Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[pre-commit.ci] pre-commit autoupdate #5102

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

[pre-commit.ci] pre-commit autoupdate #5102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a7e8ded
[pre-commit.ci] pre-commit autoupdate
pre-commit-ci[bot] Nov 5, 2024
a092c5d
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Nov 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,23 +1,23 @@
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.6.0
rev: v5.0.0
hooks:
- id: check-yaml
exclude: argilla/mkdocs.yml|examples/deployments/k8s
- id: end-of-file-fixer
exclude_types: [text, jupyter]
- id: trailing-whitespace

- repo: https://github.com/charliermarsh/ruff-pre-commit
rev: v0.4.8
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.7.2
hooks:
- id: ruff-format

##############################################################################
# argilla specific hooks
##############################################################################
- repo: https://github.com/charliermarsh/ruff-pre-commit
rev: v0.4.8
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.7.2
hooks:
- id: ruff
files: 'argilla/src/.*\.py$'
Expand All @@ -35,7 +35,7 @@ repos:
- argilla/LICENSE_HEADER
- --fuzzy-match-generates-todo
- repo: https://github.com/kynan/nbstripout
rev: 0.7.1
rev: 0.8.0
hooks:
- id: nbstripout
files: '^argilla/.*\.ipynb$'
Expand All @@ -52,8 +52,8 @@ repos:
##############################################################################
# argilla-server specific hooks
##############################################################################
- repo: https://github.com/charliermarsh/ruff-pre-commit
rev: v0.4.8
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.7.2
hooks:
- id: ruff
files: 'argila-server/src/.*\.py$'
Expand Down
7 changes: 2 additions & 5 deletions argilla/docs/community/integrations/llamaindex_rag_github.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,8 +202,7 @@
" \".svg\",\n",
" \".ico\",\n",
" \".json\",\n",
" \".ipynb\", # Erase this line if you want to include notebooks\n",
"\n",
" \".ipynb\", # Erase this line if you want to include notebooks\n",
" ],\n",
" GithubRepositoryReader.FilterType.EXCLUDE,\n",
" ),\n",
Expand Down Expand Up @@ -231,9 +230,7 @@
"outputs": [],
"source": [
"# LLM settings\n",
"Settings.llm = OpenAI(\n",
" model=\"gpt-3.5-turbo\", temperature=0.8, openai_api_key=openai_api_key\n",
")\n",
"Settings.llm = OpenAI(model=\"gpt-3.5-turbo\", temperature=0.8, openai_api_key=openai_api_key)\n",
"\n",
"# Load the data and create the index\n",
"index = VectorStoreIndex.from_documents(documents)\n",
Expand Down
53 changes: 26 additions & 27 deletions argilla/docs/tutorials/image_classification.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,13 +93,7 @@
"from PIL import Image\n",
"\n",
"from datasets import load_dataset, Dataset, load_metric\n",
"from transformers import (\n",
" AutoImageProcessor,\n",
" AutoModelForImageClassification,\n",
" pipeline,\n",
" Trainer,\n",
" TrainingArguments\n",
")\n",
"from transformers import AutoImageProcessor, AutoModelForImageClassification, pipeline, Trainer, TrainingArguments\n",
"\n",
"import argilla as rg"
]
Expand Down Expand Up @@ -182,7 +176,7 @@
" title=\"What digit do you see on the image?\",\n",
" labels=labels,\n",
" )\n",
" ]\n",
" ],\n",
")"
]
},
Expand Down Expand Up @@ -246,7 +240,7 @@
"n_rows = 100\n",
"\n",
"hf_dataset = load_dataset(\"ylecun/mnist\", streaming=True)\n",
"dataset_rows = [row for _,row in zip(range(n_rows), hf_dataset[\"train\"])]\n",
"dataset_rows = [row for _, row in zip(range(n_rows), hf_dataset[\"train\"])]\n",
"hf_dataset = Dataset.from_list(dataset_rows)\n",
"\n",
"hf_dataset"
Expand Down Expand Up @@ -525,7 +519,8 @@
],
"source": [
"def greyscale_to_rgb(img) -> Image:\n",
" return Image.merge('RGB', (img, img, img))\n",
" return Image.merge(\"RGB\", (img, img, img))\n",
"\n",
"\n",
"submitted_image_rgb = [\n",
" {\n",
Expand Down Expand Up @@ -556,7 +551,7 @@
"\n",
"submitted_image_rgb_processed = [\n",
" {\n",
" \"pixel_values\": processor(sample[\"image\"], return_tensors='pt')[\"pixel_values\"],\n",
" \"pixel_values\": processor(sample[\"image\"], return_tensors=\"pt\")[\"pixel_values\"],\n",
" \"label\": sample[\"label\"],\n",
" }\n",
" for sample in submitted_image_rgb\n",
Expand Down Expand Up @@ -624,8 +619,8 @@
"source": [
"def collate_fn(batch):\n",
" return {\n",
" 'pixel_values': torch.stack([torch.tensor(x['pixel_values'][0]) for x in batch]),\n",
" 'labels': torch.tensor([int(x['label']) for x in batch])\n",
" \"pixel_values\": torch.stack([torch.tensor(x[\"pixel_values\"][0]) for x in batch]),\n",
" \"labels\": torch.tensor([int(x[\"label\"]) for x in batch]),\n",
" }"
]
},
Expand All @@ -643,6 +638,8 @@
"outputs": [],
"source": [
"metric = load_metric(\"accuracy\", trust_remote_code=True)\n",
"\n",
"\n",
"def compute_metrics(p):\n",
" return metric.compute(predictions=np.argmax(p.predictions, axis=1), references=p.label_ids)"
]
Expand All @@ -664,7 +661,7 @@
" checkpoint,\n",
" num_labels=len(labels),\n",
" id2label={int(i): int(c) for i, c in enumerate(labels)},\n",
" label2id={int(c): int(i) for i, c in enumerate(labels)}\n",
" label2id={int(c): int(i) for i, c in enumerate(labels)},\n",
")\n",
"model.config"
]
Expand Down Expand Up @@ -698,19 +695,19 @@
],
"source": [
"training_args = TrainingArguments(\n",
" output_dir=\"./image-classifier\",\n",
" per_device_train_batch_size=16,\n",
" eval_strategy=\"steps\",\n",
" num_train_epochs=1,\n",
" fp16=False, # True if you have a GPU with mixed precision support\n",
" save_steps=100,\n",
" eval_steps=100,\n",
" logging_steps=10,\n",
" learning_rate=2e-4,\n",
" save_total_limit=2,\n",
" remove_unused_columns=True,\n",
" push_to_hub=False,\n",
" load_best_model_at_end=True,\n",
" output_dir=\"./image-classifier\",\n",
" per_device_train_batch_size=16,\n",
" eval_strategy=\"steps\",\n",
" num_train_epochs=1,\n",
" fp16=False, # True if you have a GPU with mixed precision support\n",
" save_steps=100,\n",
" eval_steps=100,\n",
" logging_steps=10,\n",
" learning_rate=2e-4,\n",
" save_total_limit=2,\n",
" remove_unused_columns=True,\n",
" push_to_hub=False,\n",
" load_best_model_at_end=True,\n",
")\n",
"\n",
"trainer = Trainer(\n",
Expand Down Expand Up @@ -745,12 +742,14 @@
"source": [
"pipe = pipeline(\"image-classification\", model=model, image_processor=processor)\n",
"\n",
"\n",
"def run_inference(batch):\n",
" predictions = pipe(batch[\"image\"])\n",
" batch[\"image_label\"] = [prediction[0][\"label\"] for prediction in predictions]\n",
" batch[\"score\"] = [prediction[0][\"score\"] for prediction in predictions]\n",
" return batch\n",
"\n",
"\n",
"hf_dataset = hf_dataset.map(run_inference, batched=True)"
]
},
Expand Down
34 changes: 19 additions & 15 deletions argilla/docs/tutorials/image_preference.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,11 +191,10 @@
" metadata=[\n",
" rg.FloatMetadataProperty(name=\"toxicity\", title=\"Toxicity score\"),\n",
" rg.FloatMetadataProperty(name=\"identity_attack\", title=\"Identity attack score\"),\n",
"\n",
" ],\n",
" vectors=[\n",
" rg.VectorField(name=\"original_caption_vector\", dimensions=384),\n",
" ]\n",
" ],\n",
")"
]
},
Expand Down Expand Up @@ -254,7 +253,7 @@
"n_rows = 25\n",
"\n",
"hf_dataset = load_dataset(\"tomg-group-umd/pixelprose\", streaming=True)\n",
"dataset_rows = [row for _,row in zip(range(n_rows), hf_dataset[\"train\"])]\n",
"dataset_rows = [row for _, row in zip(range(n_rows), hf_dataset[\"train\"])]\n",
"hf_dataset = Dataset.from_list(dataset_rows)\n",
"\n",
"hf_dataset"
Expand Down Expand Up @@ -341,8 +340,7 @@
}
],
"source": [
"hf_dataset = hf_dataset.filter(\n",
" lambda x: any([x[\"url\"].endswith(extension) for extension in [\".jpg\", \".png\", \".jpeg\"]]))\n",
"hf_dataset = hf_dataset.filter(lambda x: any([x[\"url\"].endswith(extension) for extension in [\".jpg\", \".png\", \".jpeg\"]]))\n",
"\n",
"hf_dataset"
]
Expand Down Expand Up @@ -380,6 +378,7 @@
"API_URL = \"https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-schnell\"\n",
"headers = {\"Authorization\": f\"Bearer {os.getenv('HF_TOKEN')}\"}\n",
"\n",
"\n",
"def query(payload):\n",
" response = requests.post(API_URL, headers=headers, json=payload)\n",
" if response.status_code == 200:\n",
Expand All @@ -391,9 +390,8 @@
" image = query(payload)\n",
" return image\n",
"\n",
"query({\n",
"\t\"inputs\": \"Astronaut riding a horse\"\n",
"})"
"\n",
"query({\"inputs\": \"Astronaut riding a horse\"})"
]
},
{
Expand Down Expand Up @@ -426,9 +424,10 @@
"def generate_image(row):\n",
" caption = row[\"original_caption\"]\n",
" row[\"image_1\"] = query({\"inputs\": caption})\n",
" row[\"image_2\"] = query({\"inputs\": caption + \" \"}) # space to avoid caching and getting the same image\n",
" row[\"image_2\"] = query({\"inputs\": caption + \" \"}) # space to avoid caching and getting the same image\n",
" return row\n",
" \n",
"\n",
"\n",
"hf_dataset_with_images = hf_dataset.map(generate_image, batched=False)\n",
"\n",
"hf_dataset_with_images"
Expand All @@ -451,11 +450,13 @@
"source": [
"model = SentenceTransformer(\"TaylorAI/bge-micro-v2\")\n",
"\n",
"\n",
"def encode_questions(batch):\n",
" vectors_as_numpy = model.encode(batch[\"original_caption\"])\n",
" batch[\"original_caption_vector\"] = [x.tolist() for x in vectors_as_numpy]\n",
" return batch\n",
"\n",
"\n",
"hf_dataset_with_images_vectors = hf_dataset_with_images.map(encode_questions, batched=True)"
]
},
Expand All @@ -474,11 +475,14 @@
"metadata": {},
"outputs": [],
"source": [
"dataset.records.log(records=hf_dataset_with_images_vectors, mapping={\n",
" \"key\": \"id\",\n",
" \"original_caption\": \"caption\",\n",
" \"url\": \"image_original\",\n",
"})"
"dataset.records.log(\n",
" records=hf_dataset_with_images_vectors,\n",
" mapping={\n",
" \"key\": \"id\",\n",
" \"original_caption\": \"caption\",\n",
" \"url\": \"image_original\",\n",
" },\n",
")"
]
},
{
Expand Down
8 changes: 2 additions & 6 deletions argilla/docs/tutorials/token_classification.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,9 +309,7 @@
"source": [
"def predict_gliner(model, text, labels, threshold):\n",
" entities = model.predict_entities(text, labels, threshold)\n",
" return [\n",
" {k: v for k, v in ent.items() if k not in {\"score\", \"text\"}} for ent in entities\n",
" ]"
" return [{k: v for k, v in ent.items() if k not in {\"score\", \"text\"}} for ent in entities]"
]
},
{
Expand All @@ -330,9 +328,7 @@
"data = dataset.records.to_list(flatten=True)\n",
"updated_data = [\n",
" {\n",
" \"span_label\": predict_gliner(\n",
" model=gliner_model, text=sample[\"text\"], labels=labels, threshold=0.70\n",
" ),\n",
" \"span_label\": predict_gliner(model=gliner_model, text=sample[\"text\"], labels=labels, threshold=0.70),\n",
" \"id\": sample[\"id\"],\n",
" }\n",
" for sample in data\n",
Expand Down
Loading