Skip to content

Class swarmauri_vectorstore_cloudweaviate.CloudWeaviateVectorStore.CloudWeaviateVectorStore

swarmauri_vectorstore_cloudweaviate.CloudWeaviateVectorStore.CloudWeaviateVectorStore

CloudWeaviateVectorStore(**data)

Bases: VectorStoreSaveLoadMixin, VectorStoreRetrieveMixin, VectorStoreBase, VectorStoreCloudMixin

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
38
39
40
41
42
def __init__(self, **data):
    super().__init__(**data)

    # Initialize the vectorizer and Weaviate client
    self._embedder = Doc2VecEmbedding(vector_size=self.vector_size)

type class-attribute instance-attribute

type = 'CloudWeaviateVectorStore'

api_key class-attribute instance-attribute

api_key = Field(
    None, description="API key for the cloud-based store"
)

collection_name instance-attribute

collection_name

url class-attribute instance-attribute

url = Field(
    None,
    description="URL of the cloud-based store to connect to",
)

vector_size class-attribute instance-attribute

vector_size = Field(
    None,
    description="Size of the vectors used in the store",
)

client class-attribute instance-attribute

client = Field(
    None,
    description="Client object for interacting with the cloud-based store",
)

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

name class-attribute instance-attribute

name = None

resource class-attribute instance-attribute

resource = Field(default=VECTOR_STORE.value)

version class-attribute instance-attribute

version = '0.1.0'

documents class-attribute instance-attribute

documents = []

embedder property

embedder

connect

connect(**kwargs)

Initialize the Weaviate client.

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
45
46
47
48
49
50
51
52
53
54
def connect(self, **kwargs):
    """
    Initialize the Weaviate client.
    """
    if self._client is None:
        self._client = weaviate.connect_to_weaviate_cloud(
            cluster_url=self.url,
            auth_credentials=Auth.api_key(self.api_key.get_secret_value()),
            headers=kwargs.get("headers", {}),
        )

disconnect

disconnect()

Disconnects from the Qdrant cloud vector store.

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
56
57
58
59
60
61
def disconnect(self) -> None:
    """
    Disconnects from the Qdrant cloud vector store.
    """
    if self.client is not None:
        self.client = None

add_document

add_document(document)

Add a single document to the vector store.

:param document: Document to add

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
def add_document(self, document: Document) -> None:
    """
    Add a single document to the vector store.

    :param document: Document to add
    """
    try:
        collection = self._client.collections.get(self.collection_name)

        # Generate or use existing embedding
        embedding = (
            document.embedding
            or self._embedder.fit_transform([document.content])[0]
        )

        data_object = {
            "content": document.content,
            "metadata": document.metadata,
        }

        # Generate UUID for document
        uuid = (
            str(ud.uuid5(self._namespace_uuid, document.id))
            if document.id
            else generate_uuid5(data_object)
        )

        collection.data.insert(
            properties=data_object,
            vector=embedding.value,
            uuid=uuid,
        )

        print(f"Document '{document.id}' added to Weaviate.")
    except Exception as e:
        print(f"Error adding document '{document.id}': {e}")
        raise

add_documents

add_documents(documents)

Add multiple documents to the vector store.

:param documents: List of documents to add

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
101
102
103
104
105
106
107
108
109
110
111
112
113
114
def add_documents(self, documents: List[Document]) -> None:
    """
    Add multiple documents to the vector store.

    :param documents: List of documents to add
    """
    try:
        for document in documents:
            self.add_document(document)

        print(f"{len(documents)} documents added to Weaviate.")
    except Exception as e:
        print(f"Error adding documents: {e}")
        raise

get_document

get_document(id)

Retrieve a document by its ID.

:param id: Document ID :return: Document object or None if not found

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
def get_document(self, id: str) -> Union[Document, None]:
    """
    Retrieve a document by its ID.

    :param id: Document ID
    :return: Document object or None if not found
    """
    try:
        collection = self._client.collections.get(self.collection_name)

        result = collection.query.fetch_object_by_id(
            ud.uuid5(self._namespace_uuid, id)
        )

        if result:
            return Document(
                id=id,
                content=result.properties["content"],
                metadata=result.properties["metadata"],
            )
        return None
    except Exception as e:
        print(f"Error retrieving document '{id}': {e}")
        return None

get_all_documents

get_all_documents()

Retrieve all documents from the vector store.

:return: List of Document objects

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
def get_all_documents(self) -> List[Document]:
    """
    Retrieve all documents from the vector store.

    :return: List of Document objects
    """
    try:
        collection = self._client.collections.get(self.collection_name)
        # return collection
        documents = [
            Document(
                content=item.properties["content"],
                metadata=item.properties["metadata"],
                embedding=Vector(value=list(item.vector.values())[0]),
            )
            for item in collection.iterator(include_vector=True)
        ]
        return documents
    except Exception as e:
        print(f"Error retrieving all documents: {e}")
        return []

delete_document

delete_document(id)

Delete a document by its ID.

:param id: Document ID

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
163
164
165
166
167
168
169
170
171
172
173
174
175
def delete_document(self, id: str) -> None:
    """
    Delete a document by its ID.

    :param id: Document ID
    """
    try:
        collection = self._client.collections.get(self.collection_name)
        collection.data.delete_by_id(ud.uuid5(self._namespace_uuid, id))
        print(f"Document '{id}' has been deleted from Weaviate.")
    except Exception as e:
        print(f"Error deleting document '{id}': {e}")
        raise

update_document

update_document(id, document)

Update an existing document.

:param id: Document ID :param updated_document: Document object with updated data

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
177
178
179
180
181
182
183
184
185
def update_document(self, id: str, document: Document) -> None:
    """
    Update an existing document.

    :param id: Document ID
    :param updated_document: Document object with updated data
    """
    self.delete_document(id)
    self.add_document(document)

retrieve

retrieve(query, top_k=5)

Retrieve the top_k most relevant documents based on the given query.

:param query: Query string :param top_k: Number of top similar documents to retrieve :return: List of Document objects

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
def retrieve(self, query: str, top_k: int = 5) -> List[Document]:
    """
    Retrieve the top_k most relevant documents based on the given query.

    :param query: Query string
    :param top_k: Number of top similar documents to retrieve
    :return: List of Document objects
    """
    try:
        collection = self._client.collections.get(self.collection_name)
        query_vector = self._embedder.infer_vector(query)
        response = collection.query.near_vector(
            near_vector=query_vector.value,
            limit=top_k,
            return_metadata=MetadataQuery(distance=True),
        )

        documents = [
            Document(
                # id=res.id,
                content=res.properties["content"],
                metadata=res.properties["metadata"],
            )
            for res in response.objects
        ]
        return documents
    except Exception as e:
        print(f"Error retrieving documents for query '{query}': {e}")
        return []

close

close()

Close the connection to the Weaviate server.

Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
217
218
219
220
221
222
def close(self):
    """
    Close the connection to the Weaviate server.
    """
    if self._client:
        self._client.close()

model_dump_json

model_dump_json(*args, **kwargs)
Source code in swarmauri_vectorstore_cloudweaviate/CloudWeaviateVectorStore.py
224
225
226
227
228
229
def model_dump_json(self, *args, **kwargs) -> str:
    # Call the disconnect method before serialization
    self.disconnect()

    # Now proceed with the usual JSON serialization
    return super().model_dump_json(*args, **kwargs)

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

clear_documents

clear_documents()

Deletes all documents from the vector store

Source code in swarmauri_base/vector_stores/VectorStoreBase.py
94
95
96
97
98
99
def clear_documents(self) -> None:
    """
    Deletes all documents from the vector store

    """
    self.documents = []

document_count

document_count()
Source code in swarmauri_base/vector_stores/VectorStoreBase.py
101
102
def document_count(self):
    return len(self.documents)

document_dumps

document_dumps()

Placeholder

Source code in swarmauri_base/vector_stores/VectorStoreBase.py
104
105
106
107
108
def document_dumps(self) -> str:
    """
    Placeholder
    """
    return json.dumps([each.to_dict() for each in self.documents])

document_dump

document_dump(file_path)

Placeholder

Source code in swarmauri_base/vector_stores/VectorStoreBase.py
110
111
112
113
114
115
116
117
118
119
120
def document_dump(self, file_path: str) -> None:
    """
    Placeholder
    """
    with open(file_path, "w", encoding="utf-8") as f:
        json.dump(
            [each.to_dict() for each in self.documents],
            f,
            ensure_ascii=False,
            indent=4,
        )

document_loads

document_loads(json_data)

Placeholder

Source code in swarmauri_base/vector_stores/VectorStoreBase.py
122
123
124
125
126
127
128
def document_loads(self, json_data: str) -> None:
    """
    Placeholder
    """
    self.documents = [
        globals()[each["type"]].from_dict(each) for each in json.loads(json_data)
    ]

document_load

document_load(file_path)

Placeholder

Source code in swarmauri_base/vector_stores/VectorStoreBase.py
130
131
132
133
134
135
136
137
def document_load(self, file_path: str) -> None:
    """
    Placeholder
    """
    with open(file_path, "r", encoding="utf-8"):
        self.documents = [
            globals()[each["type"]].from_dict(each) for each in json.load(file_path)
        ]

save_store

save_store(directory_path)

Saves both the vectorizer's model and the documents.

Source code in swarmauri_base/vector_stores/VectorStoreSaveLoadMixin.py
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
def save_store(self, directory_path: str) -> None:
    """
    Saves both the vectorizer's model and the documents.
    """
    # Ensure the directory exists
    if not os.path.exists(directory_path):
        os.makedirs(directory_path)

    # Save the vectorizer model
    model_path = os.path.join(directory_path, "embedding_model")
    self._vectorizer.save_model(model_path)

    # Save documents
    documents_path = os.path.join(directory_path, "documents.json")
    with open(documents_path, "w", encoding="utf-8") as f:
        json.dump(
            [each.to_dict() for each in self.documents],
            f,
            ensure_ascii=False,
            indent=4,
        )

load_store

load_store(directory_path)

Loads both the vectorizer's model and the documents.

Source code in swarmauri_base/vector_stores/VectorStoreSaveLoadMixin.py
38
39
40
41
42
43
44
45
46
47
48
49
def load_store(self, directory_path: str) -> None:
    """
    Loads both the vectorizer's model and the documents.
    """
    # Load the vectorizer model
    model_path = os.path.join(directory_path, "embedding_model")
    self.vectorizer.load_model(model_path)

    # Load documents
    documents_path = os.path.join(directory_path, "documents.json")
    with open(documents_path, "r", encoding="utf-8") as f:
        self.documents = [self._load_document(each) for each in json.load(f)]

save_parts

save_parts(directory_path, chunk_size=10485760)

Splits the file into parts if it's too large and saves those parts individually.

Source code in swarmauri_base/vector_stores/VectorStoreSaveLoadMixin.py
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
def save_parts(self, directory_path: str, chunk_size: int = 10485760) -> None:
    """
    Splits the file into parts if it's too large and saves those parts individually.
    """
    file_number = 1
    model_path = os.path.join(directory_path, "embedding_model")
    parts_directory = os.path.join(directory_path, "parts")

    if not os.path.exists(parts_directory):
        os.makedirs(parts_directory)

    with open(f"{model_path}/model.safetensors", "rb") as f:
        chunk = f.read(chunk_size)
        while chunk:
            with open(
                f"{parts_directory}/model.safetensors.part{file_number:03}", "wb"
            ) as chunk_file:
                chunk_file.write(chunk)
            file_number += 1
            chunk = f.read(chunk_size)

    # Split the documents into parts and save them
    os.path.join(directory_path, "documents")

    self._split_json_file(directory_path, chunk_size=chunk_size)

load_parts

load_parts(directory_path, file_pattern='*.part*')

Combines file parts from a directory back into a single file and loads it.

Source code in swarmauri_base/vector_stores/VectorStoreSaveLoadMixin.py
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
def load_parts(self, directory_path: str, file_pattern: str = "*.part*") -> None:
    """
    Combines file parts from a directory back into a single file and loads it.
    """
    model_path = os.path.join(directory_path, "embedding_model")
    parts_directory = os.path.join(directory_path, "parts")
    output_file_path = os.path.join(model_path, "model.safetensors")

    parts = sorted(glob.glob(os.path.join(parts_directory, file_pattern)))
    with open(output_file_path, "wb") as output_file:
        for part in parts:
            with open(part, "rb") as file_part:
                output_file.write(file_part.read())

    # Load the combined_model now
    model_path = os.path.join(directory_path, "embedding_model")
    self._vectorizer.load_model(model_path)

    # Load document files
    self._load_documents(directory_path)