first commit

enums.py

@@ -0,0 +1,10 @@
+from enum import Enum
+class ModelType(Enum):
+    EMBEDDING = "embedding"
+    TRANSCRIPTION = "transcription"
+    RESPONSE = "response"
+class PreprocessorType(Enum):
+    NORWEGIAN = "norwegian"
+    DEFAULT = "norwegian"
+class SymbolProvider(Enum):
+    TOBII_DYNAVOX = "tobii_dynavox"

pyproject.toml

@@ -0,0 +1,20 @@
+[project]
+name = "shared-types"
+version = "0.1.0"
+description = "Shared typing models for all services"
+authors = [
+    { name = "Your Team", email = "team@example.com" }
+]
+requires-python = ">=3.10"
+readme = "README.md"
+keywords = ["types", "schemas", "shared"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent"
+]
+
+[build-system]
+requires = ["setuptools>=65.5.1", "wheel"]
+build-backend = "setuptools.build_meta"

schemas.py

@@ -0,0 +1,52 @@
+from pydantic import BaseModel as PydanticBaseModel
+from typing import List, Any, Dict,Union
+from structures import Embedding,Word, Symbol,Phrase
+
+
+
+class EmbedRequest(PydanticBaseModel):
+    stemmed_words: List[str]
+    tokens: dict
+class EmbeddingResponse(PydanticBaseModel):
+    embeddings: List[Embedding]
+
+
+class ResponseRequest(PydanticBaseModel):
+    text: str
+    context: Dict[str, Any]
+    
+    
+class PreprocessRequest(PydanticBaseModel):
+    text: str
+
+class PreprocessResponse(PydanticBaseModel):
+    raw_words: List[str]
+    tokens: Dict[str, Any]
+    
+    
+class GetSymbolRequest(PydanticBaseModel):
+    lexeme_id: int
+    
+class GetSymbolResponse(PydanticBaseModel):
+    symbol: Symbol
+    
+class GetWordRequest(PydanticBaseModel):
+    word_text: str
+    stemmed: bool = False
+    
+
+class GetWordResponse(PydanticBaseModel):
+    word:Union[Word,None]
+    
+class GetSimilarWordRequest(PydanticBaseModel):
+    embedding: Embedding
+    
+class GetAllPhrasesResponse(PydanticBaseModel):
+    phrases: List[Phrase]
+    
+
+
+
+
+
+

structures/embedding.py

@@ -0,0 +1,18 @@
+from __future__ import annotations
+from dataclasses import dataclass
+import torch
+
+
+@dataclass(frozen=True)
+class Embedding:
+    data: torch.Tensor
+
+    def __post_init__(self):
+        if not isinstance(self.data, torch.Tensor):
+            raise TypeError(f"data must be a torch.Tensor, got {type(self.data)}")
+
+    def compare(self, other: Embedding) -> float:
+        """
+        Compare this embedding with another embedding.
+        """
+        raise NotImplementedError("compare method must be implemented")

structures/lexeme.py

@@ -0,0 +1,22 @@
+from abc import ABC, abstractmethod
+from typing import List, Union
+from dataclasses import dataclass
+from .embedding import Embedding
+
+
+@dataclass
+class Lexeme(ABC):
+    id: int
+
+    @property
+    @abstractmethod
+    def content(self) -> Union[str, List[str]]:
+        """Text content of the lexeme."""
+        pass
+
+    @property
+    @abstractmethod
+    def embedding(self) -> Embedding:
+        """Embedding(s) associated with the lexeme."""
+        pass
+    

structures/phrase.py

@@ -0,0 +1,26 @@
+from typing import List
+
+from .lexeme import Lexeme
+from .embedding import Embedding
+from .word import Word
+
+
+class Phrase(Lexeme):
+    def __init__(self, id: int, content: str, embedding: Embedding):
+        self.id = id
+        self._content = content
+        self._embedding = embedding
+        
+    @property
+    def content(self) -> List[str]:
+        return self._content
+
+    @property
+    def embedding(self) -> Embedding:
+        return self._embedding
+    
+    def __str__(self):
+        return self.content
+    
+    def __repr__(self):
+        return self.__str__()

structures/symbol.py

@@ -0,0 +1,10 @@
+from dataclasses import dataclass
+from typing import Optional
+from PIL import Image
+
+
+@dataclass
+class Symbol:
+    id: int
+    label: str
+    image: Optional[Image.Image]

structures/word.py

@@ -0,0 +1,23 @@
+from .lexeme import Lexeme
+from .embedding import Embedding
+
+
+class Word(Lexeme):
+    def __init__(self, word_id: int, content: str, embedding: Embedding):
+        self.id = word_id
+        self._content = content
+        self._embedding = embedding
+
+    @property
+    def content(self) -> str:
+        return self._content
+
+    @property
+    def embedding(self) -> Embedding:
+        return self._embedding
+    
+    def __str__(self):
+        return self.content
+    
+    def __repr__(self):
+        return self.__str__()