retab 0.0.42__tar.gz → 0.0.43__tar.gz

{retab-0.0.42 → retab-0.0.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: retab
-Version: 0.0.42
+Version: 0.0.43
 Summary: Retab official python library
 Home-page: https://github.com/Retab-dev/retab
 Author: Retab
@@ -61,7 +61,7 @@ Made with love by the team at [Retab](https://retab.com) 🤍.
 
 ### What is Retab?
 
-Retab solves all the major challenges in document processing with LLMs:
+Retab solves all the major challenges in document processing with Large Language Models:
 
 1. **Universal Document Preprocessing**: Convert any file type (PDFs, Excel, emails, etc.) into LLM-ready format without writing custom parsers
 2. **Structured, Schema-driven Extraction**: Get consistent, reliable outputs using schema-based prompt engineering
@@ -90,7 +90,7 @@ Many people haven't yet realized how powerful LLMs have become at document proce
 
 ## Code examples
 
-## You can check our Github repository to see code examples: [python examples](https://github.com/Retab-dev/retab/tree/main/examples) and [jupyter notebooks](https://github.com/Retab-dev/retab-nodejs/tree/main/notebooks).
+You can check our Github repository to see code examples: [python examples](https://github.com/Retab-dev/retab/tree/main/examples) and [jupyter notebooks](https://github.com/Retab-dev/retab-nodejs/tree/main/notebooks).
 
 ## Community
 
@@ -112,8 +112,6 @@ We share our roadmap publicly on [Github](https://github.com/Retab-dev/retab)
 Among the features we're working on:
 
 * [ ] Node.js SDK
-* [ ] Low-level speed optimizations for Evals Frontend
 * [ ] Schema optimization autopilot
 * [ ] Sources API
-* [ ] Parse API for RAG
 

{retab-0.0.42 → retab-0.0.43}/README.md

@@ -18,7 +18,7 @@ Made with love by the team at [Retab](https://retab.com) 🤍.
 
 ### What is Retab?
 
-Retab solves all the major challenges in document processing with LLMs:
+Retab solves all the major challenges in document processing with Large Language Models:
 
 1. **Universal Document Preprocessing**: Convert any file type (PDFs, Excel, emails, etc.) into LLM-ready format without writing custom parsers
 2. **Structured, Schema-driven Extraction**: Get consistent, reliable outputs using schema-based prompt engineering
@@ -47,7 +47,7 @@ Many people haven't yet realized how powerful LLMs have become at document proce
 
 ## Code examples
 
-## You can check our Github repository to see code examples: [python examples](https://github.com/Retab-dev/retab/tree/main/examples) and [jupyter notebooks](https://github.com/Retab-dev/retab-nodejs/tree/main/notebooks).
+You can check our Github repository to see code examples: [python examples](https://github.com/Retab-dev/retab/tree/main/examples) and [jupyter notebooks](https://github.com/Retab-dev/retab-nodejs/tree/main/notebooks).
 
 ## Community
 
@@ -69,8 +69,6 @@ We share our roadmap publicly on [Github](https://github.com/Retab-dev/retab)
 Among the features we're working on:
 
 * [ ] Node.js SDK
-* [ ] Low-level speed optimizations for Evals Frontend
 * [ ] Schema optimization autopilot
 * [ ] Sources API
-* [ ] Parse API for RAG
 

{retab-0.0.42 → retab-0.0.43}/retab/__init__.py

@@ -1,4 +1,5 @@
 from .client import AsyncRetab, Retab
 from .types.schemas.object import Schema
+from . import utils
 
-__all__ = ["Retab", "AsyncRetab", "Schema"]
+__all__ = ["Retab", "AsyncRetab", "Schema", "utils"]

{retab-0.0.42 → retab-0.0.43}/retab/client.py

@@ -7,10 +7,9 @@ import backoff
 import backoff.types
 import httpx
 import truststore
-from pydantic_core import PydanticUndefined
 
-from .resources import consensus, documents, evals, files, finetuning, models, processors, schemas, secrets, usage, evaluations
-from .types.standards import PreparedRequest
+from .resources import consensus, documents, files, finetuning, models, processors, schemas, secrets, usage, evaluations
+from .types.standards import PreparedRequest, FieldUnset
 
 
 class MaxRetriesExceeded(Exception):
@@ -43,20 +42,15 @@ class BaseRetab:
         ValueError: If no API key is provided through arguments or environment variables
     """
 
-    #   claude_api_key (str, optional): Claude API key. Will look for CLAUDE_API_KEY env variable if not provided
-    #   xai_api_key (str, optional): XAI API key. Will look for XAI_API_KEY env variable if not provided
-    #   gemini_api_key (str, optional): Gemini API key. Will look for GEMINI_API_KEY env variable if not provided
-
     def __init__(
         self,
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         timeout: float = 240.0,
         max_retries: int = 3,
-        openai_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        gemini_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        # claude_api_key: Optional[str] = PydanticUndefined,   # type: ignore[assignment]
-        xai_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
+        openai_api_key: Optional[str] = FieldUnset,
+        gemini_api_key: Optional[str] = FieldUnset,
+        xai_api_key: Optional[str] = FieldUnset,
     ) -> None:
         if api_key is None:
             api_key = os.environ.get("RETAB_API_KEY")
@@ -80,30 +74,21 @@ class BaseRetab:
             "Content-Type": "application/json",
         }
 
-        # Only check environment variables if the value is PydanticUndefined
-        if openai_api_key is PydanticUndefined:
+        # Only check environment variables if the value is FieldUnset
+        if openai_api_key is FieldUnset:
             openai_api_key = os.environ.get("OPENAI_API_KEY")
 
-        # if claude_api_key is PydanticUndefined:
-        #    claude_api_key = os.environ.get("CLAUDE_API_KEY")
-
-        # if xai_api_key is PydanticUndefined:
-        #    xai_api_key = os.environ.get("XAI_API_KEY")
-
-        if gemini_api_key is PydanticUndefined:
+        if gemini_api_key is FieldUnset:
             gemini_api_key = os.environ.get("GEMINI_API_KEY")
 
-        # Only add headers if the values are actual strings (not None or PydanticUndefined)
-        if openai_api_key and openai_api_key is not PydanticUndefined:
+        # Only add headers if the values are actual strings (not None or FieldUnset)
+        if openai_api_key and openai_api_key is not FieldUnset:
             self.headers["OpenAI-Api-Key"] = openai_api_key
 
-        # if claude_api_key and claude_api_key is not PydanticUndefined:
-        #    self.headers["Anthropic-Api-Key"] = claude_api_key
-
-        if xai_api_key and xai_api_key is not PydanticUndefined:
+        if xai_api_key and xai_api_key is not FieldUnset:
             self.headers["XAI-Api-Key"] = xai_api_key
 
-        if gemini_api_key and gemini_api_key is not PydanticUndefined:
+        if gemini_api_key and gemini_api_key is not FieldUnset:
             self.headers["Gemini-Api-Key"] = gemini_api_key
 
     def _prepare_url(self, endpoint: str) -> str:
@@ -158,8 +143,6 @@ class Retab(BaseRetab):
         timeout (float): Request timeout in seconds. Defaults to 240.0
         max_retries (int): Maximum number of retries for failed requests. Defaults to 3
         openai_api_key (str, optional): OpenAI API key. Will look for OPENAI_API_KEY env variable if not provided
-        claude_api_key (str, optional): Claude API key. Will look for CLAUDE_API_KEY env variable if not provided
-        xai_api_key (str, optional): XAI API key. Will look for XAI_API_KEY env variable if not provided
         gemini_api_key (str, optional): Gemini API key. Will look for GEMINI_API_KEY env variable if not provided
 
     Attributes:
@@ -179,10 +162,8 @@ class Retab(BaseRetab):
         base_url: Optional[str] = None,
         timeout: float = 240.0,
         max_retries: int = 3,
-        openai_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        gemini_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        # claude_api_key: Optional[str] = PydanticUndefined,   # type: ignore[assignment]
-        # xai_api_key: Optional[str] = PydanticUndefined,   # type: ignore[assignment]
+        openai_api_key: Optional[str] = FieldUnset,
+        gemini_api_key: Optional[str] = FieldUnset,
     ) -> None:
         super().__init__(
             api_key=api_key,
@@ -191,16 +172,12 @@ class Retab(BaseRetab):
             max_retries=max_retries,
             openai_api_key=openai_api_key,
             gemini_api_key=gemini_api_key,
-            # claude_api_key=claude_api_key,
-            # xai_api_key=xai_api_key,
         )
 
         self.client = httpx.Client(timeout=self.timeout)
-        self.evals = evals.Evals(client=self)
         self.evaluations = evaluations.Evaluations(client=self)
         self.files = files.Files(client=self)
         self.fine_tuning = finetuning.FineTuning(client=self)
-        # self.prompt_optimization = prompt_optimization.PromptOptimization(client=self)
         self.documents = documents.Documents(client=self)
         self.models = models.Models(client=self)
         self.schemas = schemas.Schemas(client=self)
@@ -447,10 +424,8 @@ class AsyncRetab(BaseRetab):
         base_url: Optional[str] = None,
         timeout: float = 240.0,
         max_retries: int = 3,
-        openai_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        gemini_api_key: Optional[str] = PydanticUndefined,  # type: ignore[assignment]
-        # claude_api_key: Optional[str] = PydanticUndefined,   # type: ignore[assignment]
-        # xai_api_key: Optional[str] = PydanticUndefined,   # type: ignore[assignment]
+        openai_api_key: Optional[str] = FieldUnset,
+        gemini_api_key: Optional[str] = FieldUnset,
     ) -> None:
         super().__init__(
             api_key=api_key,
@@ -459,17 +434,13 @@ class AsyncRetab(BaseRetab):
             max_retries=max_retries,
             openai_api_key=openai_api_key,
             gemini_api_key=gemini_api_key,
-            # claude_api_key=claude_api_key,
-            # xai_api_key=xai_api_key,
         )
 
         self.client = httpx.AsyncClient(timeout=self.timeout)
 
-        self.evals = evals.AsyncEvals(client=self)
         self.evaluations = evaluations.AsyncEvaluations(client=self)
         self.files = files.AsyncFiles(client=self)
         self.fine_tuning = finetuning.AsyncFineTuning(client=self)
-        # self.prompt_optimization = prompt_optimization.AsyncPromptOptimization(client=self)
         self.documents = documents.AsyncDocuments(client=self)
         self.models = models.AsyncModels(client=self)
         self.schemas = schemas.AsyncSchemas(client=self)

{retab-0.0.42 → retab-0.0.43}/retab/resources/consensus/client.py

@@ -21,7 +21,7 @@ class BaseConsensusMixin:
             mode=mode,
         )
 
-        return PreparedRequest(method="POST", url="/v1/consensus/reconcile", data=request.model_dump(), idempotency_key=idempotency_key)
+        return PreparedRequest(method="POST", url="/v1/consensus/reconcile", data=request.model_dump(mode="json", exclude_unset=True), idempotency_key=idempotency_key)
 
 
 class Consensus(SyncAPIResource, BaseConsensusMixin):

{retab-0.0.42 → retab-0.0.43}/retab/resources/consensus/responses.py

@@ -55,7 +55,7 @@ class BaseResponsesMixin:
             instructions=instructions,
         )
 
-        return PreparedRequest(method="POST", url="/v1/responses", data=request.model_dump(), idempotency_key=idempotency_key)
+        return PreparedRequest(method="POST", url="/v1/responses", data=request.model_dump(mode="json", exclude_unset=True), idempotency_key=idempotency_key)
 
     def prepare_parse(
         self,

{retab-0.0.42 → retab-0.0.43}/retab/resources/documents/client.py

@@ -4,7 +4,6 @@ from typing import Any, Literal
 
 import PIL.Image
 from pydantic import HttpUrl
-from pydantic_core import PydanticUndefined
 from openai.types.chat.chat_completion_reasoning_effort import ChatCompletionReasoningEffort
 
 from ..._resource import AsyncAPIResource, SyncAPIResource
@@ -19,8 +18,7 @@ from ...types.mime import MIMEData
 from ...types.modalities import Modality
 from ...types.ai_models import LLMModel
 from ...types.schemas.object import Schema
-from ...types.standards import PreparedRequest
-from .extractions import AsyncExtractions, Extractions
+from ...types.standards import PreparedRequest, FieldUnset
 
 
 def maybe_parse_to_pydantic(schema: Schema, response: RetabParsedChatCompletion, allow_partial: bool = False) -> RetabParsedChatCompletion:
@@ -40,40 +38,50 @@ class BaseDocumentsMixin:
         self,
         document: Path | str | IOBase | MIMEData | PIL.Image.Image | HttpUrl,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> PreparedRequest:
         mime_document = prepare_mime_document(document)
 
-        loading_request = DocumentCreateMessageRequest(
-            document=mime_document,
-            modality=modality,
-            image_resolution_dpi=image_resolution_dpi,
-            browser_canvas=browser_canvas,
+        loading_request_dict = {
+            "document": mime_document,
+            "modality": modality,
+        }
+        if image_resolution_dpi is not FieldUnset:
+            loading_request_dict["image_resolution_dpi"] = image_resolution_dpi
+        if browser_canvas is not FieldUnset:
+            loading_request_dict["browser_canvas"] = browser_canvas
+
+        loading_request = DocumentCreateMessageRequest(**loading_request_dict)
+        return PreparedRequest(
+            method="POST", url="/v1/documents/create_messages", data=loading_request.model_dump(mode="json", exclude_unset=True), idempotency_key=idempotency_key
         )
-        return PreparedRequest(method="POST", url="/v1/documents/create_messages", data=loading_request.model_dump(), idempotency_key=idempotency_key)
 
     def _prepare_create_inputs(
         self,
         document: Path | str | IOBase | MIMEData | PIL.Image.Image | HttpUrl,
         json_schema: dict[str, Any] | Path | str,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment],
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment],
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> PreparedRequest:
         mime_document = prepare_mime_document(document)
         loaded_schema = load_json_schema(json_schema)
 
-        loading_request = DocumentCreateInputRequest(
-            document=mime_document,
-            modality=modality,
-            json_schema=loaded_schema,
-            image_resolution_dpi=image_resolution_dpi,
-            browser_canvas=browser_canvas,
-        )
-        return PreparedRequest(method="POST", url="/v1/documents/create_inputs", data=loading_request.model_dump(), idempotency_key=idempotency_key)
+        loading_request_dict = {
+            "document": mime_document,
+            "modality": modality,
+            "json_schema": loaded_schema,
+        }
+        if image_resolution_dpi is not FieldUnset:
+            loading_request_dict["image_resolution_dpi"] = image_resolution_dpi
+        if browser_canvas is not FieldUnset:
+            loading_request_dict["browser_canvas"] = browser_canvas
+
+        loading_request = DocumentCreateInputRequest(**loading_request_dict)
+        return PreparedRequest(method="POST", url="/v1/documents/create_inputs", data=loading_request.model_dump(mode="json", exclude_unset=True), idempotency_key=idempotency_key)
 
     def _prepare_correct_image_orientation(self, document: Path | str | IOBase | MIMEData | PIL.Image.Image) -> PreparedRequest:
         mime_document = prepare_mime_document(document)
@@ -105,7 +113,7 @@ class BaseDocumentsMixin:
             image_resolution_dpi=image_resolution_dpi,
             browser_canvas=browser_canvas,
         )
-        return PreparedRequest(method="POST", url="/v1/documents/parse", data=parse_request.model_dump(), idempotency_key=idempotency_key)
+        return PreparedRequest(method="POST", url="/v1/documents/parse", data=parse_request.model_dump(mode="json", exclude_unset=True), idempotency_key=idempotency_key)
 
 
 class Documents(SyncAPIResource, BaseDocumentsMixin):
@@ -145,8 +153,8 @@ class Documents(SyncAPIResource, BaseDocumentsMixin):
         self,
         document: Path | str | IOBase | MIMEData | PIL.Image.Image | HttpUrl,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> DocumentMessage:
         """
@@ -175,8 +183,8 @@ class Documents(SyncAPIResource, BaseDocumentsMixin):
         document: Path | str | IOBase | MIMEData | PIL.Image.Image | HttpUrl,
         json_schema: dict[str, Any] | Path | str,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> DocumentMessage:
         """
@@ -212,12 +220,12 @@ class Documents(SyncAPIResource, BaseDocumentsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> RetabParsedChatCompletion:
@@ -264,20 +272,29 @@ class Documents(SyncAPIResource, BaseDocumentsMixin):
         else:
             raise ValueError("Must provide either 'document' or 'documents' parameter.")
 
+        # Build request dictionary with only provided fields
+        request_dict = {
+            "json_schema": json_schema,
+            "documents": processed_documents,
+            "model": model,
+            "stream": False,
+            "store": store,
+        }
+        if temperature is not FieldUnset:
+            request_dict["temperature"] = temperature
+        if modality is not FieldUnset:
+            request_dict["modality"] = modality
+        if reasoning_effort is not FieldUnset:
+            request_dict["reasoning_effort"] = reasoning_effort
+        if n_consensus is not FieldUnset:
+            request_dict["n_consensus"] = n_consensus
+        if image_resolution_dpi is not FieldUnset:
+            request_dict["image_resolution_dpi"] = image_resolution_dpi
+        if browser_canvas is not FieldUnset:
+            request_dict["browser_canvas"] = browser_canvas
+
         # Validate DocumentAPIRequest data (raises exception if invalid)
-        request = DocumentExtractRequest(
-            json_schema=json_schema,
-            documents=processed_documents,
-            model=model,
-            temperature=temperature,
-            stream=False,
-            modality=modality,
-            store=store,
-            reasoning_effort=reasoning_effort,
-            n_consensus=n_consensus,
-            image_resolution_dpi=image_resolution_dpi,
-            browser_canvas=browser_canvas,
-        )
+        request = DocumentExtractRequest(**request_dict)
 
         prepared_request = PreparedRequest(
             method="POST", url="/v1/documents/extract", data=request.model_dump(mode="json", exclude_unset=True, exclude_defaults=True), idempotency_key=idempotency_key
@@ -340,8 +357,8 @@ class AsyncDocuments(AsyncAPIResource, BaseDocumentsMixin):
         self,
         document: Path | str | IOBase | MIMEData | PIL.Image.Image,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> DocumentMessage:
         """
@@ -372,8 +389,8 @@ class AsyncDocuments(AsyncAPIResource, BaseDocumentsMixin):
         document: Path | str | IOBase | MIMEData | PIL.Image.Image | HttpUrl,
         json_schema: dict[str, Any] | Path | str,
         modality: Modality = "native",
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
         idempotency_key: str | None = None,
     ) -> DocumentMessage:
         """
@@ -434,12 +451,12 @@ class AsyncDocuments(AsyncAPIResource, BaseDocumentsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> RetabParsedChatCompletion:
@@ -486,20 +503,29 @@ class AsyncDocuments(AsyncAPIResource, BaseDocumentsMixin):
         else:
             raise ValueError("Must provide either 'document' or 'documents' parameter.")
 
+        # Build request dictionary with only provided fields
+        request_dict = {
+            "json_schema": json_schema,
+            "documents": processed_documents,
+            "model": model,
+            "stream": False,
+            "store": store,
+        }
+        if temperature is not FieldUnset:
+            request_dict["temperature"] = temperature
+        if modality is not FieldUnset:
+            request_dict["modality"] = modality
+        if reasoning_effort is not FieldUnset:
+            request_dict["reasoning_effort"] = reasoning_effort
+        if n_consensus is not FieldUnset:
+            request_dict["n_consensus"] = n_consensus
+        if image_resolution_dpi is not FieldUnset:
+            request_dict["image_resolution_dpi"] = image_resolution_dpi
+        if browser_canvas is not FieldUnset:
+            request_dict["browser_canvas"] = browser_canvas
+
         # Validate DocumentAPIRequest data (raises exception if invalid)
-        request = DocumentExtractRequest(
-            json_schema=json_schema,
-            documents=processed_documents,
-            model=model,
-            temperature=temperature,
-            stream=False,
-            modality=modality,
-            store=store,
-            reasoning_effort=reasoning_effort,
-            n_consensus=n_consensus,
-            image_resolution_dpi=image_resolution_dpi,
-            browser_canvas=browser_canvas,
-        )
+        request = DocumentExtractRequest(**request_dict)
 
         prepared_request = PreparedRequest(
             method="POST", url="/v1/documents/extract", data=request.model_dump(mode="json", exclude_unset=True, exclude_defaults=True), idempotency_key=idempotency_key

{retab-0.0.42 → retab-0.0.43}/retab/resources/documents/extractions.py

@@ -10,7 +10,6 @@ from openai.types.chat.chat_completion_reasoning_effort import ChatCompletionRea
 from openai.types.chat.parsed_chat_completion import ParsedChatCompletionMessage
 from openai.types.responses.response import Response
 from openai.types.responses.response_input_param import ResponseInputItemParam
-from pydantic_core import PydanticUndefined
 from pydantic import HttpUrl
 
 from ..._resource import AsyncAPIResource, SyncAPIResource
@@ -23,7 +22,7 @@ from ...types.documents.extractions import DocumentExtractRequest, LogExtraction
 from ...types.browser_canvas import BrowserCanvas
 from ...types.modalities import Modality
 from ...types.schemas.object import Schema
-from ...types.standards import PreparedRequest
+from ...types.standards import PreparedRequest, FieldUnset
 
 
 def maybe_parse_to_pydantic(schema: Schema, response: RetabParsedChatCompletion, allow_partial: bool = False) -> RetabParsedChatCompletion:
@@ -44,14 +43,14 @@ class BaseExtractionsMixin:
         json_schema: dict[str, Any] | Path | str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        model: str = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        model: str = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
         stream: bool = False,
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        n_consensus: int = FieldUnset,
         store: bool = False,
         idempotency_key: str | None = None,
     ) -> PreparedRequest:
@@ -71,20 +70,30 @@ class BaseExtractionsMixin:
         else:
             raise ValueError("Must provide either 'document' or 'documents' parameter.")
 
+        # Build request dictionary with only provided fields
+        request_dict = {
+            'json_schema': json_schema,
+            'documents': processed_documents,
+            'stream': stream,
+            'store': store,
+        }
+        if model is not FieldUnset:
+            request_dict['model'] = model
+        if temperature is not FieldUnset:
+            request_dict['temperature'] = temperature
+        if modality is not FieldUnset:
+            request_dict['modality'] = modality
+        if reasoning_effort is not FieldUnset:
+            request_dict['reasoning_effort'] = reasoning_effort
+        if n_consensus is not FieldUnset:
+            request_dict['n_consensus'] = n_consensus
+        if image_resolution_dpi is not FieldUnset:
+            request_dict['image_resolution_dpi'] = image_resolution_dpi
+        if browser_canvas is not FieldUnset:
+            request_dict['browser_canvas'] = browser_canvas
+
         # Validate DocumentAPIRequest data (raises exception if invalid)
-        request = DocumentExtractRequest(
-            json_schema=json_schema,
-            documents=processed_documents,
-            model=model,
-            temperature=temperature,
-            stream=stream,
-            modality=modality,
-            store=store,
-            reasoning_effort=reasoning_effort,
-            n_consensus=n_consensus,
-            image_resolution_dpi=image_resolution_dpi,
-            browser_canvas=browser_canvas,
-        )
+        request = DocumentExtractRequest(**request_dict)
 
         return PreparedRequest(
             method="POST", url="/v1/documents/extractions", data=request.model_dump(mode="json", exclude_unset=True, exclude_defaults=True), idempotency_key=idempotency_key
@@ -144,12 +153,12 @@ class Extractions(SyncAPIResource, BaseExtractionsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> RetabParsedChatCompletion:
@@ -204,12 +213,12 @@ class Extractions(SyncAPIResource, BaseExtractionsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> Generator[RetabParsedChatCompletion, None, None]:
@@ -345,12 +354,12 @@ class AsyncExtractions(AsyncAPIResource, BaseExtractionsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> RetabParsedChatCompletion:
@@ -401,12 +410,12 @@ class AsyncExtractions(AsyncAPIResource, BaseExtractionsMixin):
         model: str,
         document: Path | str | IOBase | HttpUrl | None = None,
         documents: list[Path | str | IOBase | HttpUrl] | None = None,
-        image_resolution_dpi: int = PydanticUndefined,  # type: ignore[assignment]
-        browser_canvas: BrowserCanvas = PydanticUndefined,  # type: ignore[assignment]
-        temperature: float = PydanticUndefined,  # type: ignore[assignment]
-        modality: Modality = PydanticUndefined,  # type: ignore[assignment]
-        reasoning_effort: ChatCompletionReasoningEffort = PydanticUndefined,  # type: ignore[assignment]
-        n_consensus: int = PydanticUndefined,  # type: ignore[assignment]
+        image_resolution_dpi: int = FieldUnset,
+        browser_canvas: BrowserCanvas = FieldUnset,
+        temperature: float = FieldUnset,
+        modality: Modality = FieldUnset,
+        reasoning_effort: ChatCompletionReasoningEffort = FieldUnset,
+        n_consensus: int = FieldUnset,
         idempotency_key: str | None = None,
         store: bool = False,
     ) -> AsyncGenerator[RetabParsedChatCompletion, None]: