swarmauri_embedding_doc2vec 0.6.0.dev154__tar.gz

swarmauri_embedding_doc2vec-0.6.0.dev154/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_embedding_doc2vec
+Version: 0.6.0.dev154
+Summary: A Doc2Vec based Embedding Model.
+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: gensim (==4.3.3)
+Requires-Dist: swarmauri_base (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
+Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
+Description-Content-Type: text/markdown
+
+# Swarmauri Example Plugin

swarmauri_embedding_doc2vec-0.6.0.dev154/README.md

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

swarmauri_embedding_doc2vec-0.6.0.dev154/pyproject.toml

@@ -0,0 +1,58 @@
+[tool.poetry]
+name = "swarmauri_embedding_doc2vec"
+version = "0.6.0.dev154"
+description = "A Doc2Vec based Embedding Model."
+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
+gensim = "==4.3.3"
+
+
+[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.embeddings"]
+Doc2VecEmbedding = "swarmauri_embedding_doc2vec:Doc2VecEmbedding"
+

swarmauri_embedding_doc2vec-0.6.0.dev154/swarmauri_embedding_doc2vec/Doc2VecEmbedding.py

@@ -0,0 +1,82 @@
+from typing import List, Any, Literal
+from gensim.models.doc2vec import Doc2Vec, TaggedDocument
+from swarmauri_standard.vectors.Vector import Vector
+from swarmauri_base.embeddings.EmbeddingBase import EmbeddingBase
+from swarmauri_core.ComponentBase import ComponentBase
+
+
+@ComponentBase.register_type(EmbeddingBase, "Doc2VecEmbedding")
+class Doc2VecEmbedding(EmbeddingBase):
+    _model: Doc2Vec
+    type: Literal["Doc2VecEmbedding"] = "Doc2VecEmbedding"
+
+    def __init__(
+        self,
+        vector_size: int = 3000,  # Reduced size for better performance
+        window: int = 10,
+        min_count: int = 1,
+        workers: int = 5,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self._model = Doc2Vec(
+            vector_size=vector_size,
+            window=window,
+            min_count=min_count,
+            workers=workers,
+        )
+
+    def fit(self, documents: List[str], labels=None) -> None:
+        tagged_data = [
+            TaggedDocument(words=doc.split(), tags=[str(i)])
+            for i, doc in enumerate(documents)
+        ]
+
+        # Check if the model already has a vocabulary built
+        if len(self._model.wv) == 0:
+            self._model.build_vocab(
+                tagged_data
+            )  # Build vocabulary if not already built
+        else:
+            self._model.build_vocab(
+                tagged_data, update=True
+            )  # Update the vocabulary if it exists
+
+        self._model.train(
+            tagged_data,
+            total_examples=self._model.corpus_count,
+            epochs=self._model.epochs,
+        )
+
+    def extract_features(self) -> List[Any]:
+        return list(self._model.wv.key_to_index.keys())
+
+    def infer_vector(self, data: str) -> Vector:
+        words = data.split()
+        # Check if words are known to the model's vocabulary
+        known_words = [word for word in words if word in self._model.wv]
+
+        if not known_words:
+            # Return a zero-vector if all words are OOV
+            vector = [0.0] * self._model.vector_size
+        else:
+            # Infer vector from known words
+            vector = self._model.infer_vector(known_words)
+
+        return Vector(value=vector)
+
+    def transform(self, documents: List[str]) -> List[Vector]:
+        return [self.infer_vector(doc) for doc in documents]
+
+    def fit_transform(self, documents: List[str], **kwargs) -> List[Vector]:
+        self.fit(documents, **kwargs)
+        return self.transform(documents)
+
+    def save_model(self, path: str) -> None:
+        self._model.save(path)
+
+    def load_model(self, path: str) -> None:
+        """
+        Loads a Doc2Vec model from the specified path.
+        """
+        self._model = Doc2Vec.load(path)

swarmauri_embedding_doc2vec-0.6.0.dev154/swarmauri_embedding_doc2vec/__init__.py

@@ -0,0 +1,12 @@
+from .Doc2VecEmbedding import Doc2VecEmbedding
+
+__version__ = "0.6.0.dev26"
+__long_desc__ = """
+
+# Swarmauri Doc2VecEmbedding Plugin
+
+Visit us at: https://swarmauri.com
+Follow us at: https://github.com/swarmauri
+Star us at: https://github.com/swarmauri/swarmauri-sdk
+
+"""