ELASTIC_PY_VEC_TYPES: List[Any] = [list, tuple, np.ndarray, AbstractTensor]

if TYPE_CHECKING:

import tensorflow as tf # type: ignore

import torch

torch = import_library('torch', raise_error=False)

tf = import_library('tensorflow', raise_error=False)

if torch is not None:

ELASTIC_PY_VEC_TYPES.append(torch.Tensor)

es_config: Dict[str, Any] = field(default_factory=dict)

index_settings: Dict[str, Any] = field(default_factory=dict)

index_mappings: Dict[str, Any] = field(default_factory=dict)

default_column_config: Dict[Any, Dict[str, Any]] = field(default_factory=dict)

def __post_init__(self):

self.default_column_config = {

return config

###############################################

# Implementation of abstract methods #

###############################################

num_candidates: Optional[int] = None,

) -> Dict[str, Any]:

if not num_candidates:

'num_candidates'

]

body = {

hosts: Union[str, List[str], None] = 'http://localhost:9200' # type: ignore

@dataclass

class RuntimeConfig(ElasticDocIndex.RuntimeConfig):

"""Dataclass that contains all "dynamic" configurations of ElasticDocIndex."""

###############################################

# Implementation of abstract methods #

"""Dataclass that contains all "static" configurations of HnswDocumentIndex."""

work_dir: str = '.'

default_column_config: Dict[Type, Dict[str, Any]] = field(

default_factory=lambda: {

np.ndarray: {

}

)

###############################################

# Implementation of abstract methods #

###############################################

class DBConfig(BaseDocIndex.DBConfig):

"""Dataclass that contains all "static" configurations of InMemoryExactNNIndex."""

default_column_config: Dict[Type, Dict[str, Any]] = field(

default_factory=lambda: defaultdict(

dict,

)

)

def index(self, docs: Union[BaseDoc, Sequence[BaseDoc]], **kwargs):

"""index Documents into the index.

optimizers_config: Optional[types.OptimizersConfigDiff] = None

wal_config: Optional[types.WalConfigDiff] = None

quantization_config: Optional[types.QuantizationConfig] = None

default_column_config: Dict[Type, Dict[str, Any]] = field(

default_factory=lambda: {

'id': {}, # type: ignore[dict-item]

}

)

def python_type_to_db_type(self, python_type: Type) -> Any:

"""Map python type to database type.

scopes: List[str] = field(default_factory=lambda: ["offline_access"])

auth_api_key: Optional[str] = None

embedded_options: Optional[EmbeddedOptions] = None

default_column_config: Dict[Any, Dict[str, Any]] = field(

default_factory=lambda: {

np.ndarray: {},

}

)

batch_config: Dict[str, Any] = field(

default_factory=lambda: DEFAULT_BATCH_CONFIG

)

class DBConfig(BaseDocIndex.DBConfig):

class RuntimeConfig(BaseDocIndex.RuntimeConfig):

!!! note

These are configurations that are tied to the database (or library) running in the background, such as `host`, `port`, etc.

Here you should put everything that the user cannot or should not change after initialization.

!!! note

This is a dictionary that, for each possible column type in your database, defines a default configuration for that column type.

This will automatically be passed to a `_ColumnInfo` whenever a user does not manually specify a configuration for that column.

It is probably best to see this in action, so you should check out the `HnswDocumentIndex` implementation.

After you've done the basic setup above, you can jump into the good stuff: implementing the actual indexing, searching, and deleting.

In this case, the `db_type` of `my_num` will be `'float64'` and the `db_type` of `my_text` will be `'varchar'`.

Additional information regarding the `col_type`, such as `max_len` for `varchar` will be stored in the `_ColumnsInfo.config`.

This commonly includes:

- default batch size for batching operations

- default consistency level for various database operations

- ...

For every backend, you can get the full list of configurations and their defaults:

print(runtime_config)

As you can see, `HnswDocumentIndex.RuntimeConfig` is a dataclass that contains only one configuration:

- `tens` has a dimensionality of `100`, can take up to `12` elements, and uses the `cosine` similarity space

- `tens_two` has a dimensionality of `10`, and uses the `ip` similarity space, and an `M` hyperparameter of 4

For an explanation of the configurations that are tweaked in this example, see the `HnswDocumentIndex` [documentation](index_hnswlib.md).

| `index_name` | Elasticsearch index name, the name of Elasticsearch index object | None. Data will be stored in an index named after the Document type used as schema. |

| `index_settings` | Other [index settings](https://www.elastic.co/guide/en/elasticsearch/reference/8.6/index-modules.html#index-modules-settings) in a Dict for creating the index | dict |

| `index_mappings` | Other [index mappings](https://www.elastic.co/guide/en/elasticsearch/reference/8.6/mapping.html) in a Dict for creating the index | dict |

You can pass any of the above as keyword arguments to the `__init__()` method or pass an entire configuration object.

See [here](docindex.md#configuration-options#customize-configurations) for more information.

`default_column_config` is the default configurations for every column type. Since there are many column types in Elasticsearch, you can also consider changing the column config when defining the schema.

doc_index = ElasticDocIndex[SimpleDoc]()

You can pass the above as keyword arguments to the `configure()` method or pass an entire configuration object.

See [here](docindex.md#configuration-options#customize-configurations) for more information.