Merge pull request #31 from qdrant/fix-defaults

Consistent Default to v1.5

docs/Getting Started.ipynb

@@ -38,18 +38,11 @@
    "id": "b61c6552",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "torch.Size([384])\n"
+      "(384,)\n"
      ]
     }
    ],
@@ -64,9 +57,9 @@
     "    \"This is an example document.\",\n",
     "    \"fastembed is supported by and maintained by Qdrant.\",\n",
     "]\n",
-    "# Initialize the DefaultEmbedding class with the desired parameters\n",
-    "embedding_model = DefaultEmbedding(model_name=\"BAAI/bge-small-en\", max_length=512)\n",
-    "embeddings: List[np.ndarray] = embedding_model.embed(documents)\n",
+    "# Initialize the DefaultEmbedding class\n",
+    "embedding_model = DefaultEmbedding()\n",
+    "embeddings: List[np.ndarray] = list(embedding_model.embed(documents))\n",
     "print(embeddings[0].shape)"
    ]
   },
@@ -97,7 +90,7 @@
    "source": [
     "from typing import List\n",
     "import numpy as np\n",
-    "from fastembed.embedding import DefaultEmbedding as Embedding"
+    "from fastembed.embedding import DefaultEmbedding"
    ]
   },
   {
@@ -171,20 +164,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "8013eee9",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "embeddings: List[np.ndarray] = embedding_model.embed(documents)"
+    "embeddings: List[np.ndarray] = list(embedding_model.embed(documents))"
    ]
   },
   {
@@ -197,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "0d8c8e08",
    "metadata": {},
    "outputs": [
@@ -205,7 +190,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "torch.Size([384])\n"
+      "(384,)\n"
      ]
     }
    ],

fastembed/embedding.py

@@ -403,7 +403,7 @@ class FlagEmbedding(Embedding):
 
     def __init__(
             self,
-            model_name: str = "BAAI/bge-small-en",
+            model_name: str = "BAAI/bge-small-en-v1.5",
             max_length: int = 512,
             cache_dir: str = None,
             threads: int = None,