HowdenParser 0.1.4__tar.gz → 0.1.8__tar.gz

howdenparser-0.1.8/HowdenParser/parameter/__init__.py

@@ -0,0 +1,15 @@
+import os
+import importlib
+
+# Get all .py files in this folder except __init__.py
+current_dir = os.path.dirname(__file__)
+for filename in os.listdir(current_dir):
+    if filename.endswith(".py") and filename != "__init__.py":
+        module_name = filename[:-3]  # remove .py
+        module = importlib.import_module(f".{module_name}", package=__name__)
+
+        # Add all classes from the module to the package namespace
+        for attr_name in dir(module):
+            attr = getattr(module, attr_name)
+            if isinstance(attr, type):  # only classes
+                globals()[attr_name] = attr

howdenparser-0.1.8/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.3
+Name: HowdenParser
+Version: 0.1.8
+Summary: A simple configuration manager with Pydantic and JSON export.
+License: MIT
+Keywords: config,configuration,pydantic,json
+Author: JesperThoftIllemannJ
+Author-email: jesper.jaeger@howdendanmark.dk
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Project-URL: Documentation, https://github.com/yourusername/config
+Project-URL: Homepage, https://github.com/yourusername/config
+Project-URL: Repository, https://github.com/yourusername/config
+Description-Content-Type: text/markdown
+
+# OCR & LLM Parser
+
+A powerful Python package for parsing and processing documents using multiple providers:
+- **Mistral OCR** — Extracts text from PDFs and images with high accuracy.
+- **LangChain** — Processes or summarizes text using LLMs.
+- **Llama Parser** — Advanced parsing with Markdown or text output.
+- **HuggingFace** — OCR and document question answering with transformer models.
+
+The package provides a **unified interface** so you can switch between providers easily using a **factory pattern**.
+
+---
+
+## 🚀 Features
+- Extract text from PDFs or images
+- Summarize or process text using LLMs
+- Support for **Markdown** or **plain text** output
+- Plug-and-play factory to switch providers without changing much code
+- Handles environment variable loading for API keys automatically
+
+---
+
+# 🔑 Tokens
+
+Create a .env file in your project root and add the API keys for the services you want to use.
+
+### Mistral OCR
+MISTRAL-OCR-API-TOKEN=your_mistral_api_key
+
+### Llama Parser
+LLAMA-PARSER-API-TOKEN=your_llama_parser_api_key
+
+### HuggingFace
+HF-API-TOKEN=your_huggingface_api_key
+
+Only include the keys for the providers you plan to use.
+
+---
+
+# 🛠️ Usage
+
+from HowdenParser import ParserFactory
+
+from pathlib import Path
+
+parser = ParserFactory.get_parser("mistralocr:", result_type="md")
+text = parser.parse(Path("document.pdf"))
+print(text)
+
+if HowdenConfig package being used
+
+
+parser = ParserFactory.get_parser("mistralocr:", **config.parameter.dump_model()) 
+
+text = parser.parse(Path("document.pdf"))
+
+

howdenparser-0.1.8/README.md

@@ -0,0 +1,55 @@
+# OCR & LLM Parser
+
+A powerful Python package for parsing and processing documents using multiple providers:
+- **Mistral OCR** — Extracts text from PDFs and images with high accuracy.
+- **LangChain** — Processes or summarizes text using LLMs.
+- **Llama Parser** — Advanced parsing with Markdown or text output.
+- **HuggingFace** — OCR and document question answering with transformer models.
+
+The package provides a **unified interface** so you can switch between providers easily using a **factory pattern**.
+
+---
+
+## 🚀 Features
+- Extract text from PDFs or images
+- Summarize or process text using LLMs
+- Support for **Markdown** or **plain text** output
+- Plug-and-play factory to switch providers without changing much code
+- Handles environment variable loading for API keys automatically
+
+---
+
+# 🔑 Tokens
+
+Create a .env file in your project root and add the API keys for the services you want to use.
+
+### Mistral OCR
+MISTRAL-OCR-API-TOKEN=your_mistral_api_key
+
+### Llama Parser
+LLAMA-PARSER-API-TOKEN=your_llama_parser_api_key
+
+### HuggingFace
+HF-API-TOKEN=your_huggingface_api_key
+
+Only include the keys for the providers you plan to use.
+
+---
+
+# 🛠️ Usage
+
+from HowdenParser import ParserFactory
+
+from pathlib import Path
+
+parser = ParserFactory.get_parser("mistralocr:", result_type="md")
+text = parser.parse(Path("document.pdf"))
+print(text)
+
+if HowdenConfig package being used
+
+
+parser = ParserFactory.get_parser("mistralocr:", **config.parameter.dump_model()) 
+
+text = parser.parse(Path("document.pdf"))
+

{howdenparser-0.1.4 → howdenparser-0.1.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "HowdenParser"
-version = "0.1.4"
+version = "0.1.8"
 description = "A simple configuration manager with Pydantic and JSON export."
 authors = [ "JesperThoftIllemannJ <jesper.jaeger@howdendanmark.dk>",]
 readme = "README.md"
@@ -16,3 +16,5 @@ documentation = "https://github.com/yourusername/config"
 [[tool.poetry.packages]]
 include = "HowdenParser"
 
+[tool.poetry.group.dev.dependencies]
+toml = "^0.10.2"

howdenparser-0.1.4/HowdenParser/parameter/__init__.py

@@ -1,3 +0,0 @@
-from .huggingface import Parameter as Huggingface
-from .mistralocr import Parameter as MistralOcr
-from .llamaparser import Parameter as Llamaparser

howdenparser-0.1.4/PKG-INFO

@@ -1,28 +0,0 @@
-Metadata-Version: 2.3
-Name: HowdenParser
-Version: 0.1.4
-Summary: A simple configuration manager with Pydantic and JSON export.
-License: MIT
-Keywords: config,configuration,pydantic,json
-Author: JesperThoftIllemannJ
-Author-email: jesper.jaeger@howdendanmark.dk
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.4
-Classifier: Programming Language :: Python :: 3.5
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Project-URL: Documentation, https://github.com/yourusername/config
-Project-URL: Homepage, https://github.com/yourusername/config
-Project-URL: Repository, https://github.com/yourusername/config
-Description-Content-Type: text/markdown
-
-.\build.ps1

howdenparser-0.1.4/README.md

@@ -1 +0,0 @@
-.\build.ps1