labelr 0.7.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

labelr/sample.py

@@ -1,16 +1,20 @@
 import logging
 import random
 import string
+import typing
 
 import datasets
+import PIL
 from openfoodfacts import Flavor
 from openfoodfacts.barcode import normalize_barcode
 from openfoodfacts.images import download_image, generate_image_url
+from PIL import Image, ImageOps
+from pydantic import BaseModel, Field
 
 logger = logging.getLogger(__name__)
 
 
-def format_annotation_results_from_hf(
+def format_annotation_results_from_hf_to_ls(
     objects: dict, image_width: int, image_height: int
 ):
     """Format annotation results from a HF object detection dataset into Label
@@ -56,12 +60,12 @@ def format_annotation_results_from_hf(
     return annotation_results
 
 
-def format_object_detection_sample_from_hf(hf_sample: dict, split: str) -> dict:
+def format_object_detection_sample_from_hf_to_ls(hf_sample: dict, split: str) -> dict:
     hf_meta = hf_sample["meta"]
     objects = hf_sample["objects"]
     image_width = hf_sample["width"]
     image_height = hf_sample["height"]
-    annotation_results = format_annotation_results_from_hf(
+    annotation_results = format_annotation_results_from_hf_to_ls(
         objects, image_width, image_height
     )
     image_id = hf_sample["image_id"]
@@ -149,8 +153,24 @@ def format_object_detection_sample_to_hf(
     annotations: list[dict],
     label_names: list[str],
     merge_labels: bool = False,
-    use_aws_cache: bool = True,
+    use_aws_cache: bool = False,
 ) -> dict | None:
+    """Format a Label Studio object detection sample to Hugging Face format.
+
+    Args:
+        task_data: The task data from Label Studio.
+        annotations: The annotations from Label Studio.
+        label_names: The list of label names.
+        merge_labels: Whether to merge all labels into a single label (the
+            first label in `label_names`).
+        use_aws_cache: Whether to use AWS cache when downloading images.
+
+    Returns:
+        The formatted sample, or None in the following cases:
+        - More than one annotation is found
+        - No annotation is found
+        - An error occurs when downloading the image
+    """
     if len(annotations) > 1:
         logger.info("More than one annotation found, skipping")
         return None
@@ -186,6 +206,13 @@ def format_object_detection_sample_to_hf(
         logger.error("Failed to download image: %s", image_url)
         return None
 
+    # Correct image orientation using EXIF data
+    # Label Studio provides bounding boxes based on the displayed image (after
+    # eventual EXIF rotation), so we need to apply the same transformation to
+    # the image.
+    # Indeed, Hugging Face stores images without applying EXIF rotation, and
+    # EXIF data is not preserved in the dataset.
+    ImageOps.exif_transpose(typing.cast(PIL.Image.Image, image), in_place=True)
     return {
         "image_id": task_data["image_id"],
         "image": image,
@@ -204,6 +231,34 @@ def format_object_detection_sample_to_hf(
     }
 
 
+class SampleMeta(BaseModel):
+    barcode: str | None = Field(
+        ..., description="The barcode of the product, if applicable"
+    )
+    off_image_id: str | None = Field(
+        ...,
+        description="The Open Food Facts image ID associated with the image, if applicable",
+    )
+    image_url: str | None = Field(
+        ..., description="The URL of the image, if applicable"
+    )
+
+
+class LLMImageExtractionSample(BaseModel):
+    class Config:
+        # required to allow PIL Image type
+        arbitrary_types_allowed = True
+
+    image_id: str = Field(
+        ...,
+        description="unique ID for the image. For Open Food Facts images, it follows the "
+        "format `barcode:imgid`",
+    )
+    image: Image.Image = Field(..., description="Image to extract information from")
+    output: str = Field(..., description="Expected response of the LLM")
+    meta: SampleMeta = Field(..., description="Metadata associated with the sample")
+
+
 # The HuggingFace Dataset features
 HF_DS_OBJECT_DETECTION_FEATURES = datasets.Features(
     {
@@ -240,3 +295,16 @@ HF_DS_CLASSIFICATION_FEATURES = datasets.Features(
         "category_name": datasets.Value("string"),
     }
 )
+
+HF_DS_LLM_IMAGE_EXTRACTION_FEATURES = datasets.Features(
+    {
+        "image_id": datasets.Value("string"),
+        "image": datasets.features.Image(),
+        "output": datasets.features.Value("string"),
+        "meta": {
+            "barcode": datasets.Value("string"),
+            "off_image_id": datasets.Value("string"),
+            "image_url": datasets.Value("string"),
+        },
+    }
+)

labelr/utils.py

@@ -1,3 +1,10 @@
+import io
+from pathlib import Path
+
+from google.cloud import storage
+from PIL import Image
+
+
 def parse_hf_repo_id(hf_repo_id: str) -> tuple[str, str]:
     """Parse the repo_id and the revision from a hf_repo_id in the format:
     `org/repo-name@revision`.
@@ -11,3 +18,31 @@ def parse_hf_repo_id(hf_repo_id: str) -> tuple[str, str]:
         revision = "main"
 
     return hf_repo_id, revision
+
+
+def download_image_from_gcs(image_uri: str) -> Image.Image:
+    """Download an image from a Google Cloud Storage URI and return it as a
+    PIL Image."""
+    storage_client = storage.Client()
+    bucket_name, blob_name = image_uri.replace("gs://", "").split("/", 1)
+    bucket = storage_client.bucket(bucket_name)
+    blob = bucket.blob(blob_name)
+    image_data = blob.download_as_bytes()
+    return Image.open(io.BytesIO(image_data))
+
+
+class PathWithContext:
+    """A context manager that yields a Path object.
+
+    This is useful to have a common interface with tempfile.TemporaryDirectory
+    without actually creating a temporary directory.
+    """
+
+    def __init__(self, path: Path):
+        self.path = path
+
+    def __enter__(self) -> Path:
+        return self.path
+
+    def __exit__(self, exc_type, exc_value, traceback) -> None:
+        pass

{labelr-0.7.0.dist-info → labelr-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: labelr
-Version: 0.7.0
+Version: 0.9.0
 Summary: A command-line tool to manage labeling tasks with Label Studio.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -13,10 +13,19 @@ Requires-Dist: openfoodfacts>=2.9.0
 Requires-Dist: typer>=0.15.1
 Requires-Dist: google-cloud-batch==0.18.0
 Requires-Dist: huggingface-hub
+Requires-Dist: deepdiff>=8.6.1
+Requires-Dist: rapidfuzz>=3.14.3
+Requires-Dist: aiohttp
+Requires-Dist: aiofiles
+Requires-Dist: orjson
 Provides-Extra: ultralytics
 Requires-Dist: ultralytics==8.3.223; extra == "ultralytics"
 Provides-Extra: fiftyone
 Requires-Dist: fiftyone~=1.10.0; extra == "fiftyone"
+Provides-Extra: google
+Requires-Dist: google-genai>=1.56.0; extra == "google"
+Requires-Dist: gcloud-aio-storage; extra == "google"
+Requires-Dist: google-cloud-storage; extra == "google"
 Dynamic: license-file
 
 # Labelr
@@ -73,7 +82,7 @@ Once you have a Label Studio instance running, you can create a project easily.
 For an object detection task, a command allows you to create the configuration file automatically:
 
 ```bash
-labelr projects create-config --labels 'label1' --labels 'label2' --output-file label_config.xml
+labelr ls create-config --labels 'label1' --labels 'label2' --output-file label_config.xml
 ```
 
 where `label1` and `label2` are the labels you want to use for the object detection task, and `label_config.xml` is the output file that will contain the configuration.
@@ -81,17 +90,19 @@ where `label1` and `label2` are the labels you want to use for the object detect
 Then, you can create a project on Label Studio with the following command:
 
 ```bash
-labelr projects create --title my_project --api-key API_KEY --config-file label_config.xml
+labelr ls create --title my_project --api-key API_KEY --config-file label_config.xml
 ```
 
 where `API_KEY` is the API key of the Label Studio instance (API key is available at Account page), and `label_config.xml` is the configuration file of the project.
 
+`ls` stands for Label Studio in the CLI.
+
 #### Create a dataset file
 
 If you have a list of images, for an object detection task, you can quickly create a dataset file with the following command:
 
 ```bash
-labelr projects create-dataset-file --input-file image_urls.txt --output-file dataset.json
+labelr ls create-dataset-file --input-file image_urls.txt --output-file dataset.json
 ```
 
 where `image_urls.txt` is a file containing the URLs of the images, one per line, and `dataset.json` is the output file.
@@ -101,7 +112,7 @@ where `image_urls.txt` is a file containing the URLs of the images, one per line
 Next, import the generated data to a project with the following command:
 
 ```bash
-labelr projects import-data --project-id PROJECT_ID --dataset-path dataset.json
+labelr ls import-data --project-id PROJECT_ID --dataset-path dataset.json
 ```
 
 where `PROJECT_ID` is the ID of the project you created.
@@ -117,7 +128,7 @@ To accelerate annotation, you can pre-annotate the images with an object detecti
 To pre-annotate the data with Triton, use the following command:
 
 ```bash
-labelr projects add-prediction --project-id PROJECT_ID --backend ultralytics --labels 'product' --labels 'price tag' --label-mapping '{"price tag": "price-tag"}'
+labelr ls add-prediction --project-id PROJECT_ID --backend ultralytics --labels 'product' --labels 'price tag' --label-mapping '{"price tag": "price-tag"}'
 ```
 
 where `labels` is the list of labels to use for the object detection task (you can add as many labels as you want).

labelr-0.9.0.dist-info/RECORD

@@ -0,0 +1,28 @@
+labelr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labelr/__main__.py,sha256=G4e95-IfhI-lOmkOBP6kQ8wl1x_Fl7dZlLOYr90K83c,66
+labelr/annotate.py,sha256=3fJ9FYbcozcOoKuhNtzPHV8sSnp-45FsNnMc8UeBHGU,3503
+labelr/check.py,sha256=3wK6mE0UsKvoBNm0_lyWhCMq7gxkv5r50pvO70damXY,2476
+labelr/config.py,sha256=3RXF_NdkSuHvfVMGMlYmjlw45fU77zQkLX7gmZq7NxM,64
+labelr/dataset_features.py,sha256=ZC9QAUw9oKHqyUPla2h3xQFaRT9sHq8hkPNN4RDDwmo,1257
+labelr/export.py,sha256=aPfQ-RaK3C2WJrzbETYdC9kRe0MTpCRs0nu5l2SqiRg,20092
+labelr/google_genai.py,sha256=vn_UNQOxUDOTTTWz-emAVErjOtQmnlxM_m8yo2q01Ok,14401
+labelr/main.py,sha256=OTiJSkD_TrzQmQQm291FhknD-HQQTWfBEBgImxqL0KM,2634
+labelr/project_config.py,sha256=CIHEcgSOfXb53naHWEBkTDm2V9m3abAu8C54VSzHjAs,1260
+labelr/sample.py,sha256=VL-iKDvLaIeViJ0TaBY9uCbv0ey528fkaRTYE-Zr12I,10347
+labelr/types.py,sha256=8CHfLyifF_N94OYDhG-7IcWboOh9o0Z_0LBtQapT8TQ,313
+labelr/utils.py,sha256=-zLOWLbvLwtNFtzzwZ6RjJD9GstoYR-gt4wz9r6u9lE,1363
+labelr/apps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labelr/apps/datasets.py,sha256=kJQWwm3mjA2uWIA8O_DslM7OS5ht5mgWqcFC_zF4gCo,11187
+labelr/apps/evaluate.py,sha256=UC4CuSKa4vgR5xTBZ-dFgp_1pYnkM55s2IJgix0YtkI,1157
+labelr/apps/google_batch.py,sha256=BMcfBkDwfu-zOOR80bYmtEy6k_Qc70m7K7wmp4Ww0r8,9335
+labelr/apps/hugging_face.py,sha256=B0GaDZeUZj2A7nEeC1OtCANb0DqvBkhWwFWM_9Nm2kU,1608
+labelr/apps/label_studio.py,sha256=su9shoi0K9PmI8RBLipV2KQf_MRjkF5vy5-JUcbXr5A,16852
+labelr/apps/train.py,sha256=wmOSpO9JsrwCXYMgRg2srMbV5B5TvnlfhAKPqUt6wSg,7328
+labelr/evaluate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labelr/evaluate/object_detection.py,sha256=QJIwrDY-Vsy0-It6tZSkN3qgAlmIu2W1-kGdmibiPSQ,3349
+labelr-0.9.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+labelr-0.9.0.dist-info/METADATA,sha256=cNkf4LPmbO_k3UuR7O7NtcCwRF-Z5c-yIyQRAocsjww,7322
+labelr-0.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+labelr-0.9.0.dist-info/entry_points.txt,sha256=OACukVeR_2z54i8yQuWqqk_jdEHlyTwmTFOFBmxPp1k,43
+labelr-0.9.0.dist-info/top_level.txt,sha256=bjZo50aGZhXIcZYpYOX4sdAQcamxh8nwfEh7A9RD_Ag,7
+labelr-0.9.0.dist-info/RECORD,,

labelr/apps/users.py

@@ -1,36 +0,0 @@
-from typing import Annotated
-
-import typer
-
-from ..config import LABEL_STUDIO_DEFAULT_URL
-
-app = typer.Typer()
-
-# Label Studio user management
-
-
-@app.command()
-def list(
-    api_key: Annotated[str, typer.Option(envvar="LABEL_STUDIO_API_KEY")],
-    label_studio_url: str = LABEL_STUDIO_DEFAULT_URL,
-):
-    """List all users in Label Studio."""
-    from label_studio_sdk.client import LabelStudio
-
-    ls = LabelStudio(base_url=label_studio_url, api_key=api_key)
-
-    for user in ls.users.list():
-        print(f"{user.id:02d}: {user.email}")
-
-
-@app.command()
-def delete(
-    user_id: int,
-    api_key: Annotated[str, typer.Option(envvar="LABEL_STUDIO_API_KEY")],
-    label_studio_url: str = LABEL_STUDIO_DEFAULT_URL,
-):
-    """Delete a user from Label Studio."""
-    from label_studio_sdk.client import LabelStudio
-
-    ls = LabelStudio(base_url=label_studio_url, api_key=api_key)
-    ls.users.delete(user_id)

labelr-0.7.0.dist-info/RECORD

@@ -1,23 +0,0 @@
-labelr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-labelr/__main__.py,sha256=G4e95-IfhI-lOmkOBP6kQ8wl1x_Fl7dZlLOYr90K83c,66
-labelr/annotate.py,sha256=3fJ9FYbcozcOoKuhNtzPHV8sSnp-45FsNnMc8UeBHGU,3503
-labelr/check.py,sha256=3wK6mE0UsKvoBNm0_lyWhCMq7gxkv5r50pvO70damXY,2476
-labelr/config.py,sha256=3RXF_NdkSuHvfVMGMlYmjlw45fU77zQkLX7gmZq7NxM,64
-labelr/dataset_features.py,sha256=ZC9QAUw9oKHqyUPla2h3xQFaRT9sHq8hkPNN4RDDwmo,1257
-labelr/export.py,sha256=gjC2_RJ_yX8zVYXyo1RAgI07iXSgkeqckOTEzSscRXc,17940
-labelr/main.py,sha256=CioMPtaPoGL_5Oxwj8PfalhTyFahMbfp2kd9KdZzm3Y,2258
-labelr/project_config.py,sha256=CIHEcgSOfXb53naHWEBkTDm2V9m3abAu8C54VSzHjAs,1260
-labelr/sample.py,sha256=unu9AQ64FhKPgssuL7gb3qyMd1EQJvMOfqvjdefmWOU,7807
-labelr/types.py,sha256=8CHfLyifF_N94OYDhG-7IcWboOh9o0Z_0LBtQapT8TQ,313
-labelr/utils.py,sha256=e0R15jePWBzRdN8LB6kBSH5Dl_P0MNEtRmeqB9eu5d8,415
-labelr/apps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-labelr/apps/datasets.py,sha256=4PMfKS5c7Zw3-NNRBkFbZidMQUI2RBMcXFYBvWHLz3o,11688
-labelr/apps/projects.py,sha256=HpgqIaPrUQzIR7eOLn4EBbEzXRi7hoWStT4jLMQPcBg,15153
-labelr/apps/train.py,sha256=sI0p3h39LPXhynwl_yMuZnIPlaqlcWSO_81zPC3H3yI,6886
-labelr/apps/users.py,sha256=twQSlpHxE0hrYkgrJpEFbK8lYfWnpJr8vyfLHLtdAUU,909
-labelr-0.7.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-labelr-0.7.0.dist-info/METADATA,sha256=NghQ_6mNj1Dkets_GlOOOyoAVEQqoPBbbJXhysOKAWI,6991
-labelr-0.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-labelr-0.7.0.dist-info/entry_points.txt,sha256=OACukVeR_2z54i8yQuWqqk_jdEHlyTwmTFOFBmxPp1k,43
-labelr-0.7.0.dist-info/top_level.txt,sha256=bjZo50aGZhXIcZYpYOX4sdAQcamxh8nwfEh7A9RD_Ag,7
-labelr-0.7.0.dist-info/RECORD,,