From 0212ba4db1205c5153a8d21824a1e3e0108252ee Mon Sep 17 00:00:00 2001
From: Siraj R Aizlewood <siraj@aurelio.ai>
Date: Fri, 3 May 2024 23:54:32 +0400
Subject: [PATCH] Changed typehints from dict to Dict.
The former is only supported from Python 3.10 onwards and we'd like to support Python 3.9 onwards.
---
docs/00-introduction.ipynb | 2 +-
docs/examples/unstructured-element-splitter.ipynb | 8 ++++----
replace.py | 4 ++--
semantic_router/encoders/clip.py | 8 ++++----
semantic_router/encoders/huggingface.py | 6 +++---
semantic_router/encoders/tfidf.py | 2 +-
semantic_router/encoders/vit.py | 6 +++---
semantic_router/index/base.py | 4 ++--
semantic_router/index/local.py | 4 ++--
semantic_router/index/pinecone.py | 4 ++--
semantic_router/index/qdrant.py | 2 +-
semantic_router/layer.py | 8 ++++----
semantic_router/llms/base.py | 10 +++++-----
semantic_router/llms/llamacpp.py | 6 +++---
semantic_router/llms/openai.py | 11 +++++------
semantic_router/schema.py | 6 +++---
16 files changed, 45 insertions(+), 46 deletions(-)
diff --git a/docs/00-introduction.ipynb b/docs/00-introduction.ipynb
index 209aa103..2183c213 100644
--- a/docs/00-introduction.ipynb
+++ b/docs/00-introduction.ipynb
@@ -318,7 +318,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.8"
+ "version": "3.11.4"
}
},
"nbformat": 4,
diff --git a/docs/examples/unstructured-element-splitter.ipynb b/docs/examples/unstructured-element-splitter.ipynb
index c9d67c0d..4eeb6fe9 100644
--- a/docs/examples/unstructured-element-splitter.ipynb
+++ b/docs/examples/unstructured-element-splitter.ipynb
@@ -103,10 +103,10 @@
"source": [
"from unstructured.documents.elements import Element\n",
"from colorama import Fore, Style\n",
- "from typing import List\n",
+ "from typing import List, Dict\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",
@@ -143,10 +143,10 @@
"outputs": [],
"source": [
"from semantic_router.splitters import RollingWindowSplitter\n",
- "\n",
+ "from typing import Dict\n",
"\n",
"def create_title_chunks(\n",
- " grouped_elements: dict, splitter: RollingWindowSplitter\n",
+ " grouped_elements: Dict, splitter: RollingWindowSplitter\n",
") -> list:\n",
" title_with_chunks = []\n",
" for title, elements in grouped_elements.items():\n",
diff --git a/replace.py b/replace.py
index 2e8c8c59..25592ff1 100644
--- a/replace.py
+++ b/replace.py
@@ -9,9 +9,9 @@ def replace_type_hints(file_path):
# Decode the file data with error handling
file_data = file_data.decode("utf-8", errors="ignore")
- # Regular expression pattern to find 'dict[Type1, Type2] | None' and replace with 'Optional[dict[Type1, Type2]]'
+ # Regular expression pattern to find 'Dict[Type1, Type2] | None' and replace with 'Optional[Dict[Type1, Type2]]'.
file_data = re.sub(
- r"dict\[(\w+), (\w+)\]\s*\|\s*None", r"Optional[dict[\1, \2]]", file_data
+ r"Dict\[(\w+), (\w+)\]\s*\|\s*None", r"Optional[Dict[\1, \2]]", file_data
)
with open(file_path, "w") as file:
diff --git a/semantic_router/encoders/clip.py b/semantic_router/encoders/clip.py
index 89a85cf3..6495c870 100644
--- a/semantic_router/encoders/clip.py
+++ b/semantic_router/encoders/clip.py
@@ -2,7 +2,7 @@ from typing import Any, List, Optional
import numpy as np
from pydantic.v1 import PrivateAttr
-
+from typing import Dict
from semantic_router.encoders import BaseEncoder
@@ -10,9 +10,9 @@ class CLIPEncoder(BaseEncoder):
name: str = "openai/clip-vit-base-patch16"
type: str = "huggingface"
score_threshold: float = 0.2
- tokenizer_kwargs: dict = {}
- processor_kwargs: dict = {}
- model_kwargs: dict = {}
+ tokenizer_kwargs: Dict = {}
+ processor_kwargs: Dict = {}
+ model_kwargs: Dict = {}
device: Optional[str] = None
_tokenizer: Any = PrivateAttr()
_processor: Any = PrivateAttr()
diff --git a/semantic_router/encoders/huggingface.py b/semantic_router/encoders/huggingface.py
index 24bd5cd0..7ca7580d 100644
--- a/semantic_router/encoders/huggingface.py
+++ b/semantic_router/encoders/huggingface.py
@@ -23,7 +23,7 @@ Classes:
import requests
import time
import os
-from typing import Any, List, Optional
+from typing import Any, List, Optional, Dict
from pydantic.v1 import PrivateAttr
@@ -35,8 +35,8 @@ class HuggingFaceEncoder(BaseEncoder):
name: str = "sentence-transformers/all-MiniLM-L6-v2"
type: str = "huggingface"
score_threshold: float = 0.5
- tokenizer_kwargs: dict = {}
- model_kwargs: dict = {}
+ tokenizer_kwargs: Dict = {}
+ model_kwargs: Dict = {}
device: Optional[str] = None
_tokenizer: Any = PrivateAttr()
_model: Any = PrivateAttr()
diff --git a/semantic_router/encoders/tfidf.py b/semantic_router/encoders/tfidf.py
index dbbe56f6..17cc569a 100644
--- a/semantic_router/encoders/tfidf.py
+++ b/semantic_router/encoders/tfidf.py
@@ -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():
diff --git a/semantic_router/encoders/vit.py b/semantic_router/encoders/vit.py
index 65de365a..9002ec23 100644
--- a/semantic_router/encoders/vit.py
+++ b/semantic_router/encoders/vit.py
@@ -1,4 +1,4 @@
-from typing import Any, List, Optional
+from typing import Any, List, Optional, Dict
from pydantic.v1 import PrivateAttr
@@ -9,8 +9,8 @@ class VitEncoder(BaseEncoder):
name: str = "google/vit-base-patch16-224"
type: str = "huggingface"
score_threshold: float = 0.5
- processor_kwargs: dict = {}
- model_kwargs: dict = {}
+ processor_kwargs: Dict = {}
+ model_kwargs: Dict = {}
device: Optional[str] = None
_processor: Any = PrivateAttr()
_model: Any = PrivateAttr()
diff --git a/semantic_router/index/base.py b/semantic_router/index/base.py
index d95a62a8..bc5adcca 100644
--- a/semantic_router/index/base.py
+++ b/semantic_router/index/base.py
@@ -1,4 +1,4 @@
-from typing import Any, List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union, Dict
import numpy as np
from pydantic.v1 import BaseModel
@@ -35,7 +35,7 @@ class BaseIndex(BaseModel):
"""
raise NotImplementedError("This method should be implemented by subclasses.")
- def describe(self) -> dict:
+ def describe(self) -> Dict:
"""
Returns a dictionary with index details such as type, dimensions, and total
vector count.
diff --git a/semantic_router/index/local.py b/semantic_router/index/local.py
index 6d322f07..df9e02c1 100644
--- a/semantic_router/index/local.py
+++ b/semantic_router/index/local.py
@@ -1,4 +1,4 @@
-from typing import List, Optional, Tuple
+from typing import List, Optional, Tuple, Dict
import numpy as np
@@ -49,7 +49,7 @@ class LocalIndex(BaseIndex):
raise ValueError("No routes have been added to the index.")
return list(zip(self.routes, self.utterances))
- def describe(self) -> dict:
+ def describe(self) -> Dict:
return {
"type": self.type,
"dimensions": self.index.shape[1] if self.index is not None else 0,
diff --git a/semantic_router/index/pinecone.py b/semantic_router/index/pinecone.py
index 31fbfac8..b70c5d47 100644
--- a/semantic_router/index/pinecone.py
+++ b/semantic_router/index/pinecone.py
@@ -138,7 +138,7 @@ class PineconeIndex(BaseIndex):
self.host = self.client.describe_index(self.index_name)["host"]
return index
- def _batch_upsert(self, batch: List[dict]):
+ def _batch_upsert(self, batch: List[Dict]):
"""Helper method for upserting a single batch of records."""
if self.index is not None:
self.index.upsert(vectors=batch, namespace=self.namespace)
@@ -241,7 +241,7 @@ class PineconeIndex(BaseIndex):
def delete_all(self):
self.index.delete(delete_all=True, namespace=self.namespace)
- def describe(self) -> dict:
+ def describe(self) -> Dict:
if self.index is not None:
stats = self.index.describe_index_stats()
return {
diff --git a/semantic_router/index/qdrant.py b/semantic_router/index/qdrant.py
index a2292da0..bb49f1fd 100644
--- a/semantic_router/index/qdrant.py
+++ b/semantic_router/index/qdrant.py
@@ -208,7 +208,7 @@ class QdrantIndex(BaseIndex):
),
)
- def describe(self) -> dict:
+ def describe(self) -> Dict:
collection_info = self.client.get_collection(self.index_name)
return {
diff --git a/semantic_router/layer.py b/semantic_router/layer.py
index 90cb7bfa..3639b7a8 100644
--- a/semantic_router/layer.py
+++ b/semantic_router/layer.py
@@ -428,7 +428,7 @@ class RouteLayer:
def _retrieve(
self, xq: Any, top_k: int = 5, route_filter: Optional[List[str]] = None
- ) -> List[dict]:
+ ) -> List[Dict]:
"""Given a query vector, retrieve the top_k most similar records."""
# get scores and routes
scores, routes = self.index.query(
@@ -448,7 +448,7 @@ class RouteLayer:
f"Unsupported aggregation method chosen: {aggregation}. Choose either 'SUM', 'MEAN', or 'MAX'."
)
- def _semantic_classify(self, query_results: List[dict]) -> Tuple[str, List[float]]:
+ def _semantic_classify(self, query_results: List[Dict]) -> Tuple[str, List[float]]:
scores_by_class = self.group_scores_by_class(query_results)
# Calculate total score for each class
@@ -473,7 +473,7 @@ class RouteLayer:
return None
def _semantic_classify_multiple_routes(
- self, query_results: List[dict]
+ self, query_results: List[Dict]
) -> List[Tuple[str, float]]:
scores_by_class = self.group_scores_by_class(query_results)
@@ -496,7 +496,7 @@ class RouteLayer:
return classes_above_threshold
def group_scores_by_class(
- self, query_results: List[dict]
+ self, query_results: List[Dict]
) -> Dict[str, List[float]]:
scores_by_class: Dict[str, List[float]] = {}
for result in query_results:
diff --git a/semantic_router/llms/base.py b/semantic_router/llms/base.py
index 44af45e5..b89cfdc2 100644
--- a/semantic_router/llms/base.py
+++ b/semantic_router/llms/base.py
@@ -1,5 +1,5 @@
import json
-from typing import Any, List, Optional
+from typing import Any, List, Optional, Dict
from pydantic.v1 import BaseModel
@@ -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."""
@@ -49,7 +49,7 @@ class BaseLLM(BaseModel):
logger.error(f"Input validation error: {str(e)}")
return False
- def _validate_single_function_inputs(self, inputs: dict[str, Any], function_schema: dict[str, Any]) -> bool:
+ def _validate_single_function_inputs(self, inputs: Dict[str, Any], function_schema: Dict[str, Any]) -> bool:
"""Validate the extracted inputs against the function schema"""
try:
# Extract parameter names and types from the signature string
@@ -78,8 +78,8 @@ class BaseLLM(BaseModel):
return param_names, param_types
def extract_function_inputs(
- self, query: str, function_schemas: List[dict[str, Any]]
- ) -> dict:
+ self, query: str, function_schemas: List[Dict[str, Any]]
+ ) -> Dict:
logger.info("Extracting function input...")
prompt = f"""
diff --git a/semantic_router/llms/llamacpp.py b/semantic_router/llms/llamacpp.py
index 112cea92..26d05129 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, List
+from typing import Any, Optional, List, Dict
from pydantic.v1 import PrivateAttr
@@ -79,8 +79,8 @@ class LlamaCppLLM(BaseLLM):
self.grammar = None
def extract_function_inputs(
- self, query: str, function_schema: dict[str, Any]
- ) -> dict:
+ self, query: str, function_schema: Dict[str, Any]
+ ) -> Dict:
with self._grammar():
return super().extract_function_inputs(
query=query, function_schema=function_schema
diff --git a/semantic_router/llms/openai.py b/semantic_router/llms/openai.py
index c316fdc1..1e121a3e 100644
--- a/semantic_router/llms/openai.py
+++ b/semantic_router/llms/openai.py
@@ -1,5 +1,5 @@
import os
-from typing import List, Optional, Any
+from typing import List, Optional, Any, Callable, Dict
import openai
from openai._types import NotGiven
@@ -11,7 +11,6 @@ from semantic_router.utils.logger import logger
import json
from semantic_router.utils.function_call import get_schema, convert_python_type_to_json_type
import inspect
-from typing import Callable, Dict
import re
class OpenAILLM(BaseLLM):
@@ -41,7 +40,7 @@ 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 +56,7 @@ 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.")
@@ -99,8 +98,8 @@ class OpenAILLM(BaseLLM):
raise Exception(f"LLM error: {e}") from e
def extract_function_inputs(
- self, query: str, function_schemas: List[dict[str, Any]]
- ) -> dict:
+ 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."
messages.append(Message(role="system", content=system_prompt))
diff --git a/semantic_router/schema.py b/semantic_router/schema.py
index b18d9691..63f1e440 100644
--- a/semantic_router/schema.py
+++ b/semantic_router/schema.py
@@ -1,5 +1,5 @@
from enum import Enum
-from typing import List, Optional, Union, Any
+from typing import List, Optional, Union, Any, Dict
from pydantic.v1 import BaseModel
@@ -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
@@ -55,7 +55,7 @@ class DocumentSplit(BaseModel):
is_triggered: bool = False
triggered_score: Optional[float] = None
token_count: Optional[int] = None
- metadata: Optional[dict] = None
+ metadata: Optional[Dict] = None
@property
def content(self) -> str:
--
GitLab