linting fix

activeloopai · May 15, 2023 · bfdcd17 · bfdcd17
1 parent b3947e6
commit bfdcd17
Show file tree

Hide file tree

Showing 6 changed files with 13 additions and 11 deletions.
diff --git a/deeplake/client/client.py b/deeplake/client/client.py
@@ -1,6 +1,6 @@
 import deeplake
 import requests
-from typing import Optional, List
+from typing import Any, Optional, List, Tuple
 from deeplake.util.exceptions import (
     AgreementNotAcceptedError,
     AuthorizationException,
@@ -490,7 +490,9 @@ def connect_dataset_entry(
 
         return response["generated_id"]
 
-    def remote_query(self, org_id: str, ds_name: str, query_string: str) -> List[int]:
+    def remote_query(
+        self, org_id: str, ds_name: str, query_string: str
+    ) -> Tuple[Any, Any]:
         """Queries a remote dataset.
 
         Args:
@@ -510,7 +512,7 @@ def remote_query(self, org_id: str, ds_name: str, query_string: str) -> List[int
 
         indicies = response["indices"]
         if len(indicies) == 0:
-            return []
+            return [], []
 
         scores = response.get("score")
 

diff --git a/deeplake/core/vectorstore/deeplake_vectorstore.py b/deeplake/core/vectorstore/deeplake_vectorstore.py
@@ -7,14 +7,14 @@
 from deeplake.core.vectorstore.vector_search.ingestion import ingest_data
 
 try:
-    from indra import api
+    from indra import api  # type: ignore
 
     _INDRA_INSTALLED = True
 except Exception:  # pragma: no cover
     _INDRA_INSTALLED = False  # pragma: no cover
 
 import logging
-from typing import Optional, Any, Iterable, List, Dict, Union
+from typing import Optional, Any, Iterable, List, Dict, Union, Callable
 
 import numpy as np
 
@@ -29,7 +29,7 @@ def __init__(
         self,
         dataset_path: str = DEFAULT_DEEPLAKE_PATH,
         token: Optional[str] = None,
-        embedding_function: Optional[callable] = None,
+        embedding_function: Optional[Callable] = None,
         read_only: Optional[bool] = False,
         ingestion_batch_size: int = 1024,
         num_workers: int = 0,

diff --git a/deeplake/core/vectorstore/test_deeplake_vectorstore.py b/deeplake/core/vectorstore/test_deeplake_vectorstore.py
@@ -18,7 +18,7 @@
 
 @requires_libdeeplake
 @pytest.mark.parametrize("distance_metric", ["L1", "L2", "COS", "MAX", "DOT"])
-def test_search(distance_metric, hub_cloud_dev_token):
+def test_search(distance_metric):
     k = 4
     query_embedding = np.random.randint(0, 255, (1, embedding_dim))
 
@@ -48,7 +48,7 @@ def test_search(distance_metric, hub_cloud_dev_token):
     vector_store = DeepLakeVectorStore(
         dataset_path="hub://activeloop-test/deeplake_vectorstore-test1",
         read_only=True,
-        token=hub_cloud_dev_token,
+        # token=hub_cloud_dev_token,
     )
     db_engine_view, db_engine_indices, db_engine_scores = vector_store.search(
         embedding=query_embedding, exec_option="db_engine"

diff --git a/deeplake/core/vectorstore/vector_search/indra/indra_vector_search.py b/deeplake/core/vectorstore/vector_search/indra/indra_vector_search.py
@@ -7,7 +7,7 @@
 
 
 def vector_search(
-    query_embedding: Union[List[float], np.ndarray[Any, Any]],
+    query_embedding: np.ndarray[Any, Any],
     distance_metric: str,
     deeplake_dataset: DeepLakeDataset,
     k: int,

diff --git a/deeplake/core/vectorstore/vector_search/ingestion/data_ingestion.py b/deeplake/core/vectorstore/vector_search/ingestion/data_ingestion.py
@@ -14,7 +14,7 @@ def __init__(
         self,
         elements: List[Dict[str, Any]],
         dataset: DeepLakeDataset,
-        embedding_function: Callable,
+        embedding_function: Optional[Callable],
         ingestion_batch_size: int,
         num_workers: int,
         retry_attempt: int,

diff --git a/deeplake/core/vectorstore/vector_search/ingestion/ingest_data.py b/deeplake/core/vectorstore/vector_search/ingestion/ingest_data.py
@@ -21,7 +21,7 @@ def run_data_ingestion(
         elements (List[Dict[str, Any]]): List of dictionaries. Each dictionary contains mapping of
             names of 4 tensors (i.e. "embedding", "metadata", "ids", "text") to their corresponding values.
         dataset (DeepLakeDataset): deeplake dataset object.
-        embedding_function (Callable): function used to convert query into an embedding.
+        embedding_function (Optional[Callable]): function used to convert query into an embedding.
         ingestion_batch_size (int): The batch size to use during ingestion.
         num_workers (int): The number of workers to use for ingesting data in parallel.
     """