swarmauri_parser_entityrecognition 0.11.0.dev1

spaCy-based named-entity recognition parser for Swarmauri with structured entity document output.

Swarmauri Parser Entity Recognition

swarmauri_parser_entityrecognition is the Swarmauri named-entity recognition parser built on spaCy. It extracts named entities such as people, organizations, and geopolitical entities from unstructured text and returns Swarmauri Document objects containing the entity text and entity metadata.

Why Use Swarmauri Parser Entity Recognition

• Turn raw text into structured entity objects inside a Swarmauri parser workflow.
• Preserve entity labels and entity ids in a predictable Document shape for downstream enrichment, filtering, or indexing.
• Use spaCy's English NER pipeline when available, while still retaining a minimal fallback path for constrained environments.
• Fit entity extraction into larger ingestion, retrieval, anonymization, and knowledge-graph workflows.

FAQ

What does this parser return?
A list of Swarmauri Document objects, usually one per detected entity.

Which metadata fields are included?
entity_type, entity_id, and text.

What spaCy model does it use?
It tries to load en_core_web_sm.

What happens if the model is unavailable?
The parser attempts to download the model. If that fails, it falls back to a blank English pipeline plus a small regex-based fallback used as a best-effort compatibility path.

Features

• Named-entity extraction via spaCy's English NER model.
• Automatic attempt to download en_core_web_sm if the model is missing.
• Best-effort fallback behavior for environments where the full model cannot be loaded.
• Returns Swarmauri Document objects with entity label metadata.
• Supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.

Installation

uv add swarmauri_parser_entityrecognition

pip install swarmauri_parser_entityrecognition

Optional model bootstrap:

python -m spacy download en_core_web_sm

Usage

from swarmauri_parser_entityrecognition import EntityRecognitionParser

text = "Barack Obama was born in Hawaii and served as President of the United States."
parser = EntityRecognitionParser()
entities = parser.parse(text)

for entity in entities:
    print(entity.content, entity.metadata["entity_type"])

Examples

Parse organizations, places, and people

from swarmauri_parser_entityrecognition import EntityRecognitionParser

parser = EntityRecognitionParser()
docs = parser.parse(
    "Apple Inc. is planning to open a new office in New York City, according to CEO Tim Cook."
)

for doc in docs:
    print(doc.content, doc.metadata)

Handle non-string input

from swarmauri_parser_entityrecognition import EntityRecognitionParser

parser = EntityRecognitionParser()
print(parser.parse(42))

Inspect fallback-compatible metadata

from swarmauri_parser_entityrecognition import EntityRecognitionParser

parser = EntityRecognitionParser()
entities = parser.parse("Tim Cook announced new products in New York City for Apple Inc.")
print([entity.metadata for entity in entities])

Related Packages

• swarmauri_tool_entityrecognition
• swarmauri_tool_sentimentanalysis
• swarmauri_parser_textblob
• swarmauri_parser_bertembedding

Swarmauri Foundations

• swarmauri
• swarmauri_core
• swarmauri_base
• swarmauri_standard

More Documentation

• spaCy named entity recognition docs
• spaCy model installation docs

Best Practices

• Preinstall en_core_web_sm in CI and production environments to avoid runtime downloads.
• Treat the regex fallback as a compatibility path, not as production-quality entity recognition.
• Strip markup or noisy boilerplate before parsing to improve entity quality.
• Persist entity spans or link them to downstream IDs if you need durable knowledge-graph or indexing workflows.

License

This project is licensed under the Apache-2.0 License.