swarmauri_vectorstore_doc2vec 0.6.0.dev154__py3-none-any.whl

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/__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
+
+"""

swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,6 @@
+swarmauri_vectorstore_doc2vec/__init__.py,sha256=lMwpN8881a1Zumf8QCYZIR1CcCQKDECD_PwZqTDzFGk,291
+swarmauri_vectorstore_doc2vec/Doc2VecVectorStore.py,sha256=gfGe5axKHOJOyk3rOaRl4Omvs5Cg-prqVs05bOipjLo,3014
+swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/entry_points.txt,sha256=3e0jR1vegYY6F7fGR-wa12zbIZVOna1VbTqWbMFci-4,95
+swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/METADATA,sha256=45EPB4jyrwinWK656olAc1Ds7Oh1RptFlvtqktDcA7Q,833
+swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/RECORD,,

swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.0.1
+Root-Is-Purelib: true
+Tag: py3-none-any

swarmauri_vectorstore_doc2vec-0.6.0.dev154.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[swarmauri.vector_stores]
+Doc2VecVectorStore=swarmauri_vectorstore_doc2vec:Doc2VecVectorStore
+