docs: update Milvus configuration examples (#1030)

Co-authored-by: Um Changyong <[email protected]> Co-authored-by: Jeffrey (Dongkyu) Kim <[email protected]>
Marker-Inc-Korea · Dec 3, 2024 · fc61882 · fc61882
1 parent e4cd040
commit fc61882
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 1 deletion.
diff --git a/autorag/vectordb/milvus.py b/autorag/vectordb/milvus.py
@@ -24,7 +24,7 @@ def __init__(
 		embedding_model: str,
 		collection_name: str,
 		embedding_batch: int = 100,
-		similarity_metric: str = "l2",
+		similarity_metric: str = "cosine",
 		index_type: str = "IVF_FLAT",
 		uri: str = "http://localhost:19530",
 		db_name: str = "",

diff --git a/docs/source/integration/vectordb/milvus.md b/docs/source/integration/vectordb/milvus.md
@@ -15,6 +15,10 @@ To use the Milvus vector database, you need to configure it in your YAML configu
   token: ${MILVUS_TOKEN}
   embedding_batch: 50
   similarity_metric: cosine
+  index_type: IVF_FLAT
+  params:
+    nlist: 16384
+
 ```
 
 Here is a simple example of a YAML configuration file that uses the Milvus vector database and the OpenAI:
@@ -29,6 +33,9 @@ vectordb:
     token: ${MILVUS_TOKEN}
     embedding_batch: 50
     similarity_metric: cosine
+    index_type: IVF_FLAT
+    params:
+      nlist: 16384
 node_lines:
 - node_line_name: retrieve_node_line  # Arbitrary node line name
   nodes: