chunkr-ai 0.1.0__py3-none-any.whl → 0.1.0a1__py3-none-any.whl

chunkr_ai/api/task_response.py

@@ -1,208 +0,0 @@
-from datetime import datetime
-from typing import Optional, cast, Awaitable, Union
-from pydantic import BaseModel, PrivateAttr
-import asyncio
-import json
-import os
-import httpx
-
-from .configuration import Configuration, OutputConfiguration, OutputResponse, Status
-from .protocol import ChunkrClientProtocol
-from .misc import prepare_upload_data
-from .decorators import anywhere, require_task, retry_on_429
-
-class TaskResponse(BaseModel):
-    configuration: OutputConfiguration
-    created_at: datetime
-    expires_at: Optional[datetime] = None
-    finished_at: Optional[datetime] = None
-    message: Optional[str] = None
-    output: Optional[OutputResponse] = None
-    started_at: Optional[datetime] = None
-    status: Status
-    task_id: str
-    task_url: Optional[str] = None
-    include_chunks: bool = False
-    _base64_urls: bool = False
-    _client: Optional[ChunkrClientProtocol] = PrivateAttr(default=None)
-
-    def with_client(self, client: ChunkrClientProtocol, include_chunks: bool = False, base64_urls: bool = False) -> "TaskResponse":
-        self._client = client
-        self.include_chunks = include_chunks
-        self._base64_urls = base64_urls
-        return self
-
-    def _check_status(self) -> Optional["TaskResponse"]:
-        """Helper method to check task status and handle completion/failure"""
-        if self.status == "Failed":
-            if getattr(self._client, 'raise_on_failure', True):
-                raise ValueError(self.message)
-            return self
-        if self.status not in ("Starting", "Processing"):
-            return self
-        return None
-
-    @require_task()
-    async def _poll_request(self) -> dict:
-        try:
-            if not self._client:
-                raise ValueError("Chunkr client protocol is not initialized")
-            if not self._client._client or self._client._client.is_closed:
-                raise ValueError("httpx client is not open")
-            assert self.task_url is not None 
-            r = await self._client._client.get(
-                self.task_url, headers=self._client._headers()
-            )
-            r.raise_for_status()
-            return r.json()
-        except (ConnectionError, TimeoutError, OSError, 
-                httpx.ReadTimeout, httpx.ConnectTimeout, 
-                httpx.WriteTimeout, httpx.PoolTimeout,
-                httpx.ConnectError, httpx.ReadError, 
-                httpx.NetworkError) as e:
-            print(f"Connection error while polling the task: {str(e)}\nretrying...")
-            await asyncio.sleep(0.5)
-            return await self._poll_request() 
-        except Exception as e:
-            raise e
-
-    @anywhere()
-    async def poll(self) -> "TaskResponse":
-        """Poll the task for completion."""
-        while True:
-            j = await self._poll_request()
-            if not self._client:
-                raise ValueError("Chunkr client protocol is not initialized")
-            updated = TaskResponse(**j).with_client(self._client)
-            self.__dict__.update(updated.__dict__)
-            if res := self._check_status():
-                return res
-            await asyncio.sleep(0.5)
-
-    @anywhere()
-    @require_task()
-    @retry_on_429()
-    async def update(self, config: Configuration) -> "TaskResponse":
-        """Update the task configuration."""
-        data = await prepare_upload_data(None, None, config)
-        if not self._client:
-            raise ValueError("Chunkr client protocol is not initialized")
-        if not self._client._client or self._client._client.is_closed:
-            raise ValueError("httpx client is not open")
-        assert self.task_url is not None
-        r = await self._client._client.patch(
-            f"{self.task_url}/parse",
-            json=data,
-            headers=self._client._headers()
-        )
-        r.raise_for_status()
-        updated = TaskResponse(**r.json()).with_client(self._client)
-        self.__dict__.update(updated.__dict__)
-        return cast(TaskResponse, self.poll())
-
-    @anywhere()
-    @require_task()
-    async def delete(self) -> "TaskResponse":
-        """Delete the task."""
-        if not self._client:
-            raise ValueError("Chunkr client protocol is not initialized")
-        if not self._client._client or self._client._client.is_closed:
-            raise ValueError("httpx client is not open")
-        assert self.task_url is not None
-        r = await self._client._client.delete(
-            self.task_url, headers=self._client._headers()
-        )
-        r.raise_for_status()
-        return self
-
-    @anywhere()
-    @require_task()
-    async def cancel(self) -> "TaskResponse":
-        """Cancel the task."""
-        if not self._client:
-            raise ValueError("Chunkr client protocol is not initialized")
-        if not self._client._client or self._client._client.is_closed:
-            raise ValueError("httpx client is not open")
-        assert self.task_url is not None
-        r = await self._client._client.get(
-            f"{self.task_url}/cancel", headers=self._client._headers()
-        )
-        r.raise_for_status()
-        return cast(TaskResponse, self.poll())
-
-    def _write_to_file(self, content: Union[str, dict], output_file: Optional[str], is_json: bool = False) -> None:
-        """Helper method to write content to a file
-        
-        Args:
-            content: Content to write (string or dict for JSON)
-            output_file: Path to save the content
-            is_json: Whether the content should be written as JSON
-        """
-        class DateTimeEncoder(json.JSONEncoder):
-            def default(self, obj):
-                if isinstance(obj, datetime):
-                    return obj.isoformat()
-                return super().default(obj)
-        if output_file:
-            directory = os.path.dirname(output_file)
-            if directory:
-                os.makedirs(directory, exist_ok=True)
-            with open(output_file, "w", encoding="utf-8") as f:
-                if is_json:
-                    json.dump(content, f, cls=DateTimeEncoder, indent=2)
-                else:
-                    if isinstance(content, str):
-                        f.write(content)
-                    else:
-                        raise ValueError("Content is not a string")
-
-    def html(self, output_file: Optional[str] = None) -> str:
-        """Get the full HTML of the task
-        
-        Args:
-            output_file (str, optional): Path to save the HTML content. Defaults to None.
-        """
-        content = self._get_content("html")
-        self._write_to_file(content, output_file)
-        return content
-
-    def markdown(self, output_file: Optional[str] = None) -> str:
-        """Get the full markdown of the task
-        
-        Args:
-            output_file (str, optional): Path to save the markdown content. Defaults to None.
-        """
-        content = self._get_content("markdown", separator="\n\n")
-        self._write_to_file(content, output_file)
-        return content
-
-    def content(self, output_file: Optional[str] = None) -> str:
-        """Get the full content of the task
-        
-        Args:
-            output_file (str, optional): Path to save the content. Defaults to None.
-        """
-        content = self._get_content("content")
-        self._write_to_file(content, output_file)
-        return content
-    
-    def json(self, output_file: Optional[str] = None) -> dict:
-        """Get the full task data as JSON
-        
-        Args:
-            output_file (str, optional): Path to save the task data as JSON. Defaults to None.
-        """
-        data = self.model_dump()
-        self._write_to_file(data, output_file, is_json=True)
-        return data
-
-    def _get_content(self, t: str, separator: str = "\n") -> str:
-        if not self.output:
-            return ""
-        parts = []
-        for c in self.output.chunks:
-            for s in c.segments:
-                v = getattr(s, t)
-                if v:
-                    parts.append(v)
-        return separator.join(parts)

chunkr_ai/models.py

@@ -1,55 +0,0 @@
-from .api.configuration import (
-    BoundingBox,
-    Chunk,
-    ChunkProcessing,
-    Configuration,
-    CroppingStrategy,
-    EmbedSource,
-    ErrorHandlingStrategy,
-    FallbackStrategy,
-    GenerationStrategy,
-    GenerationConfig,
-    LlmProcessing,
-    Model,
-    OCRResult,
-    OcrStrategy,
-    OutputResponse,
-    Segment,
-    SegmentFormat,
-    SegmentProcessing,
-    SegmentType,
-    SegmentationStrategy,
-    Status,
-    Pipeline,
-    Tokenizer,
-    TokenizerType,
-)
-from .api.task_response import TaskResponse
-
-__all__ = [
-    "BoundingBox",
-    "Chunk",
-    "ChunkProcessing",
-    "Configuration",
-    "CroppingStrategy",
-    "EmbedSource",
-    "ErrorHandlingStrategy",
-    "FallbackStrategy",
-    "GenerationConfig",
-    "GenerationStrategy",
-    "LlmProcessing",
-    "Model",
-    "OCRResult",
-    "OcrStrategy",
-    "OutputResponse",
-    "Segment",
-    "SegmentFormat",
-    "SegmentProcessing",
-    "SegmentType",
-    "SegmentationStrategy",
-    "Status",
-    "TaskResponse",
-    "Pipeline",
-    "Tokenizer",
-    "TokenizerType",
-]

chunkr_ai-0.1.0.dist-info/METADATA

@@ -1,268 +0,0 @@
-Metadata-Version: 2.4
-Name: chunkr-ai
-Version: 0.1.0
-Summary: Python client for Chunkr: open source document intelligence
-Author-email: Ishaan Kapoor <ishaan@lumina.sh>
-License: MIT License
-        
-        Copyright (c) 2025 Lumina AI INC
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy
-        of this software and associated documentation files (the "Software"), to deal
-        in the Software without restriction, including without limitation the rights
-        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-        copies of the Software, and to permit persons to whom the Software is
-        furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all
-        copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-        SOFTWARE.
-Project-URL: Homepage, https://chunkr.ai
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: httpx>=0.25.0
-Requires-Dist: nest-asyncio>=1.6.0
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: python-dotenv>=0.19.0
-Provides-Extra: test
-Requires-Dist: pytest>=7.0.0; extra == "test"
-Requires-Dist: pytest-xdist>=3.0.0; extra == "test"
-Requires-Dist: pytest-asyncio>=0.21.0; extra == "test"
-Requires-Dist: ruff>=0.9.3; extra == "test"
-Dynamic: license-file
-
-# Chunkr Python Client
-
-This provides a simple interface to interact with the Chunkr API.
-
-## Getting Started
-
-You can get an API key from [Chunkr](https://chunkr.ai) or deploy your own Chunkr instance. For self-hosted deployment options, check out our [deployment guide](https://github.com/lumina-ai-inc/chunkr/tree/main?tab=readme-ov-file#self-hosted-deployment-options).
-
-For more information about the API and its capabilities, visit the [Chunkr API docs](https://docs.chunkr.ai).
-
-## Installation
-
-```bash
-pip install chunkr-ai
-```
-
-## Usage
-
-The `Chunkr` client works seamlessly in both synchronous and asynchronous contexts.
-
-### Synchronous Usage
-
-```python
-from chunkr_ai import Chunkr
-
-# Initialize client
-chunkr = Chunkr()
-
-# Upload a file and wait for processing
-task = chunkr.upload("document.pdf")
-print(task.task_id)
-
-# Create task without waiting
-task = chunkr.create_task("document.pdf")
-result = task.poll()  # Check status when needed
-
-# Clean up when done
-chunkr.close()
-```
-
-### Asynchronous Usage
-
-```python
-from chunkr_ai import Chunkr
-import asyncio
-
-async def process_document():
-    # Initialize client
-    chunkr = Chunkr()
-
-    try:
-        # Upload a file and wait for processing
-        task = await chunkr.upload("document.pdf")
-        print(task.task_id)
-
-        # Create task without waiting
-        task = await chunkr.create_task("document.pdf")
-        result = await task.poll()  # Check status when needed
-    finally:
-        await chunkr.close()
-
-# Run the async function
-asyncio.run(process_document())
-```
-
-### Concurrent Processing
-
-The client supports both async concurrency and multiprocessing:
-
-```python
-# Async concurrency
-async def process_multiple():
-    chunkr = Chunkr()
-    try:
-        tasks = [
-            chunkr.upload("doc1.pdf"),
-            chunkr.upload("doc2.pdf"),
-            chunkr.upload("doc3.pdf")
-        ]
-        results = await asyncio.gather(*tasks)
-    finally:
-        await chunkr.close()
-
-# Multiprocessing
-from multiprocessing import Pool
-
-def process_file(path):
-    chunkr = Chunkr()
-    try:
-        return chunkr.upload(path)
-    finally:
-        chunkr.close()
-
-with Pool(processes=3) as pool:
-    results = pool.map(process_file, ["doc1.pdf", "doc2.pdf", "doc3.pdf"])
-```
-
-### Input Types
-
-The client supports various input types:
-
-```python
-# File path
-chunkr.upload("document.pdf")
-
-# Opened file
-with open("document.pdf", "rb") as f:
-    chunkr.upload(f)
-
-# PIL Image
-from PIL import Image
-img = Image.open("photo.jpg")
-chunkr.upload(img)
-```
-
-### Configuration
-
-You can customize the processing behavior by passing a `Configuration` object:
-
-```python
-from chunkr_ai.models import (
-    Configuration, 
-    OcrStrategy, 
-    SegmentationStrategy, 
-    GenerationStrategy
-)
-
-config = Configuration(
-    ocr_strategy=OcrStrategy.AUTO,
-    segmentation_strategy=SegmentationStrategy.LAYOUT_ANALYSIS,
-    high_resolution=True,
-    expires_in=3600,  # seconds
-)
-
-# Works in both sync and async contexts
-task = chunkr.upload("document.pdf", config)  # sync
-task = await chunkr.upload("document.pdf", config)  # async
-```
-
-#### Available Configuration Examples
-
-- **Chunk Processing**
-  ```python
-  from chunkr_ai.models import ChunkProcessing
-  config = Configuration(
-      chunk_processing=ChunkProcessing(target_length=1024)
-  )
-  ```
-- **Expires In**
-  ```python
-  config = Configuration(expires_in=3600)
-  ```
-
-- **High Resolution**
-  ```python
-  config = Configuration(high_resolution=True)
-  ```
-
-- **JSON Schema**
-  ```python
-  config = Configuration(json_schema=JsonSchema(
-      title="Sales Data",
-      properties=[
-          Property(name="Person with highest sales", prop_type="string", description="The person with the highest sales"),
-          Property(name="Person with lowest sales", prop_type="string", description="The person with the lowest sales"),
-      ]
-  ))
-  ```
-
-- **OCR Strategy**
-  ```python
-  config = Configuration(ocr_strategy=OcrStrategy.AUTO)
-  ```
-
-- **Segment Processing**
-  ```python
-  from chunkr_ai.models import SegmentProcessing, GenerationConfig, GenerationStrategy
-  config = Configuration(
-      segment_processing=SegmentProcessing(
-          page=GenerationConfig(
-              html=GenerationStrategy.LLM,
-              markdown=GenerationStrategy.LLM
-          )
-      )
-  )
-  ```
-
-- **Segmentation Strategy**
-  ```python
-  config = Configuration(
-      segmentation_strategy=SegmentationStrategy.LAYOUT_ANALYSIS  # or SegmentationStrategy.PAGE
-  )
-  ```
-
-## Environment Setup
-
-You can provide your API key and URL in several ways:
-1. Environment variables: `CHUNKR_API_KEY` and `CHUNKR_URL`
-2. `.env` file
-3. Direct initialization:
-```python
-chunkr = Chunkr(
-    api_key="your-api-key",
-    url="https://api.chunkr.ai"
-)
-```
-
-## Resource Management
-
-It's recommended to properly close the client when you're done:
-
-```python
-# Sync context
-chunkr = Chunkr()
-try:
-    result = chunkr.upload("document.pdf")
-finally:
-    chunkr.close()
-
-# Async context
-async def process():
-    chunkr = Chunkr()
-    try:
-        result = await chunkr.upload("document.pdf")
-    finally:
-        await chunkr.close()
-```

chunkr_ai-0.1.0.dist-info/RECORD

@@ -1,16 +0,0 @@
-chunkr_ai/__init__.py,sha256=6KpYv2lmD6S5z2kc9pqwuLP5VDHmOuu2qDZArUIhb1s,53
-chunkr_ai/models.py,sha256=1q4l7fSXU7cVfx2ZUcmc5EZ4K0AeUhCbvY9yaBbXL8E,1046
-chunkr_ai/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chunkr_ai/api/auth.py,sha256=0RSNFPvHt4Nrg8qtP2xvA2KbR0J_KUe1B_tKynbq9Fc,436
-chunkr_ai/api/chunkr.py,sha256=uSNYtB_mcs4-QRKsX7wZb8yv6ayXgRrJSDNZ-EbAyvc,3857
-chunkr_ai/api/chunkr_base.py,sha256=8roSPoCADmaXM2r7zz2iHfZzIcY9NopOfa4j-dfk8RA,6310
-chunkr_ai/api/configuration.py,sha256=MVAxKe8vTSUMy0AHOPWyJEOgmIL-rPTsAQ8Z83gGXew,10287
-chunkr_ai/api/decorators.py,sha256=w1l_ZEkl99C-BO3qRTbi74sYwHDFspB1Bjt1Arv9lPc,4384
-chunkr_ai/api/misc.py,sha256=AaGLxZlMzNgVPwErskDRKc2UVGkC0JwxLXU-enPwzA0,5354
-chunkr_ai/api/protocol.py,sha256=LjPrYSq52m1afIlAo0yVGXlGZxPRh8J6g7S4PAit3Zo,388
-chunkr_ai/api/task_response.py,sha256=VYa62E08VlZUyjn2YslnY4cohdK9e53HbEzsaYIXKXM,8028
-chunkr_ai-0.1.0.dist-info/licenses/LICENSE,sha256=w3R12yNDyZpMiy2lxy_hvNbsldC75ww79sF0u11rkho,1069
-chunkr_ai-0.1.0.dist-info/METADATA,sha256=nRApqY3sX17_8fqSwfgYUH7Sy4Ahg5ybpxU9ZTXvdH4,7052
-chunkr_ai-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-chunkr_ai-0.1.0.dist-info/top_level.txt,sha256=0IZY7PZIiS8bw5r4NUQRUQ-ATi-L_3vLQVq3ZLouOW8,10
-chunkr_ai-0.1.0.dist-info/RECORD,,

chunkr_ai-0.1.0.dist-info/licenses/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2025 Lumina AI INC
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

chunkr_ai-0.1.0.dist-info/top_level.txt

@@ -1 +0,0 @@
-chunkr_ai