fix

core/tests/tidb-client-quickstart.ipynb

@@ -78,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 39,
    "id": "4995a54f311c4b1c",
    "metadata": {},
    "outputs": [],
@@ -100,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 40,
    "id": "bdddb9f0a005b74d",
    "metadata": {},
    "outputs": [],
@@ -113,11 +113,13 @@
     "# Define your embedding model.\n",
     "text_embed = EmbeddingFunction(\"openai/text-embedding-3-small\")\n",
     "\n",
-    "class Chunk(TiDBModel, table=True):\n",
+    "class Chunk(TiDBModel, table=True):    \n",
     "    __tablename__ = \"chunks\"\n",
+    "    __table_args__ = {'extend_existing': True}\n",
+    "\n",
     "    id: int = Field(primary_key=True)\n",
     "    text: str = Field()\n",
-    "    text_vec: Optional[Any] = text_embed.VectorField(source_field=\"text\")\n",
+    "    text_vec: Optional[Any] = text_embed.VectorField(source_field=\"text\")   # 👈 Define the vector field.\n",
     "    user_id: int = Field()\n",
     "\n",
     "table = db.create_table(schema=Chunk)"
@@ -128,27 +130,24 @@
    "id": "3eab5d6eaaaaa868",
    "metadata": {},
    "source": [
-    "### Insert Data"
+    "### Insert Data\n",
+    "\n",
+    "🔢 Auto embedding: when you insert new data, the SDK automatically embeds the corpus for you."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 46,
    "id": "baec9a5ae06231be",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Chunk(user_id=2, id=2, text='A quick brown dog runs in the park', text_vec=array([-0.0412815 , -0.00934362,  0.01239674, ..., -0.00587278,\n",
-       "        -0.00735941,  0.01383422], dtype=float32)),\n",
-       " Chunk(user_id=2, id=3, text='The lazy fox sleeps under the tree', text_vec=array([-0.01610469, -0.00269681, -0.01787939, ..., -0.00041015,\n",
-       "         0.01320426,  0.02987844], dtype=float32)),\n",
-       " Chunk(user_id=3, id=4, text='A dog and a fox play in the park', text_vec=array([-2.7123539e-02, -4.4581316e-02, -3.8457386e-02, ...,\n",
-       "        -1.1360981e-03,  9.5597192e-05,  3.4092940e-02], dtype=float32))]"
+       "4"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -159,7 +158,8 @@
     "    Chunk(id=2, text=\"A quick brown dog runs in the park\", user_id=2),\n",
     "    Chunk(id=3, text=\"The lazy fox sleeps under the tree\", user_id=2),\n",
     "    Chunk(id=4, text=\"A dog and a fox play in the park\", user_id=3)\n",
-    "])"
+    "])\n",
+    "table.rows()"
    ]
   },
   {
@@ -172,29 +172,36 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 53,
    "id": "3c4313022f06bd3e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[(4, 'A dog and a fox play in the park', 0.7308190419242949),\n",
-       " (2, 'A quick brown dog runs in the park', 0.665493189763966),\n",
-       " (1, 'The quick brown fox jumps over the lazy dog', 0.6157064668170177)]"
+       "[('A quick brown dog runs in the park', 0.665493189763966),\n",
+       " ('The lazy fox sleeps under the tree', 0.554631888866523)]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 53,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chunks = table.search(\"A quick fox in the park\").limit(3).to_pydantic()\n",
-    "[\n",
-    "    (c.id,  c.text, c.score)\n",
-    "    for c in chunks\n",
-    "]"
+    "from autoflow.storage.tidb import DistanceMetric\n",
+    "\n",
+    "chunks = (\n",
+    "    table.search(\"A quick fox in the park\")         # 👈 The query will be embedding automatically.\n",
+    "        # .distance_metric(metric=DistanceMetric.COSINE)\n",
+    "        # .num_candidate(20)\n",
+    "        .filter({\n",
+    "            \"user_id\": 2\n",
+    "        })\n",
+    "        .limit(2)\n",
+    "        .to_pydantic()\n",
+    ")\n",
+    "[(c.text, c.score) for c in chunks]"
    ]
   },
   {
@@ -221,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 49,
    "id": "ace02b45",
    "metadata": {},
    "outputs": [
@@ -231,7 +238,7 @@
        "[(1, 'The quick brown fox jumps over the lazy dog', 1)]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -249,39 +256,35 @@
    "id": "af9c3428",
    "metadata": {},
    "source": [
-    "### Truncate table"
+    "### Truncate table\n",
+    "\n",
+    "Clear all data in the table:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 45,
    "id": "cceb0bf0",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "table.truncate()"
+    "table.truncate()\n",
+    "table.rows()"
    ]
   }
  ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
+ "metadata": {},
  "nbformat": 5,
  "nbformat_minor": 9
 }