Metadata-Version: 2.4
Name: metaminer
Version: 0.3.5
Summary: Extract structured information from documents using AI
Author-email: Travis Adams <tadams792@gmail.com>
Maintainer-email: Travis Adams <tadams792@gmail.com>
License:                    GNU LESSER GENERAL PUBLIC LICENSE
                               Version 3, 29 June 2007
        
         Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
         Everyone is permitted to copy and distribute verbatim copies
         of this license document, but changing it is not allowed.
        
        
          This version of the GNU Lesser General Public License incorporates
        the terms and conditions of version 3 of the GNU General Public
        License, supplemented by the additional permissions listed below.
        
          0. Additional Definitions.
        
          As used herein, "this License" refers to version 3 of the GNU Lesser
        General Public License, and the "GNU GPL" refers to version 3 of the GNU
        General Public License.
        
          "The Library" refers to a covered work governed by this License,
        other than an Application or a Combined Work as defined below.
        
          An "Application" is any work that makes use of an interface provided
        by the Library, but which is not otherwise based on the Library.
        Defining a subclass of a class defined by the Library is deemed a mode
        of using an interface provided by the Library.
        
          A "Combined Work" is a work produced by combining or linking an
        Application with the Library.  The particular version of the Library
        with which the Combined Work was made is also called the "Linked
        Version".
        
          The "Minimal Corresponding Source" for a Combined Work means the
        Corresponding Source for the Combined Work, excluding any source code
        for portions of the Combined Work that, considered in isolation, are
        based on the Application, and not on the Linked Version.
        
          The "Corresponding Application Code" for a Combined Work means the
        object code and/or source code for the Application, including any data
        and utility programs needed for reproducing the Combined Work from the
        Application, but excluding the System Libraries of the Combined Work.
        
          1. Exception to Section 3 of the GNU GPL.
        
          You may convey a covered work under sections 3 and 4 of this License
        without being bound by section 3 of the GNU GPL.
        
          2. Conveying Modified Versions.
        
          If you modify a copy of the Library, and, in your modifications, a
        facility refers to a function or data to be supplied by an Application
        that uses the facility (other than as an argument passed when the
        facility is invoked), then you may convey a copy of the modified
        version:
        
           a) under this License, provided that you make a good faith effort to
           ensure that, in the event an Application does not supply the
           function or data, the facility still operates, and performs
           whatever part of its purpose remains meaningful, or
        
           b) under the GNU GPL, with none of the additional permissions of
           this License applicable to that copy.
        
          3. Object Code Incorporating Material from Library Header Files.
        
          The object code form of an Application may incorporate material from
        a header file that is part of the Library.  You may convey such object
        code under terms of your choice, provided that, if the incorporated
        material is not limited to numerical parameters, data structure
        layouts and accessors, or small macros, inline functions and templates
        (ten or fewer lines in length), you do both of the following:
        
           a) Give prominent notice with each copy of the object code that the
           Library is used in it and that the Library and its use are
           covered by this License.
        
           b) Accompany the object code with a copy of the GNU GPL and this license
           document.
        
          4. Combined Works.
        
          You may convey a Combined Work under terms of your choice that,
        taken together, effectively do not restrict modification of the
        portions of the Library contained in the Combined Work and reverse
        engineering for debugging such modifications, if you also do each of
        the following:
        
           a) Give prominent notice with each copy of the Combined Work that
           the Library is used in it and that the Library and its use are
           covered by this License.
        
           b) Accompany the Combined Work with a copy of the GNU GPL and this license
           document.
        
           c) For a Combined Work that displays copyright notices during
           execution, include the copyright notice for the Library among
           these notices, as well as a reference directing the user to the
           copies of the GNU GPL and this license document.
        
           d) Do one of the following:
        
               0) Convey the Minimal Corresponding Source under the terms of this
               License, and the Corresponding Application Code in a form
               suitable for, and under terms that permit, the user to
               recombine or relink the Application with a modified version of
               the Linked Version to produce a modified Combined Work, in the
               manner specified by section 6 of the GNU GPL for conveying
               Corresponding Source.
        
               1) Use a suitable shared library mechanism for linking with the
               Library.  A suitable mechanism is one that (a) uses at run time
               a copy of the Library already present on the user's computer
               system, and (b) will operate properly with a modified version
               of the Library that is interface-compatible with the Linked
               Version.
        
           e) Provide Installation Information, but only if you would otherwise
           be required to provide such information under section 6 of the
           GNU GPL, and only to the extent that such information is
           necessary to install and execute a modified version of the
           Combined Work produced by recombining or relinking the
           Application with a modified version of the Linked Version. (If
           you use option 4d0, the Installation Information must accompany
           the Minimal Corresponding Source and Corresponding Application
           Code. If you use option 4d1, you must provide the Installation
           Information in the manner specified by section 6 of the GNU GPL
           for conveying Corresponding Source.)
        
          5. Combined Libraries.
        
          You may place library facilities that are a work based on the
        Library side by side in a single library together with other library
        facilities that are not Applications and are not covered by this
        License, and convey such a combined library under terms of your
        choice, if you do both of the following:
        
           a) Accompany the combined library with a copy of the same work based
           on the Library, uncombined with any other library facilities,
           conveyed under the terms of this License.
        
           b) Give prominent notice with the combined library that part of it
           is a work based on the Library, and explaining where to find the
           accompanying uncombined form of the same work.
        
          6. Revised Versions of the GNU Lesser General Public License.
        
          The Free Software Foundation may publish revised and/or new versions
        of the GNU Lesser General Public License from time to time. Such new
        versions will be similar in spirit to the present version, but may
        differ in detail to address new problems or concerns.
        
          Each version is given a distinguishing version number. If the
        Library as you received it specifies that a certain numbered version
        of the GNU Lesser General Public License "or any later version"
        applies to it, you have the option of following the terms and
        conditions either of that published version or of any later version
        published by the Free Software Foundation. If the Library as you
        received it does not specify a version number of the GNU Lesser
        General Public License, you may choose any version of the GNU Lesser
        General Public License ever published by the Free Software Foundation.
        
          If the Library as you received it specifies that a proxy can decide
        whether future versions of the GNU Lesser General Public License shall
        apply, that proxy's public statement of acceptance of any version is
        permanent authorization for you to choose that version for the
        Library.
        
Project-URL: Homepage, https://github.com/travis4dams/metaminer
Project-URL: Repository, https://github.com/travis4dams/metaminer
Project-URL: Issues, https://github.com/travis4dams/metaminer/issues
Project-URL: PyPI, https://pypi.org/project/metaminer/
Project-URL: Documentation, https://github.com/travis4dams/metaminer#readme
Keywords: ai,document,extraction,nlp,openai,structured-data
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
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: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing :: General
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai>=1.0.0
Requires-Dist: pandas>=1.3.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: pypandoc>=1.5
Requires-Dist: PyMuPDF>=1.20.0
Requires-Dist: python-dateutil>=2.8.0
Requires-Dist: typing_extensions>=4.0.0; python_version < "3.9"
Provides-Extra: dev
Requires-Dist: pytest>=6.0; extra == "dev"
Requires-Dist: pytest-mock; extra == "dev"
Dynamic: license-file

# Metaminer

[![Tests](https://github.com/travis4dams/metaminer/workflows/Tests/badge.svg)](https://github.com/travis4dams/metaminer/actions)
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![License: LGPL v3](https://img.shields.io/badge/License-LGPL%20v3-blue.svg)](https://www.gnu.org/licenses/lgpl-3.0)

A tool for extracting structured information from documents using AI.

## Overview

Metaminer allows you to extract structured data from various document formats (PDF, DOCX, TXT, etc.) by asking natural language questions. It uses AI to analyze documents and return structured results in CSV or JSON format.

## Installation

```bash
pip install metaminer
```

### System Requirements

Metaminer requires [pandoc](https://pandoc.org/installing.html) to be installed on your system for document processing:

- **Ubuntu/Debian**: `sudo apt-get install pandoc`
- **macOS**: `brew install pandoc`
- **Windows**: Download from [pandoc.org](https://pandoc.org/installing.html)

**Note**: Metaminer uses pandoc for most document formats and PyMuPDF specifically for PDF processing to ensure optimal text extraction.

## Usage

### Command Line Interface

```bash
# Basic usage
metaminer questions.txt documents/

# Process single document
metaminer questions.txt document.pdf

# Save results to file
metaminer questions.txt documents/ --output results.csv

# JSON output format
metaminer questions.txt documents/ --format json --output results.json

# Custom API endpoint
metaminer questions.txt documents/ --base-url http://localhost:8000/api/v1

# Show normalized question structure with inferred types
metaminer questions.txt --show-questions --output questions_analysis.csv

# Verbose output for debugging
metaminer questions.txt documents/ --verbose

# Custom API key
metaminer questions.txt documents/ --api-key your-api-key
```

### Python Module

```python
from metaminer import Inquiry, extract_metadata, Config
from metaminer import extract_text, extract_text_from_directory, get_supported_extensions
from metaminer import DataTypeInferrer, infer_question_types, setup_logging
import pandas as pd

# From question file
inquiry = Inquiry.from_file("questions.txt")
df = inquiry.process_documents("documents/")

# Direct questions
inquiry = Inquiry(questions=["Who is the author?", "What is the publication date?"])
df = inquiry.process_documents(["doc1.pdf", "doc2.docx"])

# Single document
result = inquiry.process_document("document.pdf")

# Extract text directly
text = extract_text("document.pdf")

# Extract text from directory
texts = extract_text_from_directory("documents/")

# Get supported file extensions
extensions = get_supported_extensions()

# Use configuration
config = Config()
print(f"Default API endpoint: {config.base_url}")

# Set up logging
logger = setup_logging(config)

# Infer data types for questions
questions = ["Who is the author?", "What is the publication date?", "How many pages?"]
type_suggestions = infer_question_types(questions)
for q, suggestion in type_suggestions.items():
    print(f"{q}: {suggestion.suggested_type} - {suggestion.reasoning}")

# Use DataTypeInferrer directly
inferrer = DataTypeInferrer()
suggestion = inferrer.infer_single_type("What is the priority level?")
print(f"Suggested type: {suggestion.suggested_type}")
```

## Question Formats

### Text File (.txt)
One question per line:
```
Who is the author?
What is the publication date?
What is the main topic?
```

### CSV File (.csv)
Structured format with optional field names and data types:
```csv
question,field_name,data_type
"Who is the author?",author,str
"What is the publication date?",pub_date,date
"How many pages?",page_count,int
```

Supported data types:
- `str` (default): Text
- `int`: Integer numbers
- `float`: Decimal numbers
- `bool`: True/False values
- `date`: Date values (e.g., YYYY-MM-DD)
- `datetime`: Date and time values (e.g., YYYY-MM-DD HH:MM:SS)
- `list(type)`: Arrays of values (e.g., `list(str)`, `list(int)`, `list(date)`)
- `enum(val1,val2,val3)`: Single choice from discrete values
- `multi_enum(val1,val2,val3)`: Multiple choices from discrete values

## Supported Document Formats

Thanks to pandoc integration and PyMuPDF, metaminer supports:
- PDF (.pdf)
- Microsoft Word (.docx, .doc)
- OpenDocument (.odt)
- Rich Text Format (.rtf)
- Plain text (.txt)
- Markdown (.md)
- HTML (.html)
- EPUB (.epub)
- LaTeX (.tex)

## Configuration

### API Settings

By default, metaminer connects to a local AI server at `http://localhost:5001/api/v1`. You can customize this using environment variables or command-line options:

#### Environment Variables

```bash
# API Configuration
export OPENAI_API_KEY=your-api-key
export METAMINER_BASE_URL=http://your-api-server.com/api/v1
export METAMINER_MODEL=gpt-4
export METAMINER_TIMEOUT=60
export METAMINER_MAX_RETRIES=5

# Logging Configuration
export METAMINER_LOG_LEVEL=DEBUG
```

#### Command Line

```bash
metaminer questions.txt documents/ --base-url http://your-api-server.com/api/v1
```

#### Python

```python
from metaminer import Inquiry, Config

# Using configuration
config = Config()
inquiry = Inquiry.from_file("questions.txt", base_url="http://your-api-server.com/api/v1")

# Or set environment variables before creating Inquiry
import os
os.environ["METAMINER_BASE_URL"] = "http://your-api-server.com/api/v1"
inquiry = Inquiry.from_file("questions.txt")
```

### Configuration Defaults

- **Base URL**: `http://localhost:5001/api/v1`
- **Model**: `gpt-3.5-turbo`
- **Timeout**: 30 seconds
- **Max Retries**: 3
- **Log Level**: INFO
- **Max File Size**: 50MB

## Output Format

Results include the extracted information plus metadata:

```csv
author,pub_date,page_count,_document_path,_document_name
"John Doe","2023-01-15",25,"/path/to/doc1.pdf","doc1.pdf"
"Jane Smith","2023-02-20",18,"/path/to/doc2.pdf","doc2.pdf"
```

## Examples

### Research Paper Analysis
```txt
# questions.txt
Who are the authors?
What is the title?
What journal was this published in?
What is the publication year?
What is the main research question?
What methodology was used?
```

### Invoice Processing
```csv
question,field_name,data_type
"What is the invoice number?",invoice_number,str
"What is the total amount?",total_amount,float
"What is the invoice date?",invoice_date,date
"Who is the vendor?",vendor_name,str
"What is the due date?",due_date,date
```

### Legal Document Review
```txt
What type of document is this?
Who are the parties involved?
What is the effective date?
What is the termination date?
What are the key obligations?
```

### Document Classification with Enums
```csv
question,field_name,data_type
"What is the document type?",doc_type,"enum(report,memo,letter,invoice)"
"What topics are covered?",topics,"multi_enum(finance,hr,marketing,operations)"
"What is the priority level?",priority,"enum(low,medium,high,urgent)"
"What is the title?",title,str
"Who is the author?",author,str
```

**Note**: When using enum types in CSV files, make sure to quote the entire type specification to prevent CSV parsing issues with commas.

## Data Type Inference

Metaminer includes an intelligent data type inference system that can automatically suggest appropriate data types for your questions. This feature uses AI to analyze question content and recommend the most suitable data types.

### Using Type Inference

```python
from metaminer import DataTypeInferrer, infer_question_types

# Infer types for multiple questions
questions = [
    "Who is the author?",
    "What is the publication date?", 
    "How many pages are there?",
    "Is this document confidential?",
    "What is the priority level?"
]

type_suggestions = infer_question_types(questions)
for question_id, suggestion in type_suggestions.items():
    print(f"Question: {questions[int(question_id.split('_')[1])-1]}")
    print(f"Suggested type: {suggestion.suggested_type}")
    print(f"Reasoning: {suggestion.reasoning}")
    print(f"Alternatives: {suggestion.alternatives}")
    print()
```

### CLI Type Analysis

You can also analyze your questions from the command line:

```bash
# Analyze questions and show suggested types
metaminer questions.txt --show-questions

# Save analysis to file
metaminer questions.txt --show-questions --output question_analysis.csv
```

This will output a structured analysis showing:
- Original questions
- Suggested data types
- Field names
- Reasoning for type suggestions

### Type Inference Features

- **Smart Analysis**: Uses AI to understand question context and intent
- **Fallback Logic**: Provides sensible defaults when AI analysis fails
- **Validation**: Ensures all suggested types are valid metaminer data types
- **Multiple Suggestions**: Provides alternative type options
- **Reasoning**: Explains why each type was suggested

## Development

### Running Tests
```bash
pip install -e ".[dev]"
pytest
```

### Project Structure
```
metaminer/
├── __init__.py          # Main exports
├── inquiry.py           # Core Inquiry class
├── document_reader.py   # Document text extraction
├── question_parser.py   # Question file parsing
├── schema_builder.py    # Pydantic schema generation
├── datatype_inferrer.py # AI-powered data type inference
├── extractor.py         # Metadata extraction utilities
├── config.py           # Configuration management
├── cli.py              # Command-line interface
└── __main__.py         # Module entry point
```

## License

GNU Lesser General Public License v3.0 - see LICENSE file for details.

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.
