swarmauri_vectorstore_doc2vec 0.6.0.dev154__tar.gz

swarmauri_vectorstore_doc2vec-0.6.0.dev154/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_vectorstore_doc2vec
+Version: 0.6.0.dev154
+Summary: A Doc2Vec based Vector Store and 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: swarmauri_base (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_embedding_doc2vec (>=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_vectorstore_doc2vec-0.6.0.dev154/README.md

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

swarmauri_vectorstore_doc2vec-0.6.0.dev154/pyproject.toml

@@ -0,0 +1,55 @@
+[tool.poetry]
+name = "swarmauri_vectorstore_doc2vec"
+version = "0.6.0.dev154"
+description = "A Doc2Vec based Vector Store and 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"}
+swarmauri_embedding_doc2vec = {version = "^0.6.0.dev154"}
+
+[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.vector_stores"]
+Doc2VecVectorStore = "swarmauri_vectorstore_doc2vec:Doc2VecVectorStore"

swarmauri_vectorstore_doc2vec-0.6.0.dev154/swarmauri_vectorstore_doc2vec/Doc2VecVectorStore.py

@@ -0,0 +1,78 @@
+from typing import List, Union, Literal
+
+from swarmauri_standard.documents.Document import Document
+from swarmauri_standard.distances.CosineDistance import CosineDistance
+from swarmauri_base.vector_stores.VectorStoreBase import VectorStoreBase
+from swarmauri_base.vector_stores.VectorStoreRetrieveMixin import (
+    VectorStoreRetrieveMixin,
+)
+from swarmauri_base.vector_stores.VectorStoreSaveLoadMixin import (
+    VectorStoreSaveLoadMixin,
+)
+from swarmauri_embedding_doc2vec.Doc2VecEmbedding import (
+    Doc2VecEmbedding,
+)
+from swarmauri_core.ComponentBase import ComponentBase
+
+
+@ComponentBase.register_type(VectorStoreBase, "Doc2VecVectorStore")
+class Doc2VecVectorStore(
+    VectorStoreSaveLoadMixin, VectorStoreRetrieveMixin, VectorStoreBase
+):
+    type: Literal["Doc2VecVectorStore"] = "Doc2VecVectorStore"
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self._embedder = Doc2VecEmbedding()
+        self._distance = CosineDistance()
+
+    def add_document(self, document: Document) -> None:
+        self._embedder.fit([document.content])
+        self.documents.append(document)
+
+    def add_documents(self, documents: List[Document]) -> None:
+        self.documents.extend(documents)
+        self._embedder.fit([doc.content for doc in documents])
+
+    def retrieve(self, query: str, top_k: int = 5) -> List[Document]:
+        query_vector = self._embedder.infer_vector(query)
+
+        # If the query vector is all-zero, return an empty list
+        if all(v == 0.0 for v in query_vector.value):
+            print("Query contains only OOV words.")
+            return []
+
+        # Transform the stored documents into vectors
+        document_vectors = self._embedder.transform(
+            [doc.content for doc in self.documents]
+        )
+
+        # Calculate cosine distances between the query vector and document vectors
+        distances = self._distance.distances(query_vector, document_vectors)
+
+        # Get the indices of the top_k closest documents
+        top_k_indices = sorted(range(len(distances)), key=lambda i: distances[i])[
+            :top_k
+        ]
+
+        return [self.documents[i] for i in top_k_indices]
+
+    def get_document(self, id: str) -> Union[Document, None]:
+        for document in self.documents:
+            if document.id == id:
+                return document
+        return None
+
+    def get_all_documents(self) -> List[Document]:
+        return self.documents
+
+    def delete_document(self, id: str) -> None:
+        self.documents = [doc for doc in self.documents if doc.id != id]
+        self._embedder.fit([doc.content for doc in self.documents])
+
+    def update_document(self, id: str, updated_document: Document) -> None:
+        for i, document in enumerate(self.documents):
+            if document.id == id:
+                self.documents[i] = updated_document
+                break
+        self._embedder.fit([doc.content for doc in self.documents])

swarmauri_vectorstore_doc2vec-0.6.0.dev154/swarmauri_vectorstore_doc2vec/__init__.py

@@ -0,0 +1,12 @@
+from .Doc2VecVectorStore import Doc2VecVectorStore
+
+__version__ = "0.6.0.dev26"
+__long_desc__ = """
+
+# Swarmauri Doc2Vec VectorStore Plugin
+
+Visit us at: https://swarmauri.com
+Follow us at: https://github.com/swarmauri
+Star us at: https://github.com/swarmauri/swarmauri-sdk
+
+"""