swarmauri_parser_keywordextractor 0.6.0.dev154__tar.gz

swarmauri_parser_keywordextractor-0.6.0.dev154/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_parser_keywordextractor
+Version: 0.6.0.dev154
+Summary: Keyword Extractor Parser for Swarmauri.
+License: Apache-2.0
+Author: Jacob Stewart
+Author-email: jacob@swarmauri.com
+Requires-Python: >=3.10,<3.13
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: swarmauri_base (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: yake (==0.4.8)
+Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
+Description-Content-Type: text/markdown
+
+# Swarmauri Example Plugin

swarmauri_parser_keywordextractor-0.6.0.dev154/README.md

@@ -0,0 +1 @@
+# Swarmauri Example Plugin

swarmauri_parser_keywordextractor-0.6.0.dev154/pyproject.toml

@@ -0,0 +1,56 @@
+[tool.poetry]
+name = "swarmauri_parser_keywordextractor"
+version = "0.6.0.dev154"
+description = "Keyword Extractor Parser for Swarmauri."
+authors = ["Jacob Stewart <jacob@swarmauri.com>"]
+license = "Apache-2.0"
+readme = "README.md"
+repository = "http://github.com/swarmauri/swarmauri-sdk"
+classifiers = [
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.13"
+
+# Swarmauri
+swarmauri_core = {version = "^0.6.0.dev154"}
+swarmauri_base = {version = "^0.6.0.dev154"}
+
+# Dependencies
+yake = "==0.4.8"
+
+[tool.poetry.group.dev.dependencies]
+flake8 = "^7.0"
+pytest = "^8.0"
+pytest-asyncio = ">=0.24.0"
+pytest-xdist = "^3.6.1"
+pytest-json-report = "^1.5.0"
+python-dotenv = "*"
+requests = "^2.32.3"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+norecursedirs = ["combined", "scripts"]
+
+markers = [
+    "test: standard test",
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "acceptance: Acceptance tests",
+    "experimental: Experimental tests"
+]
+log_cli = true
+log_cli_level = "INFO"
+log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
+log_cli_date_format = "%Y-%m-%d %H:%M:%S"
+asyncio_default_fixture_loop_scope = "function"
+
+[tool.poetry.plugins."swarmauri.parsers"]
+KeywordExtractorParser = "swarmauri_parser_keywordextractor:KeywordExtractorParser"

swarmauri_parser_keywordextractor-0.6.0.dev154/swarmauri_parser_keywordextractor/KeywordExtractorParser.py

@@ -0,0 +1,55 @@
+import yake
+from typing import List, Union, Any, Literal
+from pydantic import ConfigDict, PrivateAttr
+from swarmauri_standard.documents.Document import Document
+from swarmauri_base.parsers.ParserBase import ParserBase
+from swarmauri_core.ComponentBase import ComponentBase
+
+
+@ComponentBase.register_type(ParserBase, "KeywordExtractorParser")
+class KeywordExtractorParser(ParserBase):
+    """
+    Extracts keywords from text using the YAKE keyword extraction library.
+    """
+
+    lang: str = "en"
+    num_keywords: int = 10
+    _kw_extractor: yake.KeywordExtractor = PrivateAttr(default=None)
+    model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
+    type: Literal["KeywordExtractorParser"] = "KeywordExtractorParser"
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        self._kw_extractor = yake.KeywordExtractor(
+            lan=self.lang,
+            n=3,
+            dedupLim=0.9,
+            dedupFunc="seqm",
+            windowsSize=1,
+            top=self.num_keywords,
+            features=None,
+        )
+
+    def parse(self, data: Union[str, Any]) -> List[Document]:
+        """
+        Extract keywords from input text and return as list of Document instances containing keyword information.
+
+        Parameters:
+        - data (Union[str, Any]): The input text from which to extract keywords.
+
+        Returns:
+        - List[Document]: A list of Document instances, each containing information about an extracted keyword.
+        """
+        # Ensure data is in string format for analysis
+        text = str(data) if not isinstance(data, str) else data
+
+        # Extract keywords using YAKE
+        keywords = self._kw_extractor.extract_keywords(text)
+
+        # Create Document instances for each keyword
+        documents = [
+            Document(content=keyword, metadata={"score": score})
+            for index, (keyword, score) in enumerate(keywords)
+        ]
+
+        return documents

swarmauri_parser_keywordextractor-0.6.0.dev154/swarmauri_parser_keywordextractor/__init__.py

@@ -0,0 +1,14 @@
+from .KeywordExtractorParser import KeywordExtractorParser
+
+__version__ = "0.6.0.dev26"
+__long_desc__ = """
+
+# Swarmauri Keyword Extractor Plugin
+
+This repository includes a Keyword Extractor of a Swarmauri Plugin.
+
+Visit us at: https://swarmauri.com
+Follow us at: https://github.com/swarmauri
+Star us at: https://github.com/swarmauri/swarmauri-sdk
+
+"""