Enhance semantic router loading (#187)

This PR introduces some serialization methods for the `SemanticRouter`
so that it can be loaded to and from file or dict.

Author: tylerhutcherson

docs/user_guide/router.yaml

@@ -0,0 +1,35 @@
+name: topic-router
+routes:
+- name: technology
+  references:
+  - what are the latest advancements in AI?
+  - tell me about the newest gadgets
+  - what's trending in tech?
+  metadata:
+    category: tech
+    priority: '1'
+- name: sports
+  references:
+  - who won the game last night?
+  - tell me about the upcoming sports events
+  - what's the latest in the world of sports?
+  - sports
+  - basketball and football
+  metadata:
+    category: sports
+    priority: '2'
+- name: entertainment
+  references:
+  - what are the top movies right now?
+  - who won the best actor award?
+  - what's new in the entertainment industry?
+  metadata:
+    category: entertainment
+    priority: '3'
+vectorizer:
+  type: hf
+  model: sentence-transformers/all-mpnet-base-v2
+routing_config:
+  distance_threshold: 1.0
+  max_k: 3
+  aggregation_method: min

docs/user_guide/semantic_router_08.ipynb

@@ -171,7 +171,7 @@
     {
      "data": {
       "text/plain": [
-       "RouteMatch(name='technology', distance=0.119614183903)"
+       "RouteMatch(name='technology', distance=0.119614243507)"
       ]
      },
      "execution_count": 5,
@@ -244,9 +244,9 @@
     {
      "data": {
       "text/plain": [
-       "[RouteMatch(name='sports', distance=0.758580672741),\n",
-       " RouteMatch(name='entertainment', distance=0.812423805396),\n",
-       " RouteMatch(name='technology', distance=0.884235262871)]"
+       "[RouteMatch(name='sports', distance=0.758580708504),\n",
+       " RouteMatch(name='entertainment', distance=0.812423825264),\n",
+       " RouteMatch(name='technology', distance=0.88423516353)]"
       ]
      },
      "execution_count": 8,
@@ -268,9 +268,9 @@
     {
      "data": {
       "text/plain": [
-       "[RouteMatch(name='sports', distance=0.663254022598),\n",
-       " RouteMatch(name='entertainment', distance=0.712985336781),\n",
-       " RouteMatch(name='technology', distance=0.832674443722)]"
+       "[RouteMatch(name='sports', distance=0.663253903389),\n",
+       " RouteMatch(name='entertainment', distance=0.712985396385),\n",
+       " RouteMatch(name='technology', distance=0.832674384117)]"
       ]
      },
      "execution_count": 9,
@@ -321,9 +321,9 @@
     {
      "data": {
       "text/plain": [
-       "[RouteMatch(name='sports', distance=0.663254022598),\n",
-       " RouteMatch(name='entertainment', distance=0.712985336781),\n",
-       " RouteMatch(name='technology', distance=0.832674443722)]"
+       "[RouteMatch(name='sports', distance=0.663253903389),\n",
+       " RouteMatch(name='entertainment', distance=0.712985396385),\n",
+       " RouteMatch(name='technology', distance=0.832674384117)]"
       ]
      },
      "execution_count": 11,
@@ -340,13 +340,109 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Clean up the router"
+    "## Router serialization"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 12,
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'topic-router',\n",
+       " 'routes': [{'name': 'technology',\n",
+       "   'references': ['what are the latest advancements in AI?',\n",
+       "    'tell me about the newest gadgets',\n",
+       "    \"what's trending in tech?\"],\n",
+       "   'metadata': {'category': 'tech', 'priority': '1'}},\n",
+       "  {'name': 'sports',\n",
+       "   'references': ['who won the game last night?',\n",
+       "    'tell me about the upcoming sports events',\n",
+       "    \"what's the latest in the world of sports?\",\n",
+       "    'sports',\n",
+       "    'basketball and football'],\n",
+       "   'metadata': {'category': 'sports', 'priority': '2'}},\n",
+       "  {'name': 'entertainment',\n",
+       "   'references': ['what are the top movies right now?',\n",
+       "    'who won the best actor award?',\n",
+       "    \"what's new in the entertainment industry?\"],\n",
+       "   'metadata': {'category': 'entertainment', 'priority': '3'}}],\n",
+       " 'vectorizer': {'type': 'hf',\n",
+       "  'model': 'sentence-transformers/all-mpnet-base-v2'},\n",
+       " 'routing_config': {'distance_threshold': 1.0,\n",
+       "  'max_k': 3,\n",
+       "  'aggregation_method': 'min'}}"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "router.to_dict()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "15:16:28 redisvl.index.index INFO   Index already exists, not overwriting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "router2 = SemanticRouter.from_dict(router.to_dict(), redis_url=\"redis://localhost:6379\")\n",
+    "\n",
+    "assert router2 == router"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "router.to_yaml(\"router.yaml\", overwrite=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "15:17:42 redisvl.index.index INFO   Index already exists, not overwriting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "router3 = SemanticRouter.from_yaml(\"router.yaml\", redis_url=\"redis://localhost:6379\")\n",
+    "\n",
+    "assert router3 == router2 == router"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Clean up the router"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Use clear to flush all routes from the index\n",
@@ -355,7 +451,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [