docarray · JoanFM · Sep 8, 2022 · Sep 6, 2022 · Sep 6, 2022 · Sep 6, 2022
diff --git a/docarray/array/storage/annlite/backend.py b/docarray/array/storage/annlite/backend.py
@@ -27,7 +27,7 @@ class AnnliteConfig:
     ef_construction: Optional[int] = None
     ef_search: Optional[int] = None
     max_connection: Optional[int] = None
-    columns: Optional[List[Tuple[str, str]]] = None
+    columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]] = None
 
 
 class BackendMixin(BaseBackendMixin):
@@ -53,11 +53,8 @@ def _map_embedding(self, embedding: 'ArrayType') -> 'ArrayType':
 
     def _normalize_columns(self, columns):
         columns = super()._normalize_columns(columns)
-        for i in range(len(columns)):
-            columns[i] = (
-                columns[i][0],
-                self._map_type(columns[i][1]),
-            )
+        for key in columns.keys():
+            columns[key] = self._map_type(columns[key])
         return columns
 
     def _ensure_unique_config(

diff --git a/docarray/array/storage/base/backend.py b/docarray/array/storage/base/backend.py
@@ -1,7 +1,8 @@
 from abc import ABC, abstractmethod
+import warnings
 from collections import namedtuple
 from dataclasses import is_dataclass, asdict
-from typing import Dict, Optional, TYPE_CHECKING
+from typing import Dict, Optional, TYPE_CHECKING, Union, List, Tuple
 
 if TYPE_CHECKING:
     from docarray.typing import DocumentArraySourceType, ArrayType
@@ -77,7 +78,14 @@ def _map_embedding(self, embedding: 'ArrayType') -> 'ArrayType':
     def _map_type(self, col_type: str) -> str:
         return self.TYPE_MAP[col_type].type
 
-    def _normalize_columns(self, columns):
+    def _normalize_columns(
+        self, columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]]
+    ) -> Dict[str, str]:
         if columns is None:
-            return []
+            return {}
+        if isinstance(columns, list):
+            warnings.warn(
+                'Using "columns" as a List of Tuples will be deprecated soon. Please provide a Dictionary.'
+            )
+            columns = {col_desc[0]: col_desc[1] for col_desc in columns}
         return columns
diff --git a/docarray/array/storage/elastic/backend.py b/docarray/array/storage/elastic/backend.py
@@ -44,7 +44,7 @@ class ElasticConfig:
     batch_size: int = 64
     ef_construction: Optional[int] = None
     m: Optional[int] = None
-    columns: Optional[List[Tuple[str, str]]] = None
+    columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]] = None
 
 
 _banned_indexname_chars = ['[', ' ', '"', '*', '\\', '<', '|', ',', '>', '/', '?', ']']
@@ -150,7 +150,7 @@ def _build_schema_from_elastic_config(self, elastic_config):
                     'index': True,
                 }
 
-        for col, coltype in self._config.columns:
+        for col, coltype in self._config.columns.items():
             da_schema['mappings']['properties'][col] = {
                 'type': self._map_type(coltype),
                 'index': True,

diff --git a/docarray/array/storage/elastic/getsetdel.py b/docarray/array/storage/elastic/getsetdel.py
@@ -12,7 +12,9 @@ class GetSetDelMixin(BaseGetSetDelMixin):
     MAX_ES_RETURNED_DOCS = 10000
 
     def _document_to_elastic(self, doc: 'Document') -> Dict:
-        extra_columns = {col: doc.tags.get(col) for col, _ in self._config.columns}
+        extra_columns = {
+            col: doc.tags.get(col) for col, _ in self._config.columns.items()
+        }
         request = {
             '_op_type': 'index',
             '_id': doc.id,

diff --git a/docarray/array/storage/qdrant/backend.py b/docarray/array/storage/qdrant/backend.py
@@ -42,7 +42,7 @@ class QdrantConfig:
     ef_construct: Optional[int] = None
     full_scan_threshold: Optional[int] = None
     m: Optional[int] = None
-    columns: Optional[List[Tuple[str, str]]] = None
+    columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]] = None
 
 
 class BackendMixin(BaseBackendMixin):

diff --git a/docarray/array/storage/qdrant/getsetdel.py b/docarray/array/storage/qdrant/getsetdel.py
@@ -65,7 +65,9 @@ def _qdrant_to_document(self, qdrant_record: dict) -> 'Document':
         )
 
     def _document_to_qdrant(self, doc: 'Document') -> 'PointStruct':
-        extra_columns = {col: doc.tags.get(col) for col, _ in self._config.columns}
+        extra_columns = {
+            col: doc.tags.get(col) for col, _ in self._config.columns.items()
+        }
 
         return PointStruct(
             id=self._map_id(doc.id),

diff --git a/docarray/array/storage/redis/backend.py b/docarray/array/storage/redis/backend.py
@@ -31,7 +31,7 @@ class RedisConfig:
     ef_runtime: int = field(default=10)
     block_size: int = field(default=1048576)
     initial_cap: Optional[int] = None
-    columns: Optional[List[Tuple[str, str]]] = None
+    columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]] = None
 
 
 class BackendMixin(BaseBackendMixin):
@@ -146,7 +146,7 @@ def _build_schema_from_redis_config(self):
             index_param['INITIAL_CAP'] = self._config.initial_cap
         schema = [VectorField('embedding', self._config.method, index_param)]
 
-        for col, coltype in self._config.columns:
+        for col, coltype in self._config.columns.items():
             schema.append(self._map_column(col, coltype))
 
         return schema

diff --git a/docarray/array/storage/redis/getsetdel.py b/docarray/array/storage/redis/getsetdel.py
@@ -90,7 +90,7 @@ def _del_doc_by_id(self, _id: str):
     def _document_to_redis(self, doc: 'Document') -> Dict:
         extra_columns = {}
 
-        for col, _ in self._config.columns:
+        for col, _ in self._config.columns.items():
             tag = doc.tags.get(col)
             if tag is not None:
                 extra_columns[col] = int(tag) if isinstance(tag, bool) else tag

diff --git a/docarray/array/storage/sqlite/backend.py b/docarray/array/storage/sqlite/backend.py
@@ -1,16 +1,8 @@
 import sqlite3
 import warnings
-from dataclasses import dataclass, field, asdict
+from dataclasses import dataclass, field
 from tempfile import NamedTemporaryFile
-from typing import (
-    Iterable,
-    Dict,
-    Optional,
-    TYPE_CHECKING,
-    Union,
-    List,
-    Tuple,
-)
+from typing import Iterable, Dict, Optional, TYPE_CHECKING, Union
 
 from docarray.array.storage.sqlite.helper import initialize_table
 from docarray.array.storage.base.backend import BaseBackendMixin

diff --git a/docarray/array/storage/weaviate/backend.py b/docarray/array/storage/weaviate/backend.py
@@ -45,7 +45,7 @@ class WeaviateConfig:
     flat_search_cutoff: Optional[int] = None
     cleanup_interval_seconds: Optional[int] = None
     skip: Optional[bool] = None
-    columns: Optional[List[Tuple[str, str]]] = None
+    columns: Optional[Union[List[Tuple[str, str]], Dict[str, str]]] = None
     distance: Optional[str] = None
 
 
@@ -215,7 +215,7 @@ def _get_schema_by_name(self, cls_name: str) -> Dict:
                 },
             ]
         }
-        for col, coltype in self._config.columns:
+        for col, coltype in self._config.columns.items():
             new_property = {
                 'dataType': [self._map_type(coltype)],
                 'name': col,
@@ -352,10 +352,9 @@ def _doc2weaviate_create_payload(self, value: 'Document'):
         :param value: document to create a payload for
         :return: the payload dictionary
         """
-        columns_dict = {key: val for [key, val] in self._config.columns}
         extra_columns = {
-            col: self._map_column(value.tags.get(col), columns_dict[col])
-            for col, _ in self._config.columns
+            col: self._map_column(value.tags.get(col), col_type)
+            for col, col_type in self._config.columns.items()
         }
 
         return dict(

diff --git a/docs/advanced/document-store/annlite.md b/docs/advanced/document-store/annlite.md
@@ -72,7 +72,7 @@ da = DocumentArray(
     storage='annlite',
     config={
         'n_dim': n_dim,
-        'columns': [('price', 'float')],
+        'columns': {'price': 'float'},
     },
 )
 
@@ -125,7 +125,7 @@ metric = 'Euclidean'
 
 da = DocumentArray(
     storage='annlite',
-    config={'n_dim': n_dim, 'columns': [('price', 'float')], 'metric': metric},
+    config={'n_dim': n_dim, 'columns': {'price': 'float'}, 'metric': metric},
 )
 
 with da:

diff --git a/docs/advanced/document-store/elasticsearch.md b/docs/advanced/document-store/elasticsearch.md
@@ -132,7 +132,7 @@ n_dim = 3
 
 da = DocumentArray(
     storage='elasticsearch',
-    config={'n_dim': 3, 'columns': [('price', 'int')], 'distance': 'l2_norm'},
+    config={'n_dim': 3, 'columns': {'price': 'int'}, 'distance': 'l2_norm'},
 )
 
 with da:
@@ -172,7 +172,7 @@ n_dim = 3
 
 da = DocumentArray(
     storage='elasticsearch',
-    config={'n_dim': n_dim, 'columns': [('price', 'int')], 'distance': 'l2_norm'},
+    config={'n_dim': n_dim, 'columns': {'price': 'int'}, 'distance': 'l2_norm'},
 )
 
 with da:
@@ -248,7 +248,7 @@ da = DocumentArray(
     storage='elasticsearch',
     config={
         'n_dim': n_dim,
-        'columns': [('price', 'float')],
+        'columns': {'price': 'float'},
     },
 )
 

diff --git a/docs/advanced/document-store/index.md b/docs/advanced/document-store/index.md
@@ -244,7 +244,7 @@ metric = 'Euclidean'
 
 da = DocumentArray(
     storage='annlite',
-    config={'n_dim': n_dim, 'columns': [('price', 'float')], 'metric': metric},
+    config={'n_dim': n_dim, 'columns': {'price': 'float'}, 'metric': metric},
 )
 
 with da:
@@ -276,7 +276,7 @@ metric = 'Euclidean'
 
 da = DocumentArray(
     storage='annlite',
-    config={'n_dim': n_dim, 'columns': [('price', 'float')], 'metric': metric},
+    config={'n_dim': n_dim, 'columns': {'price': 'float'}, 'metric': metric},
 )
 
 with da:
@@ -317,7 +317,7 @@ metric = 'Euclidean'
 
 da = DocumentArray(
     storage='annlite',
-    config={'n_dim': n_dim, 'columns': [('price', 'float')], 'metric': metric},
+    config={'n_dim': n_dim, 'columns': {'price': 'float'}, 'metric': metric},
 )
 
 with da:

diff --git a/docs/advanced/document-store/qdrant.md b/docs/advanced/document-store/qdrant.md
@@ -155,7 +155,7 @@ distance = 'euclidean'
 
 da = DocumentArray(
     storage='qdrant',
-    config={'n_dim': n_dim, 'columns': [('price', 'float')], 'distance': distance},
+    config={'n_dim': n_dim, 'columns': {'price': 'float'}, 'distance': distance},
 )
 
 print(f'\nDocumentArray distance: {distance}')

diff --git a/docs/advanced/document-store/redis.md b/docs/advanced/document-store/redis.md
@@ -111,7 +111,7 @@ da2.summary()
 │   ef_runtime        10          │
 │   block_size        1048576     │
 │   initial_cap       None        │
-│   columns           []          │
+│   columns           {}          │
 │                                 │
 ╰─────────────────────────────────╯
 ```
@@ -146,7 +146,7 @@ da = DocumentArray(
     storage='redis',
     config={
         'n_dim': n_dim,
-        'columns': [('price', 'int'), ('color', 'str')],
+        'columns': {'price': 'int', 'color': 'str'},
         'flush': True,
         'distance': 'L2',
     },

diff --git a/docs/advanced/document-store/weaviate.md b/docs/advanced/document-store/weaviate.md
@@ -191,7 +191,7 @@ da = DocumentArray(
     storage='weaviate',
     config={
         'n_dim': n_dim,
-        'columns': [('price', 'float')],
+        'columns': {'price': 'float'},
     },
 )
 
@@ -243,7 +243,7 @@ n_dim = 3
 
 da = DocumentArray(
     storage='weaviate',
-    config={'n_dim': n_dim, 'columns': [('price', 'int')], 'distance': 'l2-squared'},
+    config={'n_dim': n_dim, 'columns': {'price': 'int'}, 'distance': 'l2-squared'},
 )
 
 with da:
@@ -317,7 +317,7 @@ da = DocumentArray(
     storage='weaviate',
     config={
         'n_dim': n_dim,
-        'columns': [('price', 'float')],
+        'columns': {'price': 'float'},
         'distance': 'l2-squared',
         "name": "Persisted",
         "host": "localhost",

diff --git a/docs/fundamentals/documentarray/subindex.md b/docs/fundamentals/documentarray/subindex.md
@@ -71,7 +71,7 @@ da = DocumentArray(
 │   ef_construction    None               │
 │   ef_search          None               │
 │   max_connection     None               │
-│   columns            []                 │
+│   columns            {}                 │
 │                                         │
 ╰─────────────────────────────────────────╯
 ```
@@ -129,7 +129,7 @@ da = DocumentArray(
 │   ef_construction    None               │
 │   ef_search          None               │
 │   max_connection     None               │
-│   columns            []                 │
+│   columns            {}                 │
 │                                         │
 ╰─────────────────────────────────────────╯
 ```
@@ -231,4 +231,4 @@ top_level_matches = da[top_image_matches[:, 'parent_id']]
 top_image_matches = da.find(query=np.random.rand(512), on='@c')
 top_level_matches = da[top_image_matches[:, 'parent_id']]
 ```
-````
+````
diff --git a/setup.py b/setup.py
@@ -70,7 +70,7 @@
             'qdrant-client~=0.7.3',
         ],
         'annlite': [
-            'annlite>=0.3.2',
+            'annlite>=0.3.10',
         ],
         'weaviate': [
             'weaviate-client~=3.3.0',
@@ -105,7 +105,7 @@
             'jupyterlab',
             'transformers>=4.16.2',
             'weaviate-client~=3.3.0',
-            'annlite>=0.3.2',
+            'annlite>=0.3.10',
             'elasticsearch>=8.2.0',
             'redis>=4.3.0',
             'jina',