[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

src/vdf_io/export_vdf/weaviate_export.py

@@ -27,14 +27,18 @@ def make_parser(cls, subparsers):
 
         parser_weaviate.add_argument("--url", type=str, help="URL of Weaviate instance")
         parser_weaviate.add_argument("--api_key", type=str, help="Weaviate API key")
-        parser_weaviate.add_argument("--openai_api_key", type=str, help="Openai API key")
+        parser_weaviate.add_argument(
+            "--openai_api_key", type=str, help="Openai API key"
+        )
         parser_weaviate.add_arguments(
-            "--batch_size", type=int, help="batch size for fetching",
-            default=1000
+            "--batch_size", type=int, help="batch size for fetching", default=1000
         )
         parser_weaviate.add_argument(
-            "--connection-type", type=str, choices=["local", "cloud"], default="cloud",
-            help="Type of connection to Weaviate (local or cloud)"
+            "--connection-type",
+            type=str,
+            choices=["local", "cloud"],
+            default="cloud",
+            help="Type of connection to Weaviate (local or cloud)",
         )
         parser_weaviate.add_argument(
             "--classes", type=str, help="Classes to export (comma-separated)"
@@ -52,7 +56,7 @@ def export_vdb(cls, args):
             args,
             "connection_type",
             "Enter 'local' or 'cloud' for connection types: ",
-            choices=['local', 'cloud'],
+            choices=["local", "cloud"],
         )
         set_arg_from_password(
             args,
@@ -83,7 +87,7 @@ def __init__(self, args):
             self.client = weaviate.connect_to_wcs(
                 cluster_url=self.args["url"],
                 auth_credentials=weaviate.auth.AuthApiKey(self.args["api_key"]),
-                headers={'X-OpenAI-Api-key': self.args["openai_api_key"]}
+                headers={"X-OpenAI-Api-key": self.args["openai_api_key"]}
                 if self.args["openai_api_key"]
                 else None,
                 skip_init_checks=True,
@@ -128,8 +132,11 @@ def get_data(self):
                 metadata = {}
                 # Need a better way
                 for obj in objects:
-                    metadata[obj.id] = {attr: getattr(obj, attr) for attr in dir(obj) if not attr.startswith("__")}
-
+                    metadata[obj.id] = {
+                        attr: getattr(obj, attr)
+                        for attr in dir(obj)
+                        if not attr.startswith("__")
+                    }
 
                 # Save vectors and metadata to Parquet file
                 num_vectors_exported += self.save_vectors_to_parquet(
@@ -143,7 +150,7 @@ def get_data(self):
                     vectors_directory,
                     total=total_vector_count,
                     num_vectors_exported=num_vectors_exported,
-                    dim=300, # Not sure of the dimensions
+                    dim=300,  # Not sure of the dimensions
                     distance="Cosine",
                 )
             ]

src/vdf_io/import_vdf/astradb_import.py

@@ -7,7 +7,6 @@
 from astrapy.db import AstraDB
 from cassandra.cluster import Cluster
 from cassandra.auth import PlainTextAuthProvider
-from qdrant_client.http.models import Distance
 
 from vdf_io.constants import INT_MAX
 from vdf_io.names import DBNames

src/vdf_io/import_vdf/lancedb_import.py

@@ -117,7 +117,9 @@ def upsert_data(self):
                     for col in df.columns:
                         if col not in [field.name for field in table.schema]:
                             col_type = df[col].dtype
-                            tqdm.write(f"Adding column {col} of type {col_type} to {new_index_name}")
+                            tqdm.write(
+                                f"Adding column {col} of type {col_type} to {new_index_name}"
+                            )
                             table.add_columns(
                                 {
                                     col: get_default_value(col_type),

src/vdf_io/import_vdf/weaviate_import.py

@@ -1,6 +1,5 @@
 import os
 import weaviate
-import json
 from tqdm import tqdm
 from vdf_io.import_vdf.vdf_import_cls import ImportVDB
 from vdf_io.names import DBNames
@@ -58,7 +57,7 @@ def __init__(self, args):
             self.client = weaviate.connect_to_wcs(
                 cluster_url=self.args["url"],
                 auth_credentials=weaviate.auth.AuthApiKey(self.args["api_key"]),
-                headers={'X-OpenAI-Api-key': self.args["openai_api_key"]}
+                headers={"X-OpenAI-Api-key": self.args["openai_api_key"]}
                 if self.args["openai_api_key"]
                 else None,
                 skip_init_checks=True,
@@ -69,13 +68,17 @@ def upsert_data(self):
         total_imported_count = 0
 
         # Iterate over the indexes and import the data
-        for index_name, index_meta in tqdm(self.vdf_meta["indexes"].items(), desc="Importing indexes"):
+        for index_name, index_meta in tqdm(
+            self.vdf_meta["indexes"].items(), desc="Importing indexes"
+        ):
             tqdm.write(f"Importing data for index '{index_name}'")
             for namespace_meta in index_meta:
                 self.set_dims(namespace_meta, index_name)
 
             # Create or get the index
-            index_name = self.create_new_name(index_name, self.client.collections.list_all().keys())
+            index_name = self.create_new_name(
+                index_name, self.client.collections.list_all().keys()
+            )
             index = self.client.collections.get(index_name)
 
             # Load data from the Parquet files
@@ -136,4 +139,4 @@ def upsert_data(self):
         #             continue
 
         # tqdm.write(f"Data import completed successfully. Imported {total_imported_count} vectors")
-        # self.args["imported_count"] = total_imported_count
+        # self.args["imported_count"] = total_imported_count