GdoczAI 0.1.0__tar.gz

gdoczai-0.1.0/GdoczAI.egg-info/PKG-INFO

@@ -0,0 +1,52 @@
+Metadata-Version: 2.4
+Name: GdoczAI
+Version: 0.1.0
+Summary: Python SDK for GdoczAI — OCR, extract, and segment documents
+Author-email: Ramkumar <ramkumarlpm4@gmail.com>
+Project-URL: Homepage, https://github.com/GramosoftAI/GdoczAI
+Keywords: ocr,document,pdf,extract,gdocz,ai
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+
+# gdoczai
+
+Official Python SDK for [GdoczAI](https://gdocz.gramopro.ai) — OCR, extract fields, 
+and segment documents with ease.
+
+## Installation
+```bash
+pip install gdocz_sdk
+```
+
+## Quick Start
+```python
+from gdocz_sdk import GdoczaiClient
+
+client = GdoczaiClient(api_key="your-api-key")
+
+# Convert PDF to Markdown
+result = client.convert("document.pdf")
+print(result.markdown)
+
+# Extract fields
+from gdocz_sdk import ExtractOptions
+result = client.extract("document.pdf", ExtractOptions(fields=["name", "date"]))
+print(result.extracted_data)
+
+# Segment document
+result = client.segment("document.pdf")
+print(result.segments)
+```
+
+## API Key
+
+Set your API key as an environment variable:
+```bash
+export GDOCZAI_API_KEY="your-api-key"
+```
+
+Or pass it directly to the client.

gdoczai-0.1.0/GdoczAI.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+README.md
+pyproject.toml
+GdoczAI.egg-info/PKG-INFO
+GdoczAI.egg-info/SOURCES.txt
+GdoczAI.egg-info/dependency_links.txt
+GdoczAI.egg-info/requires.txt
+GdoczAI.egg-info/top_level.txt
+gdocz_sdk/__init__.py
+gdocz_sdk/client.py
+gdocz_sdk/convert_options.py
+gdocz_sdk/convert_result.py
+gdocz_sdk/exceptions.py
+gdocz_sdk/extract_options.py
+gdocz_sdk/extract_result.py
+gdocz_sdk/segment_options.py
+gdocz_sdk/segment_result.py

gdoczai-0.1.0/GdoczAI.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

gdoczai-0.1.0/GdoczAI.egg-info/requires.txt

@@ -0,0 +1 @@
+requests>=2.28.0

gdoczai-0.1.0/GdoczAI.egg-info/top_level.txt

@@ -0,0 +1 @@
+gdocz_sdk

gdoczai-0.1.0/PKG-INFO

@@ -0,0 +1,52 @@
+Metadata-Version: 2.4
+Name: GdoczAI
+Version: 0.1.0
+Summary: Python SDK for GdoczAI — OCR, extract, and segment documents
+Author-email: Ramkumar <ramkumarlpm4@gmail.com>
+Project-URL: Homepage, https://github.com/GramosoftAI/GdoczAI
+Keywords: ocr,document,pdf,extract,gdocz,ai
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+
+# gdoczai
+
+Official Python SDK for [GdoczAI](https://gdocz.gramopro.ai) — OCR, extract fields, 
+and segment documents with ease.
+
+## Installation
+```bash
+pip install gdocz_sdk
+```
+
+## Quick Start
+```python
+from gdocz_sdk import GdoczaiClient
+
+client = GdoczaiClient(api_key="your-api-key")
+
+# Convert PDF to Markdown
+result = client.convert("document.pdf")
+print(result.markdown)
+
+# Extract fields
+from gdocz_sdk import ExtractOptions
+result = client.extract("document.pdf", ExtractOptions(fields=["name", "date"]))
+print(result.extracted_data)
+
+# Segment document
+result = client.segment("document.pdf")
+print(result.segments)
+```
+
+## API Key
+
+Set your API key as an environment variable:
+```bash
+export GDOCZAI_API_KEY="your-api-key"
+```
+
+Or pass it directly to the client.

gdoczai-0.1.0/README.md

@@ -0,0 +1,38 @@
+# gdoczai
+
+Official Python SDK for [GdoczAI](https://gdocz.gramopro.ai) — OCR, extract fields, 
+and segment documents with ease.
+
+## Installation
+```bash
+pip install gdocz_sdk
+```
+
+## Quick Start
+```python
+from gdocz_sdk import GdoczaiClient
+
+client = GdoczaiClient(api_key="your-api-key")
+
+# Convert PDF to Markdown
+result = client.convert("document.pdf")
+print(result.markdown)
+
+# Extract fields
+from gdocz_sdk import ExtractOptions
+result = client.extract("document.pdf", ExtractOptions(fields=["name", "date"]))
+print(result.extracted_data)
+
+# Segment document
+result = client.segment("document.pdf")
+print(result.segments)
+```
+
+## API Key
+
+Set your API key as an environment variable:
+```bash
+export GDOCZAI_API_KEY="your-api-key"
+```
+
+Or pass it directly to the client.

gdoczai-0.1.0/gdocz_sdk/__init__.py

@@ -0,0 +1,13 @@
+from .client import GdoczaiClient
+from .convert_options import ConvertOptions
+from .extract_options import ExtractOptions
+from .segment_options import SegmentOptions
+from .convert_result import ConvertResult
+from .extract_result import ExtractResult
+from .segment_result import SegmentResult
+from .exceptions import (
+    GdoczAPIError,
+    GdoczTimeoutError,
+    GdoczFileError,
+    GdoczValidationError,
+)

gdoczai-0.1.0/gdocz_sdk/client.py

@@ -0,0 +1,147 @@
+import requests
+import os
+import json
+from .convert_result import ConvertResult
+from .extract_result import ExtractResult
+from .segment_result import SegmentResult
+from .exceptions import GdoczAPIError, GdoczTimeoutError, GdoczFileError, GdoczValidationError
+
+class GdoczaiClient:
+
+    def __init__(self, api_key=None, convert_base_url=None, extract_base_url=None, segment_base_url=None, timeout=300):
+        self.api_key = api_key or os.getenv("GDOCZAI_API_KEY")
+        if not self.api_key:
+            raise GdoczValidationError("API key required")
+
+        self.convert_base_url = convert_base_url or "https://gdocz.gramopro.ai/ocr"
+        self.extract_base_url = extract_base_url or "https://gdocz.gramopro.ai/ocr"
+        self.segment_base_url = segment_base_url or "https://gdocz.gramopro.ai/ocr"
+        self.timeout = timeout
+
+    def convert(self, file_path, options=None):
+
+        if not os.path.exists(file_path):
+            raise GdoczFileError(f"File not found: {file_path}")
+
+        mode = "chandra"
+        page_range = None
+
+        if options:
+            mode = options.mode
+            page_range = options.page_range
+
+        try:
+            with open(file_path, "rb") as f:
+
+                files = {"file": (os.path.basename(file_path), f)}
+                data = {"model": mode}
+
+                if page_range:
+                    data["page_range"] = page_range
+
+                headers = {"X-API-Key": self.api_key}
+
+                response = requests.post(
+                    f"{self.convert_base_url}/ocr/markdown-only",
+                    files=files,
+                    data=data,
+                    headers=headers,
+                    timeout=self.timeout
+                )
+
+        except requests.exceptions.Timeout:
+            raise GdoczTimeoutError("Convert request timed out")
+
+        if response.status_code != 200:
+            raise GdoczAPIError(response.status_code, response.text)
+
+        return ConvertResult(response.json())
+
+    def extract(self, file_path, options=None):
+
+        if not os.path.exists(file_path):
+            raise GdoczFileError(f"File not found: {file_path}")
+
+        if options and options.fields is not None and not isinstance(options.fields, (list, dict)):
+            raise GdoczValidationError("fields must be a list or schema dict")
+
+        headers = {
+            "X-API-Key": self.api_key,
+            "Content-Type": "application/json"
+        }
+
+        try:
+            if options and options.request_id:
+                payload = {
+                    "request_id": options.request_id,
+                    "fields": options.fields
+                }
+            else:
+                convert_result = self.convert(file_path)
+                markdown = convert_result.markdown
+
+                if not markdown:
+                    raise GdoczValidationError("Markdown extraction failed — empty response from convert")
+
+                payload = {
+                    "markdown_content": markdown,
+                    "fields": options.fields if options else []
+                }
+
+            response = requests.post(
+                f"{self.extract_base_url}/ocr/extract/markdown",
+                json=payload,
+                headers=headers,
+                timeout=self.timeout
+            )
+
+        except requests.exceptions.Timeout:
+            raise GdoczTimeoutError("Extract request timed out")
+
+        if response.status_code != 200:
+            raise GdoczAPIError(response.status_code, response.text)
+
+        return ExtractResult(response.json())
+
+    def segment(self, file_path, options=None):
+
+        if not os.path.exists(file_path):
+            raise GdoczFileError(f"File not found: {file_path}")
+
+        mode = "auto"
+        segments = None
+
+        if options:
+            mode = options.mode
+            segments = options.segments
+
+        if mode == "guided" and not segments:
+            raise GdoczValidationError("Guided mode requires segments list")
+
+        try:
+            with open(file_path, "rb") as f:
+
+                files = {"file": (os.path.basename(file_path), f)}
+                data = {"mode": mode}
+
+                if mode == "guided" and segments:
+                    import json
+                    data["segments"] = json.dumps(segments)
+
+                headers = {"X-API-Key": self.api_key}
+
+                response = requests.post(
+                    f"{self.segment_base_url}/ocr/segment",
+                    files=files,
+                    data=data,
+                    headers=headers,
+                    timeout=self.timeout
+                )
+
+        except requests.exceptions.Timeout:
+            raise GdoczTimeoutError("Segment request timed out")
+
+        if response.status_code != 200:
+            raise GdoczAPIError(response.status_code, response.text)
+
+        return SegmentResult(response.json())

gdoczai-0.1.0/gdocz_sdk/convert_options.py

@@ -0,0 +1,5 @@
+class ConvertOptions:
+
+    def __init__(self, mode="chandra", page_range=None):
+        self.mode = mode
+        self.page_range = page_range

gdoczai-0.1.0/gdocz_sdk/convert_result.py

@@ -0,0 +1,22 @@
+import os
+
+class ConvertResult:
+
+    def __init__(self, data):
+        self.success = data.get("success", False)
+        self.request_id = data.get("request_id")
+        self.markdown = data.get("markdown")
+
+        # metadata fields
+        metadata = data.get("metadata", {})
+        self.metadata = metadata
+        self.page_count = metadata.get("page_count")
+        self.processing_time = metadata.get("processing_time_seconds")
+        self.filename = metadata.get("filename")
+        self.model = metadata.get("model")
+
+    def save_output(self, folder_path):
+        os.makedirs(folder_path, exist_ok=True)
+
+        with open(os.path.join(folder_path, "output.md"), "w", encoding="utf-8") as f:
+            f.write(self.markdown or "")

gdoczai-0.1.0/gdocz_sdk/exceptions.py

@@ -0,0 +1,14 @@
+class GdoczAPIError(Exception):
+    def __init__(self, status_code, response_data):
+        self.status_code = status_code
+        self.response_data = response_data
+        super().__init__(f"API error {status_code}: {response_data}")
+
+class GdoczTimeoutError(Exception):
+    pass
+
+class GdoczFileError(Exception):
+    pass
+
+class GdoczValidationError(Exception):
+    pass

gdoczai-0.1.0/gdocz_sdk/extract_options.py

@@ -0,0 +1,9 @@
+class ExtractOptions:
+
+    def __init__(self, fields=None, request_id=None):
+        """
+        fields     : list of field names e.g. ["total_amount", "tax"]
+        request_id : reuse existing convert request
+        """
+        self.fields = fields or []
+        self.request_id = request_id

gdoczai-0.1.0/gdocz_sdk/extract_result.py

@@ -0,0 +1,13 @@
+class ExtractResult:
+
+    def __init__(self, data):
+        self.success = data.get("success", False)
+        self.extracted_data = data.get("extracted_data", {})
+
+        # metadata fields
+        metadata = data.get("metadata", {})
+        self.metadata = metadata
+        self.fields_requested = metadata.get("fields_requested")
+        self.fields_extracted = metadata.get("fields_extracted")
+        self.schema_type = metadata.get("schema_type")
+        self.token_usage = metadata.get("token_usage", {})

gdoczai-0.1.0/gdocz_sdk/segment_options.py

@@ -0,0 +1,9 @@
+class SegmentOptions:
+
+    def __init__(self, mode="auto", segments=None):
+        """
+        mode: "auto" or "guided"
+        segments: list of {name, description}
+        """
+        self.mode = mode
+        self.segments = segments or []

gdoczai-0.1.0/gdocz_sdk/segment_result.py

@@ -0,0 +1,17 @@
+class SegmentResult:
+
+    def __init__(self, data):
+        self.success = data.get("success", False)
+        self.segments = data.get("segments", [])
+        self.request_id = data.get("request_id")
+        self.processing_time = data.get("processing_time")
+
+        # metadata fields
+        metadata = data.get("metadata", {})
+        self.metadata = metadata
+        self.total_pages = metadata.get("total_pages")
+        self.strategy = metadata.get("strategy")
+        self.mode = metadata.get("mode")
+        self.filename = metadata.get("filename")
+        self.ocr_time = metadata.get("ocr_time_seconds")
+        self.segmentation_time = metadata.get("segmentation_time_seconds")

gdoczai-0.1.0/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "GdoczAI"
+version = "0.1.0"
+description = "Python SDK for GdoczAI — OCR, extract, and segment documents"
+readme = "README.md"
+license = { file = "LICENSE" }
+authors = [
+    { name = "Ramkumar", email = "ramkumarlpm4@gmail.com" }
+]
+keywords = ["ocr", "document", "pdf", "extract", "gdocz", "ai"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+requires-python = ">=3.8"
+dependencies = [
+    "requests>=2.28.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/GramosoftAI/GdoczAI"

gdoczai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+