_schema() | |
| # Iterate over fields to remove from the schema | |
| for field_name in ["title", "type"]: | |
| if field_name in schema: | |
| schema.pop(field_name) | |
| return json.dumps(schema, indent=indent, ensure_ascii=False) | |
| def get_format_instructions(self) -> str: | |
| schema_str = self.get_schema() | |
| # Ensure json in context is well-formed with double quotes. | |
| return STRUCTURED_OUTPUT_FORMAT_INSTRUCTIONS.format(schema=schema_str) | |
| def parse(self, json_string: str) -> BaseModel: | |
| return self.pydantic_class.model_validate_json(json_string) | |
| ``` |