[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.5.6
+  rev: v0.14.2
   hooks:
     # Run the linter.
     - id: ruff

src/vdf_io/import_vdf/astradb_import.py

@@ -124,7 +124,7 @@ def upsert_data(self, via_cql=False):
                 data_path = namespace_meta["data_path"]
                 final_data_path = self.get_final_data_path(data_path)
                 new_index_name = index_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )
@@ -162,7 +162,7 @@ def upsert_data(self, via_cql=False):
 
                     self.session.execute(
                         f"CREATE TABLE IF NOT EXISTS {self.args['keyspace']}.{new_index_name}"
-                        f" (id text PRIMARY KEY, \"$vector\" vector<float,{namespace_meta['dimensions']}>)"
+                        f' (id text PRIMARY KEY, "$vector" vector<float,{namespace_meta["dimensions"]}>)'
                     )
                 parquet_files = self.get_parquet_files(final_data_path)
                 vectors = {}
@@ -208,7 +208,7 @@ def flush_to_db(self, vectors, metadata, collection, via_cql, parallel=True):
             keys = list(set(vectors.keys()).union(set(metadata.keys())))
             for id in keys:
                 self.session.execute(
-                    f"INSERT INTO {self.args['keyspace']}.{collection.name} (id, \"$vector\", {', '.join(metadata[id].keys())}) "
+                    f'INSERT INTO {self.args["keyspace"]}.{collection.name} (id, "$vector", {", ".join(metadata[id].keys())}) '
                     f"VALUES ('{id}', {vectors[id]}, {', '.join([str(v) for v in metadata[id].values()])})"
                 )
             return len(vectors)
@@ -248,12 +248,15 @@ def flush_batch_to_db(collection, keys, vectors, metadata):
             for i in range(0, total_points, BATCH_SIZE)
         ]
 
-        with concurrent.futures.ThreadPoolExecutor(
-            max_workers=num_parallel_threads
-        ) as executor, tqdm(
-            total=total_points,
-            desc=f"Flushing to DB in batches of {BATCH_SIZE} in {num_parallel_threads} threads",
-        ) as pbar:
+        with (
+            concurrent.futures.ThreadPoolExecutor(
+                max_workers=num_parallel_threads
+            ) as executor,
+            tqdm(
+                total=total_points,
+                desc=f"Flushing to DB in batches of {BATCH_SIZE} in {num_parallel_threads} threads",
+            ) as pbar,
+        ):
             future_to_batch = {
                 executor.submit(flush_batch_to_db, collection, *batch): batch
                 for batch in batches

src/vdf_io/import_vdf/chroma_import.py

@@ -123,7 +123,7 @@ def upsert_data(self):
                 parquet_files = self.get_parquet_files(final_data_path)
 
                 new_index_name = index_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )

src/vdf_io/import_vdf/kdbai_import.py

@@ -99,7 +99,7 @@ def upsert_data(self):
                 data_path = namespace_meta["data_path"]
                 final_data_path = self.get_final_data_path(data_path)
                 index_name = index_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )

src/vdf_io/import_vdf/lancedb_import.py

@@ -89,7 +89,7 @@ def upsert_data(self):
                 parquet_files = self.get_parquet_files(final_data_path)
 
                 new_index_name = index_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )

src/vdf_io/import_vdf/milvus_import.py

@@ -82,7 +82,7 @@ def upsert_data(self):
                 self.set_dims(namespace_meta, collection_name)
                 data_path = namespace_meta["data_path"]
                 index_name = collection_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )

src/vdf_io/import_vdf/qdrant_import.py

@@ -313,12 +313,15 @@ def get_nested_config(config, keys, default=None):
                         total_points = len(points)
 
                         num_parallel_threads = self.args.get("parallel", 5) or 5
-                        with concurrent.futures.ThreadPoolExecutor(
-                            max_workers=num_parallel_threads
-                        ) as executor, tqdm(
-                            total=total_points,
-                            desc=f"Uploading points in batches of {BATCH_SIZE} in {num_parallel_threads} threads",
-                        ) as pbar:
+                        with (
+                            concurrent.futures.ThreadPoolExecutor(
+                                max_workers=num_parallel_threads
+                            ) as executor,
+                            tqdm(
+                                total=total_points,
+                                desc=f"Uploading points in batches of {BATCH_SIZE} in {num_parallel_threads} threads",
+                            ) as pbar,
+                        ):
                             # Create a future to batch mapping to update progress bar correctly after each batch completion
                             future_to_batch = {
                                 executor.submit(

src/vdf_io/import_vdf/turbopuffer_import.py

@@ -73,7 +73,7 @@ def upsert_data(self):
                 parquet_files = self.get_parquet_files(final_data_path)
 
                 new_index_name = index_name + (
-                    f'_{namespace_meta["namespace"]}'
+                    f"_{namespace_meta['namespace']}"
                     if namespace_meta["namespace"]
                     else ""
                 )

src/vdf_io/marqo_vespa_util.py

@@ -85,7 +85,7 @@ def get_all_documents(
                 [f"{key}={value}" for key, value in query_params.items() if value]
             )
             url = f"{self.document_url}/document/v1/{schema}/{schema}/docid"
-            url = f'{url.strip("?")}?{query_string}'
+            url = f"{url.strip('?')}?{query_string}"
             print(f"{url=}")
             resp = self.http_client.get(url)
         except httpx.HTTPError as e: