folder-classifier 0.2.3__py3-none-any.whl → 0.3.2__py3-none-any.whl

{folder_classifier-0.2.3.dist-info → folder_classifier-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: folder-classifier
-Version: 0.2.3
+Version: 0.3.2
 Summary: Deploy folder classifier API to a Ray cluster
 Author: Crispin Almodovar
 Author-email: 

folder_classifier-0.3.2.dist-info/RECORD

@@ -0,0 +1,4 @@
+folder_classifier-0.3.2.dist-info/METADATA,sha256=jHP5fAMkxgCHpCPo2q9Rzc2Vm9sU-33X94vHHfrHPMs,392
+folder_classifier-0.3.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+folder_classifier-0.3.2.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+folder_classifier-0.3.2.dist-info/RECORD,,

folder_classifier-0.3.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+

folder_classifier/__init__.py

@@ -1 +0,0 @@
-from folder_classifier.deploy import build_app

folder_classifier/app.py

@@ -1,31 +0,0 @@
-import logging
-
-from fastapi import FastAPI
-from ray import serve
-
-from folder_classifier.dto import (ModelConfig, FolderClassificationResponse,
-                                   FolderClassificationRequest, Listing, Folder)
-from folder_classifier.util import flatten_folder
-from folder_classifier import classifier
-
-web_api = FastAPI(title=f"Folder Classifier API")
-
-
-@serve.deployment
-@serve.ingress(web_api)
-class FolderClassifierAPI:
-    def __init__(self, model_config: ModelConfig):
-        assert model_config, "model_config is required"
-        assert model_config.app_name and model_config.deployment, "Invalid ModelConfig values"
-        logging.basicConfig(level=logging.INFO)
-        self.logger = logging.getLogger(__name__)
-        self.logger.info(f"Initializing model: {model_config}")
-        #self.model_handle = serve.get_deployment_handle(app_name=model_config.app_name, deployment_name=model_config.deployment)
-        self.logger.info(f"Successfully initialized Folder Classifier API")
-
-    @web_api.post("/predict")
-    async def predict(self, request: FolderClassificationRequest) -> FolderClassificationResponse:
-        listing = request if isinstance(request, Listing) else Listing(items=flatten_folder(request))
-        category, confidence = classifier.predict(listing)
-        self.logger.info(f"Received request: {request}")
-        return FolderClassificationResponse(category=category, confidence=confidence)

folder_classifier/classifier.py

@@ -1,25 +0,0 @@
-from typing import Tuple
-import torch
-from transformers import pipeline
-from folder_classifier.dto import Listing
-
-
-classifier = None
-
-
-def predict(listing: Listing) -> Tuple[str, float]:
-    global classifier
-    if classifier is None:
-        classifier = pipeline(
-            "text-classification",
-            model="/mnt/cluster_storage/models/corto-ai/ModernBERT-large-folder-classifier",
-            torch_dtype=torch.bfloat16,
-            device="cuda"
-        )
-    text = "\n".join(listing.items)
-    prediction = classifier(text)
-    predicted_label = prediction[0]["label"]
-    confidence = prediction[0]["score"]
-    return predicted_label, confidence
-
-

folder_classifier/deploy.py

@@ -1,12 +0,0 @@
-from ray.serve import Application
-
-from folder_classifier.app import FolderClassifierAPI
-from folder_classifier.dto import AppConfig
-
-
-def build_app(args: AppConfig) -> Application:
-    assert args and args.model, "AppConfig model is required"
-    assert args.model.app_name and args.model.deployment, "Model's app_name and deployment are required"
-
-    app = FolderClassifierAPI.bind(args.model)
-    return app

folder_classifier/dto.py

@@ -1,54 +0,0 @@
-from __future__ import annotations
-
-from textwrap import dedent
-from typing import List, Union, Literal, Optional
-
-from pydantic import BaseModel, Field, confloat
-
-
-class ModelConfig(BaseModel):
-    app_name: str
-    deployment: str
-
-
-class AppConfig(BaseModel):
-    model: ModelConfig
-
-
-class File(BaseModel):
-    name: str
-    type: Literal["file"]
-
-
-class Folder(BaseModel):
-    name: str
-    type: Literal["folder"]
-    # Discriminated union: 'type' field is used to select between File and Folder
-    items: Optional[List[Union[File, Folder]]] = Field(default_factory=list)
-    model_config = {
-        "json_schema_extra": {
-            # Override the OpenAPI example to avoid the default 'string' entry
-            "example": dedent("""{
-                "name": "string",
-                "type": "folder",
-                "items": [
-                    {
-                      "name": "string",
-                      "type": "file"
-                    }
-                  ]
-                }""")
-        }
-    }
-
-
-class Listing(BaseModel):
-    items: List[str]
-
-
-Folder.model_rebuild()
-FolderClassificationRequest = Listing
-
-class FolderClassificationResponse(BaseModel):
-    category: Literal["matter", "other"]
-    confidence: confloat(ge=0.0, le=1.0)

folder_classifier/util.py

@@ -1,21 +0,0 @@
-from typing import List
-
-from folder_classifier.dto import Folder
-
-
-def flatten_folder(folder: Folder, parent_path: str = "") -> List[str]:
-    """
-    Traverses a Folder and returns a list of file paths.
-    Each path is constructed by joining folder and file names with '/'.
-    """
-    paths: List[str] = []
-    # Build the path for the current folder
-    current_path = f"{parent_path}/{folder.name}" if parent_path else folder.name
-
-    for item in folder.items:
-        if item.type == "file":
-            paths.append(f"{current_path}/{item.name}")
-        else:
-            # Recursively flatten subfolders
-            paths.extend(flatten_folder(item, current_path))
-    return paths

folder_classifier-0.2.3.dist-info/RECORD

@@ -1,10 +0,0 @@
-folder_classifier/__init__.py,sha256=k0YWZyUNe7myJiKeX0OaXtJ30_3EGE-vsZiAUbqa-3E,46
-folder_classifier/app.py,sha256=FqoBp_KQ3yIfoHTagdDTVsLbIj8luCn7en533Q870x8,1443
-folder_classifier/classifier.py,sha256=YVKXvNAHny167H0Iv0GlRJEtRMAYwGea3cUVeGC4_sI,668
-folder_classifier/deploy.py,sha256=UQTbQjR_JX92Xo8L5EbK4nPg_VJmwWDmzMQSjP3-7iQ,412
-folder_classifier/dto.py,sha256=Xb1ozZQkfC45cbBoNOZ8xfkillJWFKXKWQc9CZxppXI,1260
-folder_classifier/util.py,sha256=t-ma2suHovfNutogJb9jailRbRpIg4qv-zph3dHb2og,692
-folder_classifier-0.2.3.dist-info/METADATA,sha256=MZ_BgIBlPrq86na7t9aMXA8EONA05MaHPofJV1P6hZM,392
-folder_classifier-0.2.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-folder_classifier-0.2.3.dist-info/top_level.txt,sha256=36ugc9pEbNQ-mnzz4Ot2WVjY3t_LzAN6XOCjDFP4p4k,18
-folder_classifier-0.2.3.dist-info/RECORD,,

folder_classifier-0.2.3.dist-info/top_level.txt

@@ -1 +0,0 @@
-folder_classifier