SDK Revamp with CI/CD & Bug Fixes

.github/ruff.toml

@@ -0,0 +1,16 @@
+# Ruff configuration for CI/CD
+line-length = 100
+target-version = "py37"
+
+[lint]
+select = [
+    "W",  # pycodestyle warnings
+    "F",  # pyflakes
+    "I",  # isort
+    "B",  # flake8-bugbear
+    "C4", # flake8-comprehensions
+    "UP", # pyupgrade
+]
+ignore = [
+    "B008", # do not perform function calls in argument defaults
+]

.github/workflows/ci.yml

@@ -0,0 +1,93 @@
+name: CI
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main, develop ]
+
+jobs:
+  ruff-format-check:
+    name: Ruff Format Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.12'
+
+      - name: Install ruff
+        run: pip install ruff
+
+      - name: Check all files with ruff
+        run: |
+          ruff check jigsawstack/ --config .github/ruff.toml
+          ruff format --check jigsawstack/ --config .github/ruff.toml
+
+  test:
+    name: Test - ${{ matrix.test-file }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        test-file:
+          - test_audio.py
+          - test_classification.py
+          - test_embedding.py
+          - test_file_store.py
+          - test_image_generation.py
+          - test_object_detection.py
+          - test_prediction.py
+          - test_sentiment.py
+          - test_sql.py
+          - test_summary.py
+          - test_translate.py
+          - test_validate.py
+          - test_web.py
+          - test_deep_research.py
+          - test_ai_scrape.py
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install pytest pytest-asyncio pytest-cov python-dotenv
+          pip install -e .
+
+      - name: Run test ${{ matrix.test-file }}
+        env:
+          JIGSAWSTACK_API_KEY: ${{ secrets.JIGSAWSTACK_API_KEY }}
+        run: |
+          pytest tests/${{ matrix.test-file }} -v
+
+  all-checks-passed:
+    name: All Checks Passed
+    needs: [ruff-format-check, test]
+    runs-on: ubuntu-latest
+    if: always()
+    steps:
+      - name: Verify all checks passed
+        run: |
+          echo "Ruff Format Check: ${{ needs.ruff-format-check.result }}"
+          echo "Tests: ${{ needs.test.result }}"
+
+          if [[ "${{ needs.ruff-format-check.result }}" != "success" ]]; then
+            echo "❌ Ruff format check failed"
+            exit 1
+          fi
+
+          if [[ "${{ needs.test.result }}" != "success" ]]; then
+            echo "❌ Tests failed"
+            exit 1
+          fi
+
+          echo "✅ All checks passed successfully!"

README.md

@@ -68,7 +68,7 @@ VOCR:
 
 ```py
 params = {
-    "url": "https://rogilvkqloanxtvjfrkm.supabase.co/storage/v1/object/public/demo/Collabo%201080x842.jpg?t=2024-03-22T09%3A22%3A48.442Z"
+    "url": "https://images.unsplash.com/photo-1542931287-023b922fa89b?q=80&w=2574&auto=format&fit=crop&ixlib=rb-4.1.0&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D?t=2024-03-22T09%3A22%3A48.442Z"
 }
 result = jigsaw.vision.vocr(params)
 ```

jigsawstack/__init__.py

@@ -1,22 +1,23 @@
-from typing import Union, Dict
 import os
-from .audio import Audio, AsyncAudio
-from .vision import Vision, AsyncVision
+from typing import Dict, Union
+
+from .audio import AsyncAudio, Audio
+from .classification import AsyncClassification, Classification
+from .embedding import AsyncEmbedding, Embedding
+from .embedding_v2 import AsyncEmbeddingV2, EmbeddingV2
+from .exceptions import JigsawStackError
+from .image_generation import AsyncImageGeneration, ImageGeneration
+from .prediction import AsyncPrediction, Prediction
+from .prompt_engine import AsyncPromptEngine, PromptEngine
 from .search import Search
-from .prediction import Prediction, AsyncPrediction
+from .sentiment import AsyncSentiment, Sentiment
 from .sql import SQL, AsyncSQL
-from .store import Store, AsyncStore
-from .translate import Translate, AsyncTranslate
-from .web import Web, AsyncWeb
-from .sentiment import Sentiment, AsyncSentiment
-from .validate import Validate, AsyncValidate
-from .summary import Summary, AsyncSummary
-from .embedding import Embedding, AsyncEmbedding
-from .exceptions import JigsawStackError
-from .image_generation import ImageGeneration, AsyncImageGeneration
-from .classification import Classification, AsyncClassification
-from .prompt_engine import PromptEngine, AsyncPromptEngine
-from .embeddingV2 import EmbeddingV2, AsyncEmbeddingV2
+from .store import AsyncStore, Store
+from .summary import AsyncSummary, Summary
+from .translate import AsyncTranslate, Translate
+from .validate import AsyncValidate, Validate
+from .vision import AsyncVision, Vision
+from .web import AsyncWeb, Web
 
 
 class JigsawStack:
@@ -51,7 +52,7 @@ def __init__(
         if api_url is None:
             api_url = os.environ.get("JIGSAWSTACK_API_URL")
         if api_url is None:
-            api_url = f"https://api.jigsawstack.com/"
+            api_url = "https://api.jigsawstack.com/"
 
         self.api_key = api_key
         self.api_url = api_url
@@ -171,7 +172,7 @@ def __init__(
         if api_url is None:
             api_url = os.environ.get("JIGSAWSTACK_API_URL")
         if api_url is None:
-            api_url = f"https://api.jigsawstack.com/"
+            api_url = "https://api.jigsawstack.com/"
 
         self.api_key = api_key
         self.api_url = api_url

jigsawstack/async_request.py

@@ -1,8 +1,11 @@
-from typing import Any, Dict, Generic, List, Union, cast, TypedDict, AsyncGenerator
+import json
+from io import BytesIO
+from typing import Any, AsyncGenerator, Dict, Generic, List, TypedDict, Union, cast
+
 import aiohttp
 from typing_extensions import Literal, TypeVar
+
 from .exceptions import NoContentError, raise_for_code_and_type
-import json
 
 RequestVerb = Literal["get", "post", "put", "patch", "delete"]
 
@@ -22,7 +25,7 @@ def __init__(
         path: str,
         params: Union[Dict[Any, Any], List[Dict[Any, Any]]],
         verb: RequestVerb,
-        headers: Dict[str, str] = {"Content-Type": "application/json"},
+        headers: Dict[str, str] = None,
         data: Union[bytes, None] = None,
         stream: Union[bool, None] = False,
     ):
@@ -32,7 +35,7 @@ def __init__(
         self.api_url = config.get("api_url")
         self.api_key = config.get("api_key")
         self.data = data
-        self.headers = headers
+        self.headers = headers or {"Content-Type": "application/json"}
         self.disable_request_logging = config.get("disable_request_logging")
         self.stream = stream
 
@@ -243,12 +246,27 @@ async def make_request(
             )
         else:
             if data is not None:
+                form_data = aiohttp.FormData()
+                form_data.add_field(
+                    "file",
+                    BytesIO(data),
+                    content_type=headers.get("Content-Type", "application/octet-stream"),
+                    filename="file",
+                )
+
+                if self.params and isinstance(self.params, dict):
+                    form_data.add_field(
+                        "body", json.dumps(self.params), content_type="application/json"
+                    )
+
+                multipart_headers = headers.copy()
+                multipart_headers.pop("Content-Type", None)
+
                 return await session.request(
                     verb,
                     url,
-                    data=data,
-                    params=converted_params,  # Use converted params
-                    headers=headers,
+                    data=form_data,
+                    headers=multipart_headers,
                 )
             else:
                 return await session.request(

jigsawstack/audio.py

@@ -1,13 +1,11 @@
-from typing import Any, Dict, List, cast, Union, Optional, overload
-from typing_extensions import NotRequired, TypedDict
-from .request import Request, RequestConfig
-from .async_request import AsyncRequest, AsyncRequestConfig
+from typing import Any, Dict, List, Optional, Union, cast, overload
+
+from typing_extensions import Literal, NotRequired, TypedDict
+
 from ._config import ClientConfig
-from typing import Any, Dict, List, cast
-from typing_extensions import NotRequired, TypedDict, Literal
-from .custom_typing import SupportedAccents
-from .helpers import build_path
 from ._types import BaseResponse
+from .async_request import AsyncRequest, AsyncRequestConfig
+from .request import Request, RequestConfig
 
 
 class SpeechToTextParams(TypedDict):
@@ -80,22 +78,21 @@ def speech_to_text(
         blob: Union[SpeechToTextParams, bytes],
         options: Optional[SpeechToTextParams] = None,
     ) -> Union[SpeechToTextResponse, SpeechToTextWebhookResponse]:
+        options = options or {}
+        path = "/ai/transcribe"
+        content_type = options.get("content_type", "application/octet-stream")
+        headers = {"Content-Type": content_type}
         if isinstance(
             blob, dict
         ):  # If params is provided as a dict, we assume it's the first argument
             resp = Request(
                 config=self.config,
-                path="/ai/transcribe",
+                path=path,
                 params=cast(Dict[Any, Any], blob),
                 verb="post",
             ).perform_with_content()
             return resp
 
-        options = options or {}
-        path = build_path(base_path="/ai/transcribe", params=options)
-        content_type = options.get("content_type", "application/octet-stream")
-        headers = {"Content-Type": content_type}
-
         resp = Request(
             config=self.config,
             path=path,
@@ -137,20 +134,19 @@ async def speech_to_text(
         blob: Union[SpeechToTextParams, bytes],
         options: Optional[SpeechToTextParams] = None,
     ) -> Union[SpeechToTextResponse, SpeechToTextWebhookResponse]:
+        options = options or {}
+        path = "/ai/transcribe"
+        content_type = options.get("content_type", "application/octet-stream")
+        headers = {"Content-Type": content_type}
         if isinstance(blob, dict):
             resp = await AsyncRequest(
                 config=self.config,
-                path="/ai/transcribe",
+                path=path,
                 params=cast(Dict[Any, Any], blob),
                 verb="post",
             ).perform_with_content()
             return resp
 
-        options = options or {}
-        path = build_path(base_path="/ai/transcribe", params=options)
-        content_type = options.get("content_type", "application/octet-stream")
-        headers = {"Content-Type": content_type}
-
         resp = await AsyncRequest(
             config=self.config,
             path=path,

jigsawstack/classification.py

@@ -1,9 +1,11 @@
 from typing import Any, Dict, List, Union, cast
-from typing_extensions import NotRequired, TypedDict, Literal
-from .request import Request, RequestConfig
-from .async_request import AsyncRequest, AsyncRequestConfig
+
+from typing_extensions import Literal, NotRequired, TypedDict
+
 from ._config import ClientConfig
 from ._types import BaseResponse
+from .async_request import AsyncRequest, AsyncRequestConfig
+from .request import Request, RequestConfig
 
 
 class DatasetItem(TypedDict):