Add: python package

.cog/openapi_schema.json

@@ -0,0 +1 @@
+{"components":{"schemas":{"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"title":"Detail","type":"array"}},"title":"HTTPValidationError","type":"object"},"Input":{"properties":{"text":{"description":"Text to correct","title":"Text","type":"string","x-order":0}},"required":["text"],"title":"Input","type":"object"},"Output":{"title":"Output","type":"string"},"PredictionRequest":{"properties":{"created_at":{"format":"date-time","title":"Created At","type":"string"},"id":{"title":"Id","type":"string"},"input":{"$ref":"#/components/schemas/Input"},"output_file_prefix":{"title":"Output File Prefix","type":"string"},"webhook":{"format":"uri","maxLength":65536,"minLength":1,"title":"Webhook","type":"string"},"webhook_events_filter":{"default":["start","output","logs","completed"],"items":{"$ref":"#/components/schemas/WebhookEvent"},"type":"array"}},"title":"PredictionRequest","type":"object"},"PredictionResponse":{"properties":{"completed_at":{"format":"date-time","title":"Completed At","type":"string"},"created_at":{"format":"date-time","title":"Created At","type":"string"},"error":{"title":"Error","type":"string"},"id":{"title":"Id","type":"string"},"input":{"$ref":"#/components/schemas/Input"},"logs":{"default":"","title":"Logs","type":"string"},"metrics":{"title":"Metrics","type":"object"},"output":{"$ref":"#/components/schemas/Output"},"started_at":{"format":"date-time","title":"Started At","type":"string"},"status":{"$ref":"#/components/schemas/Status"},"version":{"title":"Version","type":"string"}},"title":"PredictionResponse","type":"object"},"Status":{"description":"An enumeration.","enum":["starting","processing","succeeded","canceled","failed"],"title":"Status","type":"string"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"title":"Location","type":"array"},"msg":{"title":"Message","type":"string"},"type":{"title":"Error Type","type":"string"}},"required":["loc","msg","type"],"title":"ValidationError","type":"object"},"WebhookEvent":{"description":"An enumeration.","enum":["start","output","logs","completed"],"title":"WebhookEvent","type":"string"}}},"info":{"title":"Cog","version":"0.1.0"},"openapi":"3.0.2","paths":{"/":{"get":{"operationId":"root__get","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Root  Get"}}},"description":"Successful Response"}},"summary":"Root"}},"/health-check":{"get":{"operationId":"healthcheck_health_check_get","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Healthcheck Health Check Get"}}},"description":"Successful Response"}},"summary":"Healthcheck"}},"/predictions":{"post":{"description":"Run a single prediction on the model","operationId":"predict_predictions_post","parameters":[{"in":"header","name":"prefer","required":false,"schema":{"title":"Prefer","type":"string"}}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/PredictionRequest"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/PredictionResponse"}}},"description":"Successful Response"},"422":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}},"description":"Validation Error"}},"summary":"Predict"}},"/predictions/{prediction_id}":{"put":{"description":"Run a single prediction on the model (idempotent creation).","operationId":"predict_idempotent_predictions__prediction_id__put","parameters":[{"in":"path","name":"prediction_id","required":true,"schema":{"title":"Prediction ID","type":"string"}},{"in":"header","name":"prefer","required":false,"schema":{"title":"Prefer","type":"string"}}],"requestBody":{"content":{"application/json":{"schema":{"allOf":[{"$ref":"#/components/schemas/PredictionRequest"}],"title":"Prediction Request"}}},"required":true},"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/PredictionResponse"}}},"description":"Successful Response"},"422":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}},"description":"Validation Error"}},"summary":"Predict Idempotent"}},"/predictions/{prediction_id}/cancel":{"post":{"description":"Cancel a running prediction","operationId":"cancel_predictions__prediction_id__cancel_post","parameters":[{"in":"path","name":"prediction_id","required":true,"schema":{"title":"Prediction ID","type":"string"}}],"responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Cancel Predictions  Prediction Id  Cancel Post"}}},"description":"Successful Response"},"422":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}},"description":"Validation Error"}},"summary":"Cancel"}},"/shutdown":{"post":{"operationId":"start_shutdown_shutdown_post","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Start Shutdown Shutdown Post"}}},"description":"Successful Response"}},"summary":"Start Shutdown"}}}}

.dockerignore

@@ -0,0 +1,17 @@
+# The .dockerignore file excludes files from the container build process.
+#
+# https://docs.docker.com/engine/reference/builder/#dockerignore-file
+
+# Exclude Git files
+**/.git
+**/.github
+**/.gitignore
+
+# Exclude Python cache files
+__pycache__
+.mypy_cache
+.pytest_cache
+.ruff_cache
+
+# Exclude Python virtual environment
+/venv

.github/workflows/push.yaml

@@ -0,0 +1,54 @@
+name: Push to Replicate
+
+on:
+  # Workflow dispatch allows you to manually trigger the workflow from GitHub.com
+  # Go to your repo, click "Actions", click "Push to Replicate", click "Run workflow"
+  workflow_dispatch:
+    inputs:
+      model_name:
+        description: 'Enter the model name, like "alice/bunny-detector". If unset, this will default to the value of `image` in cog.yaml.'
+  # # Uncomment these lines to trigger the workflow on every push to the main branch
+  # push:
+  #   branches:
+  #     - main
+
+jobs:
+  push_to_replicate:
+    name: Push to Replicate
+
+    # If your model is large, the default GitHub Actions runner may not 
+    # have enough disk space. If you need more space you can set up a 
+    # bigger runner on GitHub.
+    runs-on: ubuntu-latest
+
+    steps:
+      # This action cleans up disk space to make more room for your
+      # model code, weights, etc.
+      - name: Free disk space
+        uses: jlumbroso/[email protected]
+        with:
+          tool-cache: false
+          docker-images: false
+
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      # This action installs Docker buildx and Cog (and optionally CUDA)
+      - name: Setup Cog
+        uses: replicate/setup-cog@v2
+        with:
+          # If you set REPLICATE_API_TOKEN in your GitHub repository secrets,
+          # the action will authenticate with Replicate automatically so you
+          # can push your model
+          token: ${{ secrets.REPLICATE_API_TOKEN }}
+
+      # If you trigger the workflow manually, you can specify the model name.
+      # If you leave it blank (or if the workflow is triggered by a push), the 
+      # model name will be derived from the `image` value in cog.yaml.
+      - name: Push to Replicate
+        run: |
+          if [ -n "${{ inputs.model_name }}" ]; then
+            cog push r8.im/${{ inputs.model_name }}
+          else
+            cog push
+          fi

cog.yaml

@@ -0,0 +1,20 @@
+# Configuration for Cog ⚙️
+# Reference: https://cog.run/yaml
+
+build:
+  # Set to true if your model requires a GPU
+  gpu: false
+
+  # Python version in the form '3.11' or '3.11.4'
+  python_version: "3.11"
+
+  # A list of packages in the format <package-name>==<version>
+  python_packages:
+    - "transformers==4.48.2"
+    - "datasets==3.2.0"
+    - "torch==2.5.1"
+    - "accelerate==1.3.0"
+    - "sentencepiece==0.2.0"
+
+# predict.py defines how predictions are run on your model
+predict: "predict.py:Predictor"

grammarcorrector/README.md

@@ -0,0 +1,23 @@
+# GrammarCorrector
+
+GrammarCorrector is a Python package that uses a remote model hosted on Replicate to correct grammatical errors in text.
+
+## Installation
+
+```bash
+pip install grammarcorrector
+```
+
+## Usage
+
+```bash
+export REPLICATE_API_TOKEN='your_replicate_api_token'
+```
+
+```python
+from grammarcorrector import GrammarCorrector
+
+corrector = GrammarCorrector()
+corrected_text = corrector.correct("This are bad grammar sentence.")
+print(corrected_text)  # Output: "This is a bad grammar sentence."
+```

grammarcorrector/build/lib/grammarcorrector/__init__.py

@@ -0,0 +1,3 @@
+from .corrector import GrammarCorrector
+
+__all__ = ["GrammarCorrector"]

grammarcorrector/build/lib/grammarcorrector/corrector.py

@@ -0,0 +1,12 @@
+import replicate
+
+class GrammarCorrector:
+    def __init__(self):
+        self.model = "aaurelions/t5-grammar-corrector:4502e6d4714acf2152cd417a63792f3a59e983d440b9aa4c8df9b5d84a72931f"
+
+    def correct(self, text):
+        output = replicate.run(
+            self.model,
+            input={"text": text}
+        )
+        return output

grammarcorrector/build/lib/tests/test_corrector.py

@@ -0,0 +1,14 @@
+import unittest
+from grammarcorrector import GrammarCorrector
+
+class TestGrammarCorrector(unittest.TestCase):
+    def setUp(self):
+        self.corrector = GrammarCorrector()
+
+    def test_correction(self):
+        input_text = "This are bad grammar sentence."
+        expected_output = "This is a bad grammar sentence."
+        self.assertEqual(self.corrector.correct(input_text), expected_output)
+
+if __name__ == "__main__":
+    unittest.main()

grammarcorrector/grammarcorrector.egg-info/PKG-INFO

@@ -0,0 +1,46 @@
+Metadata-Version: 2.2
+Name: grammarcorrector
+Version: 0.1.0
+Summary: A Python package for grammar correction using a remote model on Replicate.
+Home-page: https://github.com/aaurelions/grammarcorrector
+Author: D.
+Author-email: [email protected]
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+Requires-Dist: replicate>=1.0.4
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# GrammarCorrector
+
+GrammarCorrector is a Python package that uses a remote model hosted on Replicate to correct grammatical errors in text.
+
+## Installation
+
+```bash
+pip install grammarcorrector
+```
+
+## Usage
+
+```bash
+export REPLICATE_API_TOKEN='your_replicate_api_token'
+```
+
+```python
+from grammarcorrector import GrammarCorrector
+
+corrector = GrammarCorrector()
+corrected_text = corrector.correct("This are bad grammar sentence.")
+print(corrected_text)  # Output: "This is a bad grammar sentence."
+```

grammarcorrector/grammarcorrector.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.md
+setup.py
+grammarcorrector/__init__.py
+grammarcorrector/corrector.py
+grammarcorrector.egg-info/PKG-INFO
+grammarcorrector.egg-info/SOURCES.txt
+grammarcorrector.egg-info/dependency_links.txt
+grammarcorrector.egg-info/requires.txt
+grammarcorrector.egg-info/top_level.txt
+tests/__init__.py
+tests/test_corrector.py

grammarcorrector/grammarcorrector.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

grammarcorrector/grammarcorrector.egg-info/requires.txt

@@ -0,0 +1 @@
+replicate>=1.0.4

grammarcorrector/grammarcorrector.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+grammarcorrector
+tests

grammarcorrector/grammarcorrector/__init__.py

@@ -0,0 +1,3 @@
+from .corrector import GrammarCorrector
+
+__all__ = ["GrammarCorrector"]

grammarcorrector/grammarcorrector/corrector.py

@@ -0,0 +1,12 @@
+import replicate
+
+class GrammarCorrector:
+    def __init__(self):
+        self.model = "aaurelions/t5-grammar-corrector:4502e6d4714acf2152cd417a63792f3a59e983d440b9aa4c8df9b5d84a72931f"
+
+    def correct(self, text):
+        output = replicate.run(
+            self.model,
+            input={"text": text}
+        )
+        return output

grammarcorrector/requirements.txt

@@ -0,0 +1 @@
+replicate>=1.0.4

grammarcorrector/setup.py

@@ -0,0 +1,22 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="grammarcorrector",
+    version="0.1.0",
+    packages=find_packages(),
+    install_requires=[
+        "replicate>=1.0.4",
+    ],
+    author="D.",
+    author_email="[email protected]",
+    description="A Python package for grammar correction using a remote model on Replicate.",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    url="https://github.com/aaurelions/grammarcorrector",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.7',
+)

grammarcorrector/tests/test_corrector.py

@@ -0,0 +1,14 @@
+import unittest
+from grammarcorrector import GrammarCorrector
+
+class TestGrammarCorrector(unittest.TestCase):
+    def setUp(self):
+        self.corrector = GrammarCorrector()
+
+    def test_correction(self):
+        input_text = "This are bad grammar sentence."
+        expected_output = "This is a bad grammar sentence."
+        self.assertEqual(self.corrector.correct(input_text), expected_output)
+
+if __name__ == "__main__":
+    unittest.main()

predict.py

@@ -0,0 +1,16 @@
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+from cog import BasePredictor, Input
+
+class Predictor(BasePredictor):
+    def setup(self):
+        """Load the model and tokenizer into memory to make running multiple predictions efficient"""
+        self.model = T5ForConditionalGeneration.from_pretrained("aaurelions/t5-grammar-corrector")
+        self.tokenizer = T5Tokenizer.from_pretrained("aaurelions/t5-grammar-corrector")
+
+    def predict(self, text: str = Input(description="Text to correct")) -> str:
+        """Run a single prediction on the model"""
+        input_text = "fix grammar: " + text
+        input_ids = self.tokenizer(input_text, return_tensors="pt").input_ids
+        output_ids = self.model.generate(input_ids, max_length=128)
+        corrected_text = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
+        return corrected_text