From 8fb2be1f8bf19be4628159a86ff1c146eff30094 Mon Sep 17 00:00:00 2001
From: Um Changyong <changyong.um@sfa.co.kr>
Date: Mon, 16 Dec 2024 11:52:00 +0900
Subject: [PATCH] fix: reformatting...

---
 autorag/nodes/retrieval/base.py     |  5 ++++-
 autorag/nodes/retrieval/vectordb.py |  2 +-
 autorag/vectordb/chroma.py          |  4 +++-
 autorag/vectordb/milvus.py          |  2 +-
 autorag/vectordb/pinecone.py        |  4 ++--
 autorag/vectordb/qdrant.py          | 16 ++++++++++++----
 6 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/autorag/nodes/retrieval/base.py b/autorag/nodes/retrieval/base.py
index 9da0e6f4a..16fb8335d 100644
--- a/autorag/nodes/retrieval/base.py
+++ b/autorag/nodes/retrieval/base.py
@@ -102,7 +102,10 @@ def cast_queries(queries: Union[str, List[str]]) -> List[str]:
 
 
 def evenly_distribute_passages(
-	ids: List[List[str]], scores: List[List[float]], contents: [List[List[str]]], top_k: int
+	ids: List[List[str]],
+	scores: List[List[float]],
+	contents: [List[List[str]]],
+	top_k: int,
 ) -> Tuple[List[str], List[float], List[str]]:
 	assert len(ids) == len(scores), "ids and scores must have same length."
 	query_cnt = len(ids)
diff --git a/autorag/nodes/retrieval/vectordb.py b/autorag/nodes/retrieval/vectordb.py
index a02bca4bf..fcaa1cb77 100644
--- a/autorag/nodes/retrieval/vectordb.py
+++ b/autorag/nodes/retrieval/vectordb.py
@@ -27,7 +27,7 @@
 	flatten_apply,
 	result_to_dataframe,
 	pop_params,
-	fetch_contents,
+	# fetch_contents,
 	empty_cuda_cache,
 	convert_inputs_to_list,
 	make_batch,
diff --git a/autorag/vectordb/chroma.py b/autorag/vectordb/chroma.py
index 37a73f21c..c7375fef2 100644
--- a/autorag/vectordb/chroma.py
+++ b/autorag/vectordb/chroma.py
@@ -68,7 +68,9 @@ async def add(self, ids: List[str], texts: List[str]):
 		texts = self.truncated_inputs(texts)
 		text_embeddings = await self.embedding.aget_text_embedding_batch(texts)
 		if isinstance(self.collection, AsyncCollection):
-			await self.collection.add(ids=ids, embeddings=text_embeddings, documents=texts)
+			await self.collection.add(
+				ids=ids, embeddings=text_embeddings, documents=texts
+			)
 		else:
 			self.collection.add(ids=ids, embeddings=text_embeddings, documents=texts)
 
diff --git a/autorag/vectordb/milvus.py b/autorag/vectordb/milvus.py
index 4be88d3c7..bd2e7638c 100644
--- a/autorag/vectordb/milvus.py
+++ b/autorag/vectordb/milvus.py
@@ -68,7 +68,7 @@ def __init__(
 			field = FieldSchema(
 				name="vector", dtype=DataType.FLOAT_VECTOR, dim=dimension
 			)
-   			content = FieldSchema(
+			content = FieldSchema(
 				name="content", dtype=DataType.VARCHAR, max_length=65535
 			)
 			schema = CollectionSchema(fields=[pk, field, content])
diff --git a/autorag/vectordb/pinecone.py b/autorag/vectordb/pinecone.py
index cf78cc9f6..28e16304e 100644
--- a/autorag/vectordb/pinecone.py
+++ b/autorag/vectordb/pinecone.py
@@ -62,8 +62,8 @@ async def add(self, ids: List[str], texts: List[str]):
 
 		metadatas = [{} for _ in texts]
 		for metadata, text in zip(metadatas, texts):
-            metadata[self.text_key] = text
-            
+			metadata[self.text_key] = text
+
 		vector_tuples = list(zip(ids, text_embeddings, metadatas))
 		batch_vectors = make_batch(vector_tuples, self.ingest_batch)
 
diff --git a/autorag/vectordb/qdrant.py b/autorag/vectordb/qdrant.py
index a18f171a4..680bb810c 100644
--- a/autorag/vectordb/qdrant.py
+++ b/autorag/vectordb/qdrant.py
@@ -86,10 +86,13 @@ async def add(self, ids: List[str], texts: List[str]):
 
 		metadatas = [{} for _ in texts]
 		for metadata, text in zip(metadatas, texts):
-            metadata[self.text_key] = text
+			metadata[self.text_key] = text
 
 		points = list(
-			map(lambda x: PointStruct(id=x[0], vector=x[1], payload=x[2]), zip(ids, text_embeddings, metadatas))
+			map(
+				lambda x: PointStruct(id=x[0], vector=x[1], payload=x[2]),
+				zip(ids, text_embeddings, metadatas),
+			)
 		)
 
 		self.client.upload_points(
@@ -133,7 +136,9 @@ async def query(
 
 		search_queries = list(
 			map(
-				lambda x: SearchRequest(vector=x, limit=top_k, with_vector=True, with_payload=True),
+				lambda x: SearchRequest(
+					vector=x, limit=top_k, with_vector=True, with_payload=True
+				),
 				query_embeddings,
 			)
 		)
@@ -145,7 +150,10 @@ async def query(
 		# Extract IDs and distances
 		ids = [[str(hit.id) for hit in result] for result in search_result]
 		scores = [[hit.score for hit in result] for result in search_result]
-		contents = [[hit.payload.get(self.text_key) for hit in result] for result in search_result]
+		contents = [
+			[hit.payload.get(self.text_key) for hit in result]
+			for result in search_result
+		]
 
 		return ids, scores, contents