docextractbr 0.1.0__tar.gz

docextractbr-0.1.0/.gitignore

@@ -0,0 +1,9 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+.env
+*.db
+.venv/
+.ruff_cache/
+.pytest_cache/

docextractbr-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 DocExtract
+
+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.

docextractbr-0.1.0/PKG-INFO

@@ -0,0 +1,93 @@
+Metadata-Version: 2.4
+Name: docextractbr
+Version: 0.1.0
+Summary: SDK Python para a DocExtract API — extração de dados de documentos com IA
+Project-URL: Homepage, https://docextract.com.br
+Project-URL: Documentation, https://docextract.com.br/docs
+Author: DocExtract
+License: MIT
+License-File: LICENSE
+Keywords: ai,api,document,extraction,llm,ocr,pdf,sdk
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.9
+Requires-Dist: httpx>=0.24.0
+Description-Content-Type: text/markdown
+
+# DocExtract
+
+SDK Python para extração de dados de documentos com IA.
+
+Converte PDFs, imagens e documentos brasileiros em JSON estruturado.
+
+## Instalação
+
+```bash
+pip install docextract
+```
+
+## Uso rápido
+
+```python
+from docextract import DocExtract
+
+doc = DocExtract(api_key="dk_sua_chave")
+
+# Extrair dados de um PDF
+result = doc.extract("nota_fiscal.pdf")
+print(result["fields"]["emitente_cnpj"])
+print(result["confidence"])  # 0.98
+
+# Especificar tipo de documento
+result = doc.extract("cnh.jpg", document_type="cnh")
+print(result["fields"]["nome"])
+print(result["fields"]["cpf"])
+
+# Auto-detect
+result = doc.extract("documento.pdf", document_type="auto")
+print(result["document_type"])  # "nfe", "cnh", etc.
+```
+
+## Tipos de documentos suportados
+
+| Tipo | Código |
+|------|--------|
+| CNH | `cnh` |
+| RG | `rg` |
+| CPF | `cpf` |
+| NF-e | `nfe` |
+| NFS-e | `nfse` |
+| Boleto | `boleto` |
+| Contrato Social | `contrato_social` |
+| Comprovante de Residência | `comprovante_residencia` |
+| Holerite | `comprovante_renda` |
+| Detecção automática | `auto` |
+
+## BYOK (Bring Your Own Key)
+
+Configure sua própria API key de IA no painel, ou passe inline:
+
+```python
+result = doc.extract(
+    "documento.pdf",
+    llm_provider="gemini",
+    llm_api_key="sua_gemini_key",
+    llm_model="gemini-2.5-flash",
+)
+```
+
+## Extrair de bytes em memória
+
+```python
+with open("doc.pdf", "rb") as f:
+    result = doc.extract_bytes(f.read(), "doc.pdf", document_type="nfe")
+```
+
+## Links
+
+- Documentação: https://docextract.com.br/docs
+- Painel: https://docextract.com.br

docextractbr-0.1.0/README.md

@@ -0,0 +1,73 @@
+# DocExtract
+
+SDK Python para extração de dados de documentos com IA.
+
+Converte PDFs, imagens e documentos brasileiros em JSON estruturado.
+
+## Instalação
+
+```bash
+pip install docextract
+```
+
+## Uso rápido
+
+```python
+from docextract import DocExtract
+
+doc = DocExtract(api_key="dk_sua_chave")
+
+# Extrair dados de um PDF
+result = doc.extract("nota_fiscal.pdf")
+print(result["fields"]["emitente_cnpj"])
+print(result["confidence"])  # 0.98
+
+# Especificar tipo de documento
+result = doc.extract("cnh.jpg", document_type="cnh")
+print(result["fields"]["nome"])
+print(result["fields"]["cpf"])
+
+# Auto-detect
+result = doc.extract("documento.pdf", document_type="auto")
+print(result["document_type"])  # "nfe", "cnh", etc.
+```
+
+## Tipos de documentos suportados
+
+| Tipo | Código |
+|------|--------|
+| CNH | `cnh` |
+| RG | `rg` |
+| CPF | `cpf` |
+| NF-e | `nfe` |
+| NFS-e | `nfse` |
+| Boleto | `boleto` |
+| Contrato Social | `contrato_social` |
+| Comprovante de Residência | `comprovante_residencia` |
+| Holerite | `comprovante_renda` |
+| Detecção automática | `auto` |
+
+## BYOK (Bring Your Own Key)
+
+Configure sua própria API key de IA no painel, ou passe inline:
+
+```python
+result = doc.extract(
+    "documento.pdf",
+    llm_provider="gemini",
+    llm_api_key="sua_gemini_key",
+    llm_model="gemini-2.5-flash",
+)
+```
+
+## Extrair de bytes em memória
+
+```python
+with open("doc.pdf", "rb") as f:
+    result = doc.extract_bytes(f.read(), "doc.pdf", document_type="nfe")
+```
+
+## Links
+
+- Documentação: https://docextract.com.br/docs
+- Painel: https://docextract.com.br

docextractbr-0.1.0/docextract/__init__.py

@@ -0,0 +1,6 @@
+"""DocExtract SDK — extração de dados de documentos com IA."""
+
+from docextract.client import DocExtract
+
+__version__ = "0.1.0"
+__all__ = ["DocExtract"]

docextractbr-0.1.0/docextract/client.py

@@ -0,0 +1,115 @@
+"""Cliente Python para a DocExtract API."""
+
+from pathlib import Path
+
+import httpx
+
+
+class DocExtract:
+    """Extrai dados estruturados de documentos com IA.
+
+    Uso:
+        doc = DocExtract(api_key="dk_sua_chave")
+        result = doc.extract("nota_fiscal.pdf")
+        print(result["fields"]["valor_total"])
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        base_url: str = "https://api.docextract.com.br",
+        timeout: float = 120.0,
+    ):
+        self.api_key = api_key
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+
+    def extract(
+        self,
+        file_path: str,
+        document_type: str = "auto",
+        llm_provider: str | None = None,
+        llm_api_key: str | None = None,
+        llm_model: str | None = None,
+    ) -> dict:
+        """Extrai dados de um documento.
+
+        Args:
+            file_path: caminho do arquivo (PDF, imagem, DOCX, etc.)
+            document_type: "auto", "cnh", "rg", "nfe", "nfse", "boleto", etc.
+            llm_provider: override do provider (gemini/openai/anthropic)
+            llm_api_key: override da API key do LLM (BYOK inline)
+            llm_model: override do modelo
+
+        Returns:
+            dict com success, document_type, confidence, fields, metadata
+        """
+        path = Path(file_path)
+        if not path.exists():
+            raise FileNotFoundError(f"Arquivo não encontrado: {file_path}")
+
+        data = {"document_type": document_type}
+        if llm_provider:
+            data["llm_provider"] = llm_provider
+        if llm_api_key:
+            data["llm_api_key"] = llm_api_key
+        if llm_model:
+            data["llm_model"] = llm_model
+
+        with open(path, "rb") as f:
+            response = httpx.post(
+                f"{self.base_url}/v1/extract",
+                headers={"x-api-key": self.api_key},
+                files={"file": (path.name, f)},
+                data=data,
+                timeout=self.timeout,
+            )
+
+        if response.status_code == 429:
+            error = response.json()
+            raise Exception(f"Limite mensal atingido: {error.get('detail', {}).get('message', '')}")
+
+        response.raise_for_status()
+        return response.json()
+
+    def extract_bytes(
+        self,
+        file_bytes: bytes,
+        filename: str,
+        document_type: str = "auto",
+    ) -> dict:
+        """Extrai dados de bytes em memória.
+
+        Args:
+            file_bytes: conteúdo do arquivo em bytes
+            filename: nome do arquivo (para detectar tipo)
+            document_type: tipo do documento ou "auto"
+        """
+        response = httpx.post(
+            f"{self.base_url}/v1/extract",
+            headers={"x-api-key": self.api_key},
+            files={"file": (filename, file_bytes)},
+            data={"document_type": document_type},
+            timeout=self.timeout,
+        )
+        response.raise_for_status()
+        return response.json()
+
+    def types(self) -> dict:
+        """Lista tipos de documentos suportados."""
+        response = httpx.get(
+            f"{self.base_url}/v1/types",
+            timeout=self.timeout,
+        )
+        response.raise_for_status()
+        return response.json()
+
+    def usage(self) -> dict:
+        """Retorna uso atual do mês."""
+        response = httpx.get(
+            f"{self.base_url}/v1/usage",
+            headers={"x-api-key": self.api_key},
+            timeout=self.timeout,
+        )
+        response.raise_for_status()
+        return response.json()

docextractbr-0.1.0/pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "docextractbr"
+version = "0.1.0"
+description = "SDK Python para a DocExtract API — extração de dados de documentos com IA"
+readme = "README.md"
+requires-python = ">=3.9"
+license = {text = "MIT"}
+authors = [
+    {name = "DocExtract"},
+]
+keywords = ["document", "extraction", "ocr", "pdf", "ai", "llm", "api", "sdk"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Text Processing",
+]
+dependencies = [
+    "httpx>=0.24.0",
+]
+
+[project.urls]
+Homepage = "https://docextract.com.br"
+Documentation = "https://docextract.com.br/docs"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["docextract"]