Swarmauri Parser Entityrecognition
Named-entity recognition (NER) parser for Swarmauri built on spaCy. Extracts entities (PERSON, ORG, GPE, etc.) from unstructured text and returns Document objects with entity metadata.
Features
- Uses spaCy's
en_core_web_smmodel by default (downloads automatically if missing). - Falls back to a blank English pipeline with minimal regex-based tagging when the full model is unavailable (best-effort mode).
- Emits
Documentinstances containing the entity text and metadata (entity_type,entity_id).
Prerequisites
- Python 3.10 or newer.
- spaCy and its English model. The parser attempts to download
en_core_web_smif missing; setSPACY_HOMEor pre-install the model in production deployments. - If running without internet access, install the model ahead of time:
python -m spacy download en_core_web_sm.
Installation
# pip
pip install swarmauri_parser_entityrecognition
# poetry
poetry add swarmauri_parser_entityrecognition
# uv (pyproject-based projects)
uv add swarmauri_parser_entityrecognition
Quickstart
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_doc in entities:
print(entity_doc.content, entity_doc.metadata["entity_type"])
Batch Processing
texts = [
"Apple Inc. unveiled new MacBooks in California.",
"Tim Cook met investors in New York City.",
]
parser = EntityRecognitionParser()
results = [parser.parse(t) for t in texts]
for doc_set in results:
for doc in doc_set:
print(doc.content, doc.metadata["entity_type"])
Handling Fallback Mode
When spaCy's English model is unavailable, the parser performs best-effort matching using a blank pipeline and simple regex patterns. Check for entity_type values and the entity_id metadata to understand which mode produced the result.
parser = EntityRecognitionParser()
entities = parser.parse("Tim Cook announced new products in New York City for Apple Inc.")
print([d.metadata for d in entities])
Install spaCy models before production use to avoid fallback accuracy losses.
Tips
- For languages beyond English, load a different spaCy model by changing the initialization logic (e.g., subclass the parser and load
es_core_news_sm). - Preprocess text to remove noise (HTML tags, markup) before parsing to improve NER accuracy.
- Combine with Swarmauri middleware or pipelines to fuse entity data with downstream tasks (e.g., knowledge graph enrichment, anonymization).
Want to help?
If you want to contribute to swarmauri-sdk, read up on our guidelines for contributing that will help you get started.
1 maintainer
Metadata
1 maintainer
Release files for swarmauri_parser_entityrecognition 0.8.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| swarmauri_parser_entityrecognition-0.8.3.tar.gz | 8.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| swarmauri_parser_entityrecognition-0.8.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 18.5 kB
Release files / swarmauri_parser_entityrecognition-0.8.3.tar.gz
| Download URL | swarmauri_parser_entityrecognition-0.8.3.tar.gz |
|---|---|
| Size | 8.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3e4a00ddd218b30d0be8732280f5512acde444cdc92bb35fe67343e55a97a824
|
|
BLAKE2b-256 checksum How to use checksums |
689db7c80585f17a1d11950a2162c61fe1857e425b0f8b7b033109a9596eabfe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.0 {"installer":{"name":"uv","version":"0.11.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / swarmauri_parser_entityrecognition-0.8.3-py3-none-any.whl
| Download URL | swarmauri_parser_entityrecognition-0.8.3-py3-none-any.whl |
|---|---|
| Size | 9.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c33d60f82d0ce901a595d602eee37cc977da888711fa8e3643661e868ceb0ba4
|
|
BLAKE2b-256 checksum How to use checksums |
8f26db964017723beefbe2c5449a6ade662eb3978259aa47f1114217d6a93ff4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.0 {"installer":{"name":"uv","version":"0.11.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
