@staticmethod
def from_str(string: str) -> "LLMProvider"

from haystack import Document
from haystack.components.generators import OpenAIGenerator
from haystack_experimental.components.extractors import LLMMetadataExtractor

NER_PROMPT = '''
-Goal-
Given text and a list of entity types, identify all entities of those types from the text.

-Steps-
1. Identify all entities. For each identified entity, extract the following information:
- entity_name: Name of the entity, capitalized
- entity_type: One of the following types: [organization, product, service, industry]
Format each entity as {"entity": <entity_name>, "entity_type": <entity_type>}

2. Return output in a single list with all the entities identified in steps 1.

-Examples-
######################
Example 1:
entity_types: [organization, person, partnership, financial metric, product, service, industry, investment strategy, market trend]
text:
Another area of strength is our co-brand issuance. Visa is the primary network partner for eight of the top 10 co-brand partnerships in the US today and we are pleased that Visa has finalized a multi-year extension of our successful credit co-branded partnership with Alaska Airlines, a portfolio that benefits from a loyal customer base and high cross-border usage.
We have also had significant co-brand momentum in CEMEA. First, we launched a new co-brand card in partnership with Qatar Airways, British Airways and the National Bank of Kuwait. Second, we expanded our strong global Marriott relationship to launch Qatar's first hospitality co-branded card with Qatar Islamic Bank. Across the United Arab Emirates, we now have exclusive agreements with all the leading airlines marked by a recent agreement with Emirates Skywards.
And we also signed an inaugural Airline co-brand agreement in Morocco with Royal Air Maroc. Now newer digital issuers are equally
------------------------
output:
{"entities": [{"entity": "Visa", "entity_type": "company"}, {"entity": "Alaska Airlines", "entity_type": "company"}, {"entity": "Qatar Airways", "entity_type": "company"}, {"entity": "British Airways", "entity_type": "company"}, {"entity": "National Bank of Kuwait", "entity_type": "company"}, {"entity": "Marriott", "entity_type": "company"}, {"entity": "Qatar Islamic Bank", "entity_type": "company"}, {"entity": "Emirates Skywards", "entity_type": "company"}, {"entity": "Royal Air Maroc", "entity_type": "company"}]}
#############################
-Real Data-
######################
entity_types: [company, organization, person, country, product, service]
text: {{input_text}}
######################
output:
'''

docs = [
    Document(content="deepset was founded in 2018 in Berlin, and is known for its Haystack framework"),
    Document(content="Hugging Face is a company founded in Paris, France and is known for its Transformers library")
]

extractor = LLMMetadataExtractor(prompt=NER_PROMPT, expected_keys=["entities"], generator_api="openai", prompt_variable='input_text')
extractor.run(documents=docs)
>> {'documents': [
    Document(id=.., content: 'deepset was founded in 2018 in Berlin, and is known for its Haystack framework',
    meta: {'entities': [{'entity': 'deepset', 'entity_type': 'company'}, {'entity': 'Berlin', 'entity_type': 'city'},
          {'entity': 'Haystack', 'entity_type': 'product'}]}),
    Document(id=.., content: 'Hugging Face is a company founded in Paris, France and is known for its Transformers library',
    meta: {'entities': [
            {'entity': 'Hugging Face', 'entity_type': 'company'}, {'entity': 'Paris', 'entity_type': 'city'},
            {'entity': 'France', 'entity_type': 'country'}, {'entity': 'Transformers', 'entity_type': 'product'}
            ]})
       ]
   }
>>

def __init__(prompt: str,
             prompt_variable: str,
             expected_keys: List[str],
             generator_api: Union[str, LLMProvider],
             generator_api_params: Optional[Dict[str, Any]] = None,
             page_range: Optional[List[Union[str, int]]] = None,
             raise_on_failure: bool = False)

def is_valid_json_and_has_expected_keys(expected: List[str],
                                        received: str) -> bool

def to_dict() -> Dict[str, Any]

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "LLMMetadataExtractor"

@component.output_types(documents=List[Document], errors=Dict[str, Any])
def run(documents: List[Document],
        page_range: Optional[List[Union[str, int]]] = None)