Merge pull request #266 from aurelio-labs/anup/splitter-fix

fix: video splitter -> type error
aurelio-labs · May 2, 2024 · 4de9294 · 4de9294
2 parents 29762f0 + dafd97d
commit 4de9294
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 23 deletions.
diff --git a/docs/00-introduction.ipynb b/docs/00-introduction.ipynb
@@ -63,9 +63,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "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",
@@ -91,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -118,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -146,14 +155,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 4,
    "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 12:38:34 INFO semantic_router.utils.logger local\u001b[0m\n"
      ]
     }
    ],
@@ -172,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -181,7 +190,7 @@
        "RouteChoice(name='politics', function_call=None, similarity_score=None)"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -192,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -201,7 +210,7 @@
        "RouteChoice(name='chitchat', function_call=None, similarity_score=None)"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -219,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -228,7 +237,7 @@
        "RouteChoice(name=None, function_call=None, similarity_score=None)"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -246,7 +255,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -256,7 +265,7 @@
        " RouteChoice(name='chitchat', function_call=None, similarity_score=0.8356239688161808)]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -267,7 +276,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -276,7 +285,7 @@
        "[]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -309,7 +318,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

diff --git a/semantic_router/encoders/openai.py b/semantic_router/encoders/openai.py
@@ -80,9 +80,7 @@ def __call__(self, docs: List[str], truncate: bool = True) -> List[List[float]]:
         if truncate:
             # check if any document exceeds token limit and truncate if so
             for i in range(len(docs)):
-                logger.info(f"Document {i+1} length: {len(docs[i])}")
                 docs[i] = self._truncate(docs[i])
-                logger.info(f"Document {i+1} trunc length: {len(docs[i])}")
 
         # Exponential backoff
         for j in range(1, 7):

diff --git 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
 
 
@@ -52,15 +51,15 @@ def __str__(self):
 
 
 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
     metadata: Optional[dict] = None
 
     @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):