fdsa

semsearch.py

@@ -200,58 +200,6 @@ logger.debug(f"### webpageDocNames: {webpageDocNames}")
 # Create database webpage and chunks collections.
 #wpCollection = createWebpageCollection()
 #wpChunkCollection = createChunksCollection()
-
-logger.info("#### createChunksCollection() entered.")
-if client.collections.exists("Chunks"):
-    client.collections.delete("Chunks")
-
-class_obj = {
-    "class": "Chunks",
-    "description": "Collection for document chunks.",
-    "vectorizer": "text2vec-transformers",
-    "moduleConfig": {
-        "text2vec-transformers": {
-            "vectorizeClassName": True
-        }
-    },
-    "vectorIndexType": "hnsw",  
-    "vectorIndexConfig": {
-        "distance": "cosine",
-    },
-    "properties": [
-        {
-            "name": "chunk",
-            "dataType": ["text"],
-            "description": "Single webpage chunk.",
-            "vectorizer": "text2vec-transformers",
-            "moduleConfig": {
-                "text2vec-transformers": {
-                  "vectorizePropertyName": False,
-                  "skip": False,
-                  "tokenization": "lowercase"
-                }
-            }
-        },
-        {
-            "name": "chunk_index",
-            "dataType": ["int"]
-        },
-        {
-            "name": "webpage",
-            "dataType": ["Documents"],
-            "description": "Webpage content chunks.",
-        
-            "invertedIndexConfig": {
-                "bm25": {
-                    "b": 0.75,
-                    "k1": 1.2
-                }
-            }  
-        }
-    ]
-}
-wpChunkCollection = client.collections.create_from_dict(class_obj)
-
 logger.info("#### createWebpageCollection() entered.")
 if client.collections.exists("Documents"):
     client.collections.delete("Documents")
@@ -304,6 +252,57 @@ class_obj = {
 }
 wpCollection = client.collections.create_from_dict(class_obj)
 
+logger.info("#### createChunksCollection() entered.")
+if client.collections.exists("Chunks"):
+    client.collections.delete("Chunks")
+
+class_obj = {
+    "class": "Chunks",
+    "description": "Collection for document chunks.",
+    "vectorizer": "text2vec-transformers",
+    "moduleConfig": {
+        "text2vec-transformers": {
+            "vectorizeClassName": True
+        }
+    },
+    "vectorIndexType": "hnsw",  
+    "vectorIndexConfig": {
+        "distance": "cosine",
+    },
+    "properties": [
+        {
+            "name": "chunk",
+            "dataType": ["text"],
+            "description": "Single webpage chunk.",
+            "vectorizer": "text2vec-transformers",
+            "moduleConfig": {
+                "text2vec-transformers": {
+                  "vectorizePropertyName": False,
+                  "skip": False,
+                  "tokenization": "lowercase"
+                }
+            }
+        },
+        {
+            "name": "chunk_index",
+            "dataType": ["int"]
+        },
+        {
+            "name": "webpage",
+            "dataType": ["Documents"],
+            "description": "Webpage content chunks.",
+        
+            "invertedIndexConfig": {
+                "bm25": {
+                    "b": 0.75,
+                    "k1": 1.2
+                }
+            }  
+        }
+    ]
+}
+wpChunkCollection = client.collections.create_from_dict(class_obj)
+
 
 ###########################################################
 # Create document and chunks objects in the database.