diff --git a/docs/examples/unstructured-element-splitter.ipynb b/docs/examples/unstructured-element-splitter.ipynb
index c9561b7538e986fd5ce6811fcf3639d9b919e9c0..c9d67c0da0881314194651f9f768b7cbeea1d10b 100644
--- a/docs/examples/unstructured-element-splitter.ipynb
+++ b/docs/examples/unstructured-element-splitter.ipynb
@@ -103,9 +103,10 @@
"source": [
"from unstructured.documents.elements import Element\n",
"from colorama import Fore, Style\n",
+ "from typing import List\n",
"\n",
"\n",
- "def group_elements_by_title(elements: list[Element]) -> dict:\n",
+ "def group_elements_by_title(elements: List[Element]) -> dict:\n",
" grouped_elements = {}\n",
" current_title = \"Untitled\" # Default title for initial text without a title\n",
"\n",
diff --git a/semantic_router/encoders/tfidf.py b/semantic_router/encoders/tfidf.py
index 77069da2b89dafbbd05a9a95bc4d10bbee15a449..dbbe56f69110c4c9a162eddc711adbfc6bd8cfd7 100644
--- a/semantic_router/encoders/tfidf.py
+++ b/semantic_router/encoders/tfidf.py
@@ -1,6 +1,6 @@
import string
from collections import Counter
-from typing import Dict
+from typing import Dict, List
import numpy as np
from numpy import ndarray
@@ -20,7 +20,7 @@ class TfidfEncoder(BaseEncoder):
self.word_index = {}
self.idf = np.array([])
- def __call__(self, docs: list[str]) -> list[list[float]]:
+ def __call__(self, docs: List[str]) -> List[List[float]]:
if len(self.word_index) == 0 or self.idf.size == 0:
raise ValueError("Vectorizer is not initialized.")
if len(docs) == 0:
@@ -31,7 +31,7 @@ class TfidfEncoder(BaseEncoder):
tfidf = tf * self.idf
return tfidf.tolist()
- def fit(self, routes: list[Route]):
+ def fit(self, routes: List[Route]):
docs = []
for route in routes:
for doc in route.utterances:
@@ -39,7 +39,7 @@ class TfidfEncoder(BaseEncoder):
self.word_index = self._build_word_index(docs)
self.idf = self._compute_idf(docs)
- def _build_word_index(self, docs: list[str]) -> dict:
+ def _build_word_index(self, docs: List[str]) -> dict:
words = set()
for doc in docs:
for word in doc.split():
@@ -47,7 +47,7 @@ class TfidfEncoder(BaseEncoder):
word_index = {word: i for i, word in enumerate(words)}
return word_index
- def _compute_tf(self, docs: list[str]) -> np.ndarray:
+ def _compute_tf(self, docs: List[str]) -> np.ndarray:
if len(self.word_index) == 0:
raise ValueError("Word index is not initialized.")
tf = np.zeros((len(docs), len(self.word_index)))
@@ -60,7 +60,7 @@ class TfidfEncoder(BaseEncoder):
tf = tf / norm(tf, axis=1, keepdims=True)
return tf
- def _compute_idf(self, docs: list[str]) -> np.ndarray:
+ def _compute_idf(self, docs: List[str]) -> np.ndarray:
if len(self.word_index) == 0:
raise ValueError("Word index is not initialized.")
idf = np.zeros(len(self.word_index))
diff --git a/semantic_router/layer.py b/semantic_router/layer.py
index b7905cca30d69b57638baa9ecb93ec79504a43ca..90cb7bfa6e9c4637bae3b5f485b297922cc85804 100644
--- a/semantic_router/layer.py
+++ b/semantic_router/layer.py
@@ -196,7 +196,7 @@ class RouteLayer:
else:
self.encoder = encoder
self.llm = llm
- self.routes: list[Route] = routes if routes is not None else []
+ self.routes: List[Route] = routes if routes is not None else []
self.score_threshold = self.encoder.score_threshold
self.top_k = top_k
if self.top_k < 1:
diff --git a/semantic_router/llms/base.py b/semantic_router/llms/base.py
index d3f207a187f8d9690c422f19d6b0f1a057b979c0..44af45e51b902670d035783d566ebec10dd2d20d 100644
--- a/semantic_router/llms/base.py
+++ b/semantic_router/llms/base.py
@@ -20,7 +20,7 @@ class BaseLLM(BaseModel):
raise NotImplementedError("Subclasses must implement this method")
def _is_valid_inputs(
- self, inputs: list[dict[str, Any]], function_schemas: list[dict[str, Any]]
+ self, inputs: List[dict[str, Any]], function_schemas: List[dict[str, Any]]
) -> bool:
"""Determine if the functions chosen by the LLM exist within the function_schemas,
and if the input arguments are valid for those functions."""
@@ -68,7 +68,7 @@ class BaseLLM(BaseModel):
logger.error(f"Single input validation error: {str(e)}")
return False
- def _extract_parameter_info(self, signature: str) -> tuple[list[str], list[str]]:
+ def _extract_parameter_info(self, signature: str) -> tuple[List[str], List[str]]:
"""Extract parameter names and types from the function signature."""
param_info = [param.strip() for param in signature[1:-1].split(",")]
param_names = [info.split(":")[0].strip() for info in param_info]
@@ -78,7 +78,7 @@ class BaseLLM(BaseModel):
return param_names, param_types
def extract_function_inputs(
- self, query: str, function_schemas: list[dict[str, Any]]
+ self, query: str, function_schemas: List[dict[str, Any]]
) -> dict:
logger.info("Extracting function input...")
diff --git a/semantic_router/llms/llamacpp.py b/semantic_router/llms/llamacpp.py
index 5a737b869b229fd36b8bf623e0ef6920423dbbd3..112cea9211d9dc70fdc5a08fdcc0da8d2ad56969 100644
--- a/semantic_router/llms/llamacpp.py
+++ b/semantic_router/llms/llamacpp.py
@@ -1,6 +1,6 @@
from contextlib import contextmanager
from pathlib import Path
-from typing import Any, Optional
+from typing import Any, Optional, List
from pydantic.v1 import PrivateAttr
@@ -48,7 +48,7 @@ class LlamaCppLLM(BaseLLM):
def __call__(
self,
- messages: list[Message],
+ messages: List[Message],
) -> str:
try:
completion = self.llm.create_chat_completion(
diff --git a/semantic_router/llms/openai.py b/semantic_router/llms/openai.py
index 7a887b8eaf80d345d270506463b32b992c11c886..c316fdc1df914ac13b2db97afe1f26ee0dfbd52c 100644
--- a/semantic_router/llms/openai.py
+++ b/semantic_router/llms/openai.py
@@ -41,7 +41,7 @@ class OpenAILLM(BaseLLM):
self.temperature = temperature
self.max_tokens = max_tokens
- def _extract_tool_calls_info(self, tool_calls: list[dict[str, Any]]) -> list[dict[str, Any]]:
+ def _extract_tool_calls_info(self, tool_calls: List[dict[str, Any]]) -> List[dict[str, Any]]:
tool_calls_info = []
for tool_call in tool_calls:
if tool_call.function.arguments is None:
@@ -57,7 +57,7 @@ class OpenAILLM(BaseLLM):
def __call__(
self,
messages: List[Message],
- function_schemas: Optional[list[dict[str, Any]]] = None,
+ function_schemas: Optional[List[dict[str, Any]]] = None,
) -> str:
if self.client is None:
raise ValueError("OpenAI client is not initialized.")
@@ -99,7 +99,7 @@ class OpenAILLM(BaseLLM):
raise Exception(f"LLM error: {e}") from e
def extract_function_inputs(
- self, query: str, function_schemas: list[dict[str, Any]]
+ self, query: str, function_schemas: List[dict[str, Any]]
) -> dict:
messages = []
system_prompt = "You are an intelligent AI. Given a command or request from the user, call the function to complete the request."
diff --git a/semantic_router/route.py b/semantic_router/route.py
index 74209058f9a79e363e963054e4b4e85d0b854708..e9fe47bbf536ff8df3d4148b96cbb76b81c0dafe 100644
--- a/semantic_router/route.py
+++ b/semantic_router/route.py
@@ -47,7 +47,7 @@ class Route(BaseModel):
name: str
utterances: Union[List[str], List[Union[Any, "Image"]]]
description: Optional[str] = None
- function_schemas: Optional[list[Dict[str, Any]]] = None
+ function_schemas: Optional[List[Dict[str, Any]]] = None
llm: Optional[BaseLLM] = None
score_threshold: Optional[float] = None
diff --git a/semantic_router/schema.py b/semantic_router/schema.py
index f2c5baeb8cae606cd7027684c96bf17d9b15c89b..b18d9691d7650811ee73694a9515bf662d18d49b 100644
--- a/semantic_router/schema.py
+++ b/semantic_router/schema.py
@@ -24,7 +24,7 @@ class EncoderInfo(BaseModel):
class RouteChoice(BaseModel):
name: Optional[str] = None
- function_call: Optional[list[dict]] = None
+ function_call: Optional[List[dict]] = None
similarity_score: Optional[float] = None
diff --git a/semantic_router/splitters/rolling_window.py b/semantic_router/splitters/rolling_window.py
index 89336a2b50f6b5f2db4d5ce514a1175ce9b69660..fb4ce20adae1e0c8dfa58e5a1ca901d5f6d96961 100644
--- a/semantic_router/splitters/rolling_window.py
+++ b/semantic_router/splitters/rolling_window.py
@@ -340,7 +340,7 @@ class RollingWindowSplitter(BaseSplitter):
self,
similarities: List[float],
split_indices: List[int],
- splits: list[DocumentSplit],
+ splits: List[DocumentSplit],
):
try:
from matplotlib import pyplot as plt
diff --git a/semantic_router/splitters/utils.py b/semantic_router/splitters/utils.py
index 349c3eaac76017c53dd5425abfe65e7e2952a679..6f71f979d1e1c668c5bded72722377e8232471ad 100644
--- a/semantic_router/splitters/utils.py
+++ b/semantic_router/splitters/utils.py
@@ -1,8 +1,8 @@
import regex
import tiktoken
+from typing import List
-
-def split_to_sentences(text: str) -> list[str]:
+def split_to_sentences(text: str) -> List[str]:
"""
Enhanced regex pattern to split a given text into sentences more accurately.
diff --git a/semantic_router/text.py b/semantic_router/text.py
index 6038888d1926c59f256dd8b5df8c15851f84e784..0706556e32cc409a93a43b4d784e040bd77ce276 100644
--- a/semantic_router/text.py
+++ b/semantic_router/text.py
@@ -157,7 +157,7 @@ class Conversation(BaseModel):
:raises ValueError: If the splitter is not configured before calling this method.
:return: A tuple containing the updated list of topics and the list of new topics generated in this call.
- :rtype: tuple[list[tuple[int, str]], list[DocumentSplit]]
+ :rtype: tuple[List[tuple[int, str]], List[DocumentSplit]]
"""
if self.splitter is None: