diff --git a/docs/00-introduction.ipynb b/docs/00-introduction.ipynb
index 7ce5f4e490aa0f7c5145e5fd3c8030aaf8d18c71..d03a09ffe670d9c35bb6cc67a1b7fbe276ed1d2b 100644
--- a/docs/00-introduction.ipynb
+++ b/docs/00-introduction.ipynb
@@ -65,7 +65,16 @@
"cell_type": "code",
"execution_count": 3,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "d:\\Program_Installation\\anaconda\\envs\\rag\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+ " from .autonotebook import tqdm as notebook_tqdm\n"
+ ]
+ }
+ ],
"source": [
"from semantic_router import Route\n",
"\n",
@@ -146,14 +155,36 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "\u001b[32m2024-04-19 18:34:06 INFO semantic_router.utils.logger local\u001b[0m\n"
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger local\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 1 length: 34\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 1 trunc length: 34\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 2 length: 51\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 2 trunc length: 51\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 3 length: 33\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 3 trunc length: 33\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 4 length: 33\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 4 trunc length: 33\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 5 length: 38\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 5 trunc length: 38\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 6 length: 27\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 6 trunc length: 27\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 7 length: 24\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 7 trunc length: 24\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 8 length: 21\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 8 trunc length: 21\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 9 length: 20\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 9 trunc length: 20\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 10 length: 25\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 10 trunc length: 25\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 11 length: 22\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 11 trunc length: 22\u001b[0m\n"
]
}
],
@@ -172,16 +203,24 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 7,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[32m2024-05-02 12:09:35 INFO semantic_router.utils.logger Document 1 length: 24\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:35 INFO semantic_router.utils.logger Document 1 trunc length: 24\u001b[0m\n"
+ ]
+ },
{
"data": {
"text/plain": [
"RouteChoice(name='politics', function_call=None, similarity_score=None)"
]
},
- "execution_count": 8,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -192,16 +231,24 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 8,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[32m2024-05-02 12:09:37 INFO semantic_router.utils.logger Document 1 length: 24\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:37 INFO semantic_router.utils.logger Document 1 trunc length: 24\u001b[0m\n"
+ ]
+ },
{
"data": {
"text/plain": [
"RouteChoice(name='chitchat', function_call=None, similarity_score=None)"
]
},
- "execution_count": 9,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -219,16 +266,24 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 9,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[32m2024-05-02 12:09:38 INFO semantic_router.utils.logger Document 1 length: 40\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:38 INFO semantic_router.utils.logger Document 1 trunc length: 40\u001b[0m\n"
+ ]
+ },
{
"data": {
"text/plain": [
"RouteChoice(name=None, function_call=None, similarity_score=None)"
]
},
- "execution_count": 10,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -246,9 +301,17 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 10,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[32m2024-05-02 12:09:40 INFO semantic_router.utils.logger Document 1 length: 35\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:40 INFO semantic_router.utils.logger Document 1 trunc length: 35\u001b[0m\n"
+ ]
+ },
{
"data": {
"text/plain": [
@@ -256,7 +319,7 @@
" RouteChoice(name='chitchat', function_call=None, similarity_score=0.8356239688161808)]"
]
},
- "execution_count": 11,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -267,16 +330,24 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 11,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[32m2024-05-02 12:09:42 INFO semantic_router.utils.logger Document 1 length: 40\u001b[0m\n",
+ "\u001b[32m2024-05-02 12:09:42 INFO semantic_router.utils.logger Document 1 trunc length: 40\u001b[0m\n"
+ ]
+ },
{
"data": {
"text/plain": [
"[]"
]
},
- "execution_count": 12,
+ "execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -309,7 +380,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.5"
+ "version": "3.11.8"
}
},
"nbformat": 4,
diff --git a/semantic_router/schema.py b/semantic_router/schema.py
index 60f61536e08840e2c023fd12867cc960a14d3608..20b6ef825872ca329a90fc5230a49e877987f6d9 100644
--- a/semantic_router/schema.py
+++ b/semantic_router/schema.py
@@ -1,6 +1,5 @@
from enum import Enum
-from typing import List, Optional
-
+from typing import List, Optional, Union, Any
from pydantic.v1 import BaseModel
@@ -52,7 +51,7 @@ class Message(BaseModel):
class DocumentSplit(BaseModel):
- docs: List[str]
+ docs: List[Union[str, Any]]
is_triggered: bool = False
triggered_score: Optional[float] = None
token_count: Optional[int] = None
@@ -60,7 +59,7 @@ class DocumentSplit(BaseModel):
@property
def content(self) -> str:
- return " ".join(self.docs)
+ return " ".join([doc if isinstance(doc, str) else "" for doc in self.docs])
class Metric(Enum):