wuenlp_tools.utils.summarize 

 1from typing import List, Type
 2
 3from pathlib import Path
 4
 5from loguru import logger
 6from pydantic import BaseModel
 7from tqdm import tqdm
 8from wuenlp.impl.UIMANLPStructs import UIMADocument, UIMAAnnotation, UIMASystemScene, UIMASpan
 9
10from wuenlp_tools.pipeline import PipelineProcessor
11from wuenlp_tools.utils.prompting import LLM, default_llm
12
13
14class Summary(BaseModel):
15    summary: str
16    keywords: List[str]
17
18
19class Summarizer(LLM):
20    def __init__(self, model=default_llm, system_prompt=None, num_sentences=3):
21        if system_prompt is None:
22            system_prompt = f"You are given a piece of text. Please summarize it in about {num_sentences} sentences."
23        if "{}" in system_prompt:
24            system_prompt = system_prompt.format(num_sentences)
25        if "{num_sentences}" in system_prompt:
26            system_prompt = system_prompt.format(num_sentences=num_sentences)
27        super().__init__(model, system_prompt, output_format=Summary)
28
29
30def summarize_doc(doc: UIMADocument, summarizer: Summarizer = Summarizer(),
31                  unit_type: Type[UIMAAnnotation] = UIMASystemScene,
32                  summary_variable_name="llama_summary",
33                  keyword_variable_name="llama_keywords", overwrite: bool = False, ) -> UIMADocument:
34    segments = doc._get_annos_of_type(unit_type)
35    for i, segment in tqdm(enumerate(segments), total=len(segments)):
36        if not overwrite and summary_variable_name in segment.additional_features and segment.additional_features[
37            summary_variable_name]:
38            continue
39        segment_text = segment.text
40        summary: Summary = summarizer(segment_text)
41        segment.additional_features[summary_variable_name] = summary.summary
42        segment.additional_features[keyword_variable_name] = summary.keywords
43        logger.info(summary)
44    return doc
45
46
47class SummarizeProcessor(PipelineProcessor):
48    def __init__(self, summarizer: Summarizer, overwrite: bool = False, summary_variable_name="llama_summary",
49                 keyword_variable_name="llama_keywords"):
50        self.summarizer = summarizer
51        self.overwrite = overwrite
52        self.summary_variable_name = summary_variable_name
53        self.keyword_variable_name = keyword_variable_name
54
55    def __call__(self, doc: UIMADocument, unit_type: Type[UIMASpan] = UIMASystemScene, overwrite: bool = False,
56                 **kwargs) -> UIMADocument:
57        return summarize_doc(doc, summary_variable_name=self.summary_variable_name,
58                             keyword_variable_name=self.keyword_variable_name, unit_type=unit_type,
59                             summarizer=self.summarizer, overwrite=overwrite)
class Summary(pydantic.main.BaseModel): 
15class Summary(BaseModel):
16    summary: str
17    keywords: List[str]

!!! abstract "Usage Documentation" Models

A base class for creating Pydantic models.

Attributes: __class_vars__: The names of the class variables defined on the model. __private_attributes__: Metadata about the private attributes of the model. __signature__: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.
__pydantic_core_schema__: The core schema of the model.
__pydantic_custom_init__: Whether the model has a custom `__init__` function.
__pydantic_decorators__: Metadata containing the decorators defined on the model.
    This replaces `Model.__validators__` and `Model.__root_validators__` from Pydantic V1.
__pydantic_generic_metadata__: A dictionary containing metadata about generic Pydantic models.
    The `origin` and `args` items map to the [`__origin__`][genericalias.__origin__]
    and [`__args__`][genericalias.__args__] attributes of [generic aliases][types-genericalias],
    and the `parameter` item maps to the `__parameter__` attribute of generic classes.
__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.
__pydantic_post_init__: The name of the post-init method for the model, if defined.
__pydantic_root_model__: Whether the model is a [`RootModel`][pydantic.root_model.RootModel].
__pydantic_serializer__: The `pydantic-core` `SchemaSerializer` used to dump instances of the model.
__pydantic_validator__: The `pydantic-core` `SchemaValidator` used to validate instances of the model.

__pydantic_fields__: A dictionary of field names and their corresponding [`FieldInfo`][pydantic.fields.FieldInfo] objects.
__pydantic_computed_fields__: A dictionary of computed field names and their corresponding [`ComputedFieldInfo`][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__: A dictionary containing extra values, if [`extra`][pydantic.config.ConfigDict.extra]
    is set to `'allow'`.
__pydantic_fields_set__: The names of fields explicitly set during instantiation.
__pydantic_private__: Values of private attributes set on the model instance.
summary: str = PydanticUndefined
keywords: List[str] = PydanticUndefined
class Summarizer(wuenlp_tools.utils.prompting.LLM): 
20class Summarizer(LLM):
21    def __init__(self, model=default_llm, system_prompt=None, num_sentences=3):
22        if system_prompt is None:
23            system_prompt = f"You are given a piece of text. Please summarize it in about {num_sentences} sentences."
24        if "{}" in system_prompt:
25            system_prompt = system_prompt.format(num_sentences)
26        if "{num_sentences}" in system_prompt:
27            system_prompt = system_prompt.format(num_sentences=num_sentences)
28        super().__init__(model, system_prompt, output_format=Summary)
Summarizer( model=LLMArchitecture(name='gpt-5-nano', model='gpt-5-nano', max_tokens=128000, provider='openai', free=False), system_prompt=None, num_sentences=3) 
21    def __init__(self, model=default_llm, system_prompt=None, num_sentences=3):
22        if system_prompt is None:
23            system_prompt = f"You are given a piece of text. Please summarize it in about {num_sentences} sentences."
24        if "{}" in system_prompt:
25            system_prompt = system_prompt.format(num_sentences)
26        if "{num_sentences}" in system_prompt:
27            system_prompt = system_prompt.format(num_sentences=num_sentences)
28        super().__init__(model, system_prompt, output_format=Summary)
Inherited Members
wuenlp_tools.utils.prompting.LLM
proxy_config
litellm_metadata
local_base_url
model
system_prompt
post_prompt
cache_maxsize
seed
json
output_format
with_reasoning
def summarize_doc( doc: wuenlp.impl.uima.UIMANLPStructs.UIMADocument, summarizer: Summarizer = <Summarizer object>, unit_type: Type[wuenlp.impl.uima.UIMANLPStructs.UIMAAnnotation] = <class 'wuenlp.impl.uima.UIMANLPStructs.UIMASystemScene'>, summary_variable_name='llama_summary', keyword_variable_name='llama_keywords', overwrite: bool = False) -> wuenlp.impl.uima.UIMANLPStructs.UIMADocument: 
31def summarize_doc(doc: UIMADocument, summarizer: Summarizer = Summarizer(),
32                  unit_type: Type[UIMAAnnotation] = UIMASystemScene,
33                  summary_variable_name="llama_summary",
34                  keyword_variable_name="llama_keywords", overwrite: bool = False, ) -> UIMADocument:
35    segments = doc._get_annos_of_type(unit_type)
36    for i, segment in tqdm(enumerate(segments), total=len(segments)):
37        if not overwrite and summary_variable_name in segment.additional_features and segment.additional_features[
38            summary_variable_name]:
39            continue
40        segment_text = segment.text
41        summary: Summary = summarizer(segment_text)
42        segment.additional_features[summary_variable_name] = summary.summary
43        segment.additional_features[keyword_variable_name] = summary.keywords
44        logger.info(summary)
45    return doc
class SummarizeProcessor(wuenlp_tools.pipeline.AbstractPipelineProcessor[wuenlp.impl.uima.UIMANLPStructs.UIMADocument]): 
48class SummarizeProcessor(PipelineProcessor):
49    def __init__(self, summarizer: Summarizer, overwrite: bool = False, summary_variable_name="llama_summary",
50                 keyword_variable_name="llama_keywords"):
51        self.summarizer = summarizer
52        self.overwrite = overwrite
53        self.summary_variable_name = summary_variable_name
54        self.keyword_variable_name = keyword_variable_name
55
56    def __call__(self, doc: UIMADocument, unit_type: Type[UIMASpan] = UIMASystemScene, overwrite: bool = False,
57                 **kwargs) -> UIMADocument:
58        return summarize_doc(doc, summary_variable_name=self.summary_variable_name,
59                             keyword_variable_name=self.keyword_variable_name, unit_type=unit_type,
60                             summarizer=self.summarizer, overwrite=overwrite)

Base class for protocol classes.

Protocol classes are defined as::

class Proto(Protocol):
    def meth(self) -> int:
        ...

Such classes are primarily used with static type checkers that recognize structural subtyping (static duck-typing).

For example::

class C:
    def meth(self) -> int:
        return 0

def func(x: Proto) -> int:
    return x.meth()

func(C())  # Passes static type check

See PEP 544 for details. Protocol classes decorated with @typing.runtime_checkable act as simple-minded runtime protocols that check only the presence of given attributes, ignoring their type signatures. Protocol classes can be generic, they are defined as::

class GenProto[T](Protocol):
    def meth(self) -> T:
        ...
SummarizeProcessor( summarizer: Summarizer, overwrite: bool = False, summary_variable_name='llama_summary', keyword_variable_name='llama_keywords') 
49    def __init__(self, summarizer: Summarizer, overwrite: bool = False, summary_variable_name="llama_summary",
50                 keyword_variable_name="llama_keywords"):
51        self.summarizer = summarizer
52        self.overwrite = overwrite
53        self.summary_variable_name = summary_variable_name
54        self.keyword_variable_name = keyword_variable_name
summarizer
overwrite
summary_variable_name
keyword_variable_name