pdf-anonymizer-cli 0.3.1__tar.gz → 0.3.3__tar.gz

pdf_anonymizer_cli-0.3.3/PKG-INFO

@@ -0,0 +1,144 @@
+Metadata-Version: 2.4
+Name: pdf-anonymizer-cli
+Version: 0.3.3
+Summary: CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs.
+Author-email: Leonid Ganeline <leo.gan.57@gmail.com>
+License: MIT
+Project-URL: repository, https://github.com/leo-gan/anonymizer
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: typer
+Requires-Dist: rich
+Requires-Dist: pdf-anonymizer-core
+
+# 🦉🫥 PDF Anonymizer CLI
+
+A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
+
+- **High-Quality Anonymization**: Leverages LLMs to identify and replace Personally Identifiable Information (PII) with high accuracy.
+- **Large File Support**: Consistently anonymizes large files (tested up to 1GB).
+- **Multi-Provider & Cost-Effective**: Free to use with local [Ollama](https://ollama.com/) models. It also supports major providers like [OpenAI](https://openai.com/), [Anthropic](https://www.anthropic.com/), [Google](https://ai.google.com/), [Hugging Face](https://huggingface.co/), and [OpenRouter](https://openrouter.ai/).
+- **Reversible**: Supports deanonymization to recover original data when needed.
+- **Multi-Format**: Works with PDF, Markdown, and plain text files.
+
+
+## Installation
+
+Install the CLI with your favorite package manager. To use a specific LLM provider, you must install the corresponding extra.
+
+- **Google**: `pip install "pdf-anonymizer-cli[google]"`
+- **Ollama**: `pip install "pdf-anonymizer-cli[ollama]"`
+- **Hugging Face**: `pip install "pdf-anonymizer-cli[huggingface]"`
+- **OpenRouter**: `pip install "pdf-anonymizer-cli[openrouter]"`
+- **OpenAI**: `pip install "pdf-anonymizer-cli[openai]"`
+- **Anthropic**: `pip install "pdf-anonymizer-cli[anthropic]"`
+
+You can also install multiple extras at once:
+
+```bash
+pip install "pdf-anonymizer-cli[google,openrouter]"
+```
+
+This installs the `pdf-anonymizer` executable.
+
+
+## Environment Variables
+
+The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
+
+- `GOOGLE_API_KEY`: Required when using Google models.
+- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
+- `OPENROUTER_API_KEY`: Required when using OpenRouter models.
+- `OPENAI_API_KEY`: Required when using OpenAI models.
+- `ANTHROPIC_API_KEY`: Required when using Anthropic models.
+- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using Ollama models.
+
+Example `.env` file:
+```env
+GOOGLE_API_KEY="YOUR_API_KEY_HERE"
+HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
+OPENROUTER_API_KEY="YOUR_OPENROUTER_KEY"
+```
+
+## Usage
+
+### Anonymize
+
+The `run` command anonymizes one or more files.
+
+```bash
+pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
+  [--characters-to-anonymize INTEGER] \
+  [--prompt-name {simple|detailed}] \
+  [--model-name TEXT] \
+  [--anonymized-entities PATH]
+```
+
+**Arguments**:
+- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
+
+**Options**:
+- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
+- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
+- `--model-name TEXT`: The language model to use.
+- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
+
+**Models**:
+You can use any of the predefined models below, or specify a new model using the format `"provider/model-name"`. 
+For example: `--model-name "google/gemini-flash-latest"`.
+
+- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
+- **Ollama**: `gemma:7b`, `phi4-mini`.
+- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
+- **OpenRouter**: `openai/gpt-4o`, `google/gemini-pro`.
+- **OpenAI**: `gpt-4o`, `gpt-5`.
+- **Anthropic**: `claude-4-sonet`, `claude-4.5-sonet`.
+
+### Examples
+
+**Basic anonymization with the default model (Google)**:
+```bash
+pdf-anonymizer run document.pdf
+```
+
+**A new model (Google) and a simple prompt**:
+```bash
+pdf-anonymizer run notes.md --model-name "google/gemini-flash-latest" --prompt-name simple
+```
+
+**Using an OpenRouter model**:
+```bash
+pdf-anonymizer run report.pdf --model-name "openai/gpt-4o"
+```
+
+### Deanonymize
+
+The `deanonymize` command reverts anonymization using a mapping file.
+
+```bash
+pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
+```
+
+**Arguments**:
+- `ANONYMIZED_FILE`: Path to the anonymized text file.
+- `MAPPING_FILE`: Path to the JSON mapping file.
+
+**Example**:
+```bash
+pdf-anonymizer deanonymize \
+    data/anonymized/document.anonymized.md \
+    data/mappings/document.mapping.json
+```
+
+This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.

pdf_anonymizer_cli-0.3.3/README.md

@@ -0,0 +1,131 @@
+# 🦉🫥 PDF Anonymizer CLI
+
+A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
+
+- **High-Quality Anonymization**: Leverages LLMs to identify and replace Personally Identifiable Information (PII) with high accuracy.
+- **Large File Support**: Consistently anonymizes large files (tested up to 1GB).
+- **Multi-Provider & Cost-Effective**: Free to use with local [Ollama](https://ollama.com/) models. It also supports major providers like [OpenAI](https://openai.com/), [Anthropic](https://www.anthropic.com/), [Google](https://ai.google.com/), [Hugging Face](https://huggingface.co/), and [OpenRouter](https://openrouter.ai/).
+- **Reversible**: Supports deanonymization to recover original data when needed.
+- **Multi-Format**: Works with PDF, Markdown, and plain text files.
+
+
+## Installation
+
+Install the CLI with your favorite package manager. To use a specific LLM provider, you must install the corresponding extra.
+
+- **Google**: `pip install "pdf-anonymizer-cli[google]"`
+- **Ollama**: `pip install "pdf-anonymizer-cli[ollama]"`
+- **Hugging Face**: `pip install "pdf-anonymizer-cli[huggingface]"`
+- **OpenRouter**: `pip install "pdf-anonymizer-cli[openrouter]"`
+- **OpenAI**: `pip install "pdf-anonymizer-cli[openai]"`
+- **Anthropic**: `pip install "pdf-anonymizer-cli[anthropic]"`
+
+You can also install multiple extras at once:
+
+```bash
+pip install "pdf-anonymizer-cli[google,openrouter]"
+```
+
+This installs the `pdf-anonymizer` executable.
+
+
+## Environment Variables
+
+The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
+
+- `GOOGLE_API_KEY`: Required when using Google models.
+- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
+- `OPENROUTER_API_KEY`: Required when using OpenRouter models.
+- `OPENAI_API_KEY`: Required when using OpenAI models.
+- `ANTHROPIC_API_KEY`: Required when using Anthropic models.
+- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using Ollama models.
+
+Example `.env` file:
+```env
+GOOGLE_API_KEY="YOUR_API_KEY_HERE"
+HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
+OPENROUTER_API_KEY="YOUR_OPENROUTER_KEY"
+```
+
+## Usage
+
+### Anonymize
+
+The `run` command anonymizes one or more files.
+
+```bash
+pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
+  [--characters-to-anonymize INTEGER] \
+  [--prompt-name {simple|detailed}] \
+  [--model-name TEXT] \
+  [--anonymized-entities PATH]
+```
+
+**Arguments**:
+- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
+
+**Options**:
+- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
+- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
+- `--model-name TEXT`: The language model to use.
+- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
+
+**Models**:
+You can use any of the predefined models below, or specify a new model using the format `"provider/model-name"`. 
+For example: `--model-name "google/gemini-flash-latest"`.
+
+- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
+- **Ollama**: `gemma:7b`, `phi4-mini`.
+- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
+- **OpenRouter**: `openai/gpt-4o`, `google/gemini-pro`.
+- **OpenAI**: `gpt-4o`, `gpt-5`.
+- **Anthropic**: `claude-4-sonet`, `claude-4.5-sonet`.
+
+### Examples
+
+**Basic anonymization with the default model (Google)**:
+```bash
+pdf-anonymizer run document.pdf
+```
+
+**A new model (Google) and a simple prompt**:
+```bash
+pdf-anonymizer run notes.md --model-name "google/gemini-flash-latest" --prompt-name simple
+```
+
+**Using an OpenRouter model**:
+```bash
+pdf-anonymizer run report.pdf --model-name "openai/gpt-4o"
+```
+
+### Deanonymize
+
+The `deanonymize` command reverts anonymization using a mapping file.
+
+```bash
+pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
+```
+
+**Arguments**:
+- `ANONYMIZED_FILE`: Path to the anonymized text file.
+- `MAPPING_FILE`: Path to the JSON mapping file.
+
+**Example**:
+```bash
+pdf-anonymizer deanonymize \
+    data/anonymized/document.anonymized.md \
+    data/mappings/document.mapping.json
+```
+
+This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.

{pdf_anonymizer_cli-0.3.1 → pdf_anonymizer_cli-0.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pdf-anonymizer-cli"
-version = "0.3.1"
+version = "0.3.3"
 description = "CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs."
 authors = [{ name = "Leonid Ganeline", email = "leo.gan.57@gmail.com" }]
 license = { text = "MIT" }

{pdf_anonymizer_cli-0.3.1 → pdf_anonymizer_cli-0.3.3}/src/pdf_anonymizer_cli/cli.py

@@ -7,15 +7,14 @@ from typing import Dict, List, Optional
 import typer
 from dotenv import load_dotenv
 from pdf_anonymizer_core.conf import (
-    DEFAULT_CHARACTERS_TO_ANONYMIZE,
-    DEFAULT_MODEL_NAME,
-    DEFAULT_PROMPT_NAME,
-    ModelName,
-    ModelProvider,
+    DEFAULT_LOG_FILE,
+    ConfigProfile,
     PromptEnum,
-    get_enum_value,
+    get_config_for_profile,
+    get_provider_and_model_name,
 )
 from pdf_anonymizer_core.core import anonymize_file
+from pdf_anonymizer_core.llm_provider import configure_cache
 from pdf_anonymizer_core.prompts import detailed, simple
 from pdf_anonymizer_core.utils import (
     consolidate_mapping,
@@ -24,10 +23,11 @@ from pdf_anonymizer_core.utils import (
 )
 from typing_extensions import Annotated
 
+# Setup logging using log file configured in conf.py
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
-    handlers=[logging.FileHandler("app.log"), logging.StreamHandler()],
+    handlers=[logging.FileHandler(DEFAULT_LOG_FILE), logging.StreamHandler()],
 )
 
 app = typer.Typer()
@@ -54,24 +54,34 @@ def run(
             resolve_path=True,
         ),
     ],
+    config_profile: Annotated[
+        ConfigProfile,
+        typer.Option(
+            "--config-profile",
+            "-p",
+            help="The configuration profile to use (best-quality, best-speed, best-cost).",
+            case_sensitive=False,
+        ),
+    ] = ConfigProfile.BEST_SPEED,
     characters_to_anonymize: Annotated[
-        int,
-        typer.Option(help="Number of characters to send for anonymization in one go."),
-    ] = DEFAULT_CHARACTERS_TO_ANONYMIZE,
+        Optional[int],
+        typer.Option(
+            help="Override number of characters to send for anonymization in one go (chunk size)."
+        ),
+    ] = None,
     prompt_name: Annotated[
-        PromptEnum,
+        Optional[PromptEnum],
         typer.Option(
-            help="The name of the prompt to use for anonymization.",
+            help="Override prompt template to use for anonymization.",
             case_sensitive=False,
         ),
-    ] = get_enum_value(PromptEnum, DEFAULT_PROMPT_NAME),
+    ] = None,
     model_name: Annotated[
-        ModelName,
+        Optional[str],
         typer.Option(
-            help="The name of the model to use for anonymization.",
-            case_sensitive=False,
+            help="Override the language model to use for anonymization.",
         ),
-    ] = get_enum_value(ModelName, DEFAULT_MODEL_NAME),
+    ] = None,
     anonymized_entities: Annotated[
         Optional[Path],
         typer.Option(
@@ -88,34 +98,45 @@ def run(
 ) -> None:
     """
     Anonymize one or more files by replacing PII with anonymized placeholders.
-
-    Args:
-        file_paths: List of paths to files to process.
-        characters_to_anonymize: Number of characters to process in each chunk.
-        prompt_name: The prompt template to use for anonymization.
-        model_name: The language model to use for anonymization.
-        anonymized_entities: A file with a list of entities to anonymize.
     """
     load_environment()
 
-    if model_name.provider == ModelProvider.GOOGLE:
-        if "gemini" in model_name.value and not os.getenv("GOOGLE_API_KEY"):
+    # Get configuration based on profile and optional user overrides
+    config = get_config_for_profile(
+        profile=config_profile,
+        model_name=model_name,
+        prompt_name=prompt_name,
+        chunk_size=characters_to_anonymize,
+    )
+
+    # Configure LLM caching with values from configuration
+    configure_cache(
+        enabled=config.enable_cache,
+        cache_dir=config.cache_dir,
+        cache_file=config.cache_file,
+    )
+
+    provider_name, _ = get_provider_and_model_name(config.model_name)
+    if provider_name == "google":
+        if "gemini" in config.model_name and not os.getenv("GOOGLE_API_KEY"):
             logging.error(
                 "Error: GOOGLE_API_KEY not found. Please set it in the .env file."
             )
             sys.exit(1)
 
+    logging.info(f"Using configuration profile: {config_profile.value}")
     logging.info(f"  --file-paths: {file_paths}")
-    logging.info(f"  --characters-to-anonymize: {characters_to_anonymize}")
-    logging.info(f"  --model-name: {model_name.value}")
+    logging.info(f"  --chunk-size: {config.chunk_size}")
+    logging.info(f"  --chunk-overlap: {config.chunk_overlap}")
+    logging.info(f"  --model-name: {config.model_name}")
 
     # Select the appropriate prompt template
     prompt_templates: Dict[str, str] = {
-        PromptEnum.simple: simple.prompt_template,
-        PromptEnum.detailed: detailed.prompt_template,
+        PromptEnum.simple.value: simple.prompt_template,
+        PromptEnum.detailed.value: detailed.prompt_template,
     }
-    prompt_template: str = prompt_templates[prompt_name]
-    logging.info(f"  --prompt-name: {prompt_name.value}")
+    prompt_template: str = prompt_templates[config.prompt_name]
+    logging.info(f"  --prompt-name: {config.prompt_name}")
 
     entities_to_anonymize = None
     if anonymized_entities:
@@ -129,11 +150,16 @@ def run(
         logging.info("=" * 40)
         logging.info(f"Processing file {i}/{len(file_paths)}: {file_path}")
         full_anonymized_text, final_mapping = anonymize_file(
-            str(file_path),
-            characters_to_anonymize,
-            prompt_template,
-            model_name.value,
-            entities_to_anonymize,
+            file_path=str(file_path),
+            characters_to_anonymize=config.chunk_size,
+            prompt_template=prompt_template,
+            model_name=config.model_name,
+            anonymized_entities=entities_to_anonymize,
+            chunk_overlap=config.chunk_overlap,
+            regex_patterns=config.regex_patterns,
+            max_retries=config.max_retries,
+            base_retry_delay=config.base_retry_delay,
+            max_retry_delay=config.max_retry_delay,
         )
 
         if full_anonymized_text and final_mapping:
@@ -183,10 +209,6 @@ def deanonymize(
 ) -> None:
     """
     Deanonymize a file using a mapping file.
-
-    Args:
-        anonymized_file: Path to the anonymized file.
-        mapping_file: Path to the mapping file.
     """
     logging.info(f"Deanonymizing '{anonymized_file}' using '{mapping_file}'")
     deanonymized_output_file, stats_file = deanonymize_file(

pdf_anonymizer_cli-0.3.3/src/pdf_anonymizer_cli.egg-info/PKG-INFO

@@ -0,0 +1,144 @@
+Metadata-Version: 2.4
+Name: pdf-anonymizer-cli
+Version: 0.3.3
+Summary: CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs.
+Author-email: Leonid Ganeline <leo.gan.57@gmail.com>
+License: MIT
+Project-URL: repository, https://github.com/leo-gan/anonymizer
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: typer
+Requires-Dist: rich
+Requires-Dist: pdf-anonymizer-core
+
+# 🦉🫥 PDF Anonymizer CLI
+
+A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
+
+- **High-Quality Anonymization**: Leverages LLMs to identify and replace Personally Identifiable Information (PII) with high accuracy.
+- **Large File Support**: Consistently anonymizes large files (tested up to 1GB).
+- **Multi-Provider & Cost-Effective**: Free to use with local [Ollama](https://ollama.com/) models. It also supports major providers like [OpenAI](https://openai.com/), [Anthropic](https://www.anthropic.com/), [Google](https://ai.google.com/), [Hugging Face](https://huggingface.co/), and [OpenRouter](https://openrouter.ai/).
+- **Reversible**: Supports deanonymization to recover original data when needed.
+- **Multi-Format**: Works with PDF, Markdown, and plain text files.
+
+
+## Installation
+
+Install the CLI with your favorite package manager. To use a specific LLM provider, you must install the corresponding extra.
+
+- **Google**: `pip install "pdf-anonymizer-cli[google]"`
+- **Ollama**: `pip install "pdf-anonymizer-cli[ollama]"`
+- **Hugging Face**: `pip install "pdf-anonymizer-cli[huggingface]"`
+- **OpenRouter**: `pip install "pdf-anonymizer-cli[openrouter]"`
+- **OpenAI**: `pip install "pdf-anonymizer-cli[openai]"`
+- **Anthropic**: `pip install "pdf-anonymizer-cli[anthropic]"`
+
+You can also install multiple extras at once:
+
+```bash
+pip install "pdf-anonymizer-cli[google,openrouter]"
+```
+
+This installs the `pdf-anonymizer` executable.
+
+
+## Environment Variables
+
+The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
+
+- `GOOGLE_API_KEY`: Required when using Google models.
+- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
+- `OPENROUTER_API_KEY`: Required when using OpenRouter models.
+- `OPENAI_API_KEY`: Required when using OpenAI models.
+- `ANTHROPIC_API_KEY`: Required when using Anthropic models.
+- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using Ollama models.
+
+Example `.env` file:
+```env
+GOOGLE_API_KEY="YOUR_API_KEY_HERE"
+HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
+OPENROUTER_API_KEY="YOUR_OPENROUTER_KEY"
+```
+
+## Usage
+
+### Anonymize
+
+The `run` command anonymizes one or more files.
+
+```bash
+pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
+  [--characters-to-anonymize INTEGER] \
+  [--prompt-name {simple|detailed}] \
+  [--model-name TEXT] \
+  [--anonymized-entities PATH]
+```
+
+**Arguments**:
+- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
+
+**Options**:
+- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
+- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
+- `--model-name TEXT`: The language model to use.
+- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
+
+**Models**:
+You can use any of the predefined models below, or specify a new model using the format `"provider/model-name"`. 
+For example: `--model-name "google/gemini-flash-latest"`.
+
+- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
+- **Ollama**: `gemma:7b`, `phi4-mini`.
+- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
+- **OpenRouter**: `openai/gpt-4o`, `google/gemini-pro`.
+- **OpenAI**: `gpt-4o`, `gpt-5`.
+- **Anthropic**: `claude-4-sonet`, `claude-4.5-sonet`.
+
+### Examples
+
+**Basic anonymization with the default model (Google)**:
+```bash
+pdf-anonymizer run document.pdf
+```
+
+**A new model (Google) and a simple prompt**:
+```bash
+pdf-anonymizer run notes.md --model-name "google/gemini-flash-latest" --prompt-name simple
+```
+
+**Using an OpenRouter model**:
+```bash
+pdf-anonymizer run report.pdf --model-name "openai/gpt-4o"
+```
+
+### Deanonymize
+
+The `deanonymize` command reverts anonymization using a mapping file.
+
+```bash
+pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
+```
+
+**Arguments**:
+- `ANONYMIZED_FILE`: Path to the anonymized text file.
+- `MAPPING_FILE`: Path to the JSON mapping file.
+
+**Example**:
+```bash
+pdf-anonymizer deanonymize \
+    data/anonymized/document.anonymized.md \
+    data/mappings/document.mapping.json
+```
+
+This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.
+
+---
+
+## See Also
+
+- **[Main Documentation](https://leo-gan.github.io/anonymizer/)** — Full guides including the 101 course.
+- **[Core Package README](../pdf-anonymizer-core/README.md)** — Details on the underlying library.
+- **[Recipes & Common Workflows](https://leo-gan.github.io/anonymizer/project/recipes/)** — Practical CLI usage examples (profiles, batching, external workflows, etc.).
+- **[CLI Reference (full)](https://leo-gan.github.io/anonymizer/project/cli-usage/)** — Complete command reference on the docs site.
+- **[Troubleshooting](https://leo-gan.github.io/anonymizer/project/troubleshooting/)** — Help with common CLI problems.
+- **[Architecture](https://leo-gan.github.io/anonymizer/project/architecture/)** — How the CLI and core work together.

pdf_anonymizer_cli-0.3.1/PKG-INFO

@@ -1,103 +0,0 @@
-Metadata-Version: 2.4
-Name: pdf-anonymizer-cli
-Version: 0.3.1
-Summary: CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs.
-Author-email: Leonid Ganeline <leo.gan.57@gmail.com>
-License: MIT
-Project-URL: repository, https://github.com/leo-gan/anonymizer
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-Requires-Dist: typer
-Requires-Dist: rich
-Requires-Dist: pdf-anonymizer-core
-
-# 🦉🫥 PDF Anonymizer CLI
-
-A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
-
-## Installation
-
-This project uses `uv` and is structured as a monorepo. The dependencies for the CLI and its core library are managed at the root of the project.
-
-1.  **Install `uv`**: Follow the [official installation instructions](https://astral.sh/docs/uv#installation).
-2.  **Install dependencies from the repository root**:
-    ```bash
-    # From the repository root
-    uv sync
-    ```
-    This installs the `pdf-anonymizer` executable.
-
-## Environment Variables
-
-The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
-
-- `GOOGLE_API_KEY`: Required when using Google's Gemini models.
-- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using local Ollama models.
-- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
-
-Example `.env` file:
-```env
-GOOGLE_API_KEY="YOUR_API_KEY_HERE"
-HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
-```
-
-## Usage
-
-### Anonymize
-
-The `run` command anonymizes one or more files.
-
-```bash
-pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
-  [--characters-to-anonymize INTEGER] \
-  [--prompt-name {simple|detailed}] \
-  [--model-name TEXT] \
-  [--anonymized-entities PATH]
-```
-
-**Arguments**:
-- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
-
-**Options**:
-- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
-- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
-- `--model-name TEXT`: The language model to use.
-- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
-
-**Models**:
-- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
-- **Ollama**: `gemma:7b`, `phi4-mini`.
-- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
-
-### Examples
-
-**Basic anonymization**:
-```bash
-pdf-anonymizer run document.pdf
-```
-
-**Custom model and prompt**:
-```bash
-pdf-anonymizer run notes.md --model-name phi4-mini --prompt-name simple
-```
-
-### Deanonymize
-
-The `deanonymize` command reverts anonymization using a mapping file.
-
-```bash
-pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
-```
-
-**Arguments**:
-- `ANONYMIZED_FILE`: Path to the anonymized text file.
-- `MAPPING_FILE`: Path to the JSON mapping file.
-
-**Example**:
-```bash
-pdf-anonymizer deanonymize \
-    data/anonymized/document.anonymized.md \
-    data/mappings/document.mapping.json
-```
-
-This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.

pdf_anonymizer_cli-0.3.1/README.md

@@ -1,90 +0,0 @@
-# 🦉🫥 PDF Anonymizer CLI
-
-A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
-
-## Installation
-
-This project uses `uv` and is structured as a monorepo. The dependencies for the CLI and its core library are managed at the root of the project.
-
-1.  **Install `uv`**: Follow the [official installation instructions](https://astral.sh/docs/uv#installation).
-2.  **Install dependencies from the repository root**:
-    ```bash
-    # From the repository root
-    uv sync
-    ```
-    This installs the `pdf-anonymizer` executable.
-
-## Environment Variables
-
-The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
-
-- `GOOGLE_API_KEY`: Required when using Google's Gemini models.
-- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using local Ollama models.
-- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
-
-Example `.env` file:
-```env
-GOOGLE_API_KEY="YOUR_API_KEY_HERE"
-HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
-```
-
-## Usage
-
-### Anonymize
-
-The `run` command anonymizes one or more files.
-
-```bash
-pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
-  [--characters-to-anonymize INTEGER] \
-  [--prompt-name {simple|detailed}] \
-  [--model-name TEXT] \
-  [--anonymized-entities PATH]
-```
-
-**Arguments**:
-- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
-
-**Options**:
-- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
-- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
-- `--model-name TEXT`: The language model to use.
-- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
-
-**Models**:
-- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
-- **Ollama**: `gemma:7b`, `phi4-mini`.
-- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
-
-### Examples
-
-**Basic anonymization**:
-```bash
-pdf-anonymizer run document.pdf
-```
-
-**Custom model and prompt**:
-```bash
-pdf-anonymizer run notes.md --model-name phi4-mini --prompt-name simple
-```
-
-### Deanonymize
-
-The `deanonymize` command reverts anonymization using a mapping file.
-
-```bash
-pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
-```
-
-**Arguments**:
-- `ANONYMIZED_FILE`: Path to the anonymized text file.
-- `MAPPING_FILE`: Path to the JSON mapping file.
-
-**Example**:
-```bash
-pdf-anonymizer deanonymize \
-    data/anonymized/document.anonymized.md \
-    data/mappings/document.mapping.json
-```
-
-This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.

pdf_anonymizer_cli-0.3.1/src/pdf_anonymizer_cli.egg-info/PKG-INFO

@@ -1,103 +0,0 @@
-Metadata-Version: 2.4
-Name: pdf-anonymizer-cli
-Version: 0.3.1
-Summary: CLI for a tool to anonymize PDF, Markdown, and plain text files using LLMs.
-Author-email: Leonid Ganeline <leo.gan.57@gmail.com>
-License: MIT
-Project-URL: repository, https://github.com/leo-gan/anonymizer
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-Requires-Dist: typer
-Requires-Dist: rich
-Requires-Dist: pdf-anonymizer-core
-
-# 🦉🫥 PDF Anonymizer CLI
-
-A command-line interface for anonymizing PDF, Markdown, and plain text files using LLMs.
-
-## Installation
-
-This project uses `uv` and is structured as a monorepo. The dependencies for the CLI and its core library are managed at the root of the project.
-
-1.  **Install `uv`**: Follow the [official installation instructions](https://astral.sh/docs/uv#installation).
-2.  **Install dependencies from the repository root**:
-    ```bash
-    # From the repository root
-    uv sync
-    ```
-    This installs the `pdf-anonymizer` executable.
-
-## Environment Variables
-
-The CLI will automatically load a `.env` file from the current directory or any parent directory. For consistency, it's recommended to place a single `.env` file at the root of the repository.
-
-- `GOOGLE_API_KEY`: Required when using Google's Gemini models.
-- `OLLAMA_HOST`: Optional, defaults to `http://localhost:11434` when using local Ollama models.
-- `HUGGING_FACE_TOKEN`: Required when using Hugging Face models. You can get a token from [here](https://huggingface.co/docs/hub/security-tokens).
-
-Example `.env` file:
-```env
-GOOGLE_API_KEY="YOUR_API_KEY_HERE"
-HUGGING_FACE_TOKEN="YOUR_HF_TOKEN_HERE"
-```
-
-## Usage
-
-### Anonymize
-
-The `run` command anonymizes one or more files.
-
-```bash
-pdf-anonymizer run FILE_PATH [FILE_PATH ...] \
-  [--characters-to-anonymize INTEGER] \
-  [--prompt-name {simple|detailed}] \
-  [--model-name TEXT] \
-  [--anonymized-entities PATH]
-```
-
-**Arguments**:
-- `FILE_PATH`: Path to one or several PDF, Markdown, or text files for anonymization.
-
-**Options**:
-- `--characters-to-anonymize INTEGER`: Number of characters to process in each chunk (default: `100000`).
-- `--prompt-name [simple|detailed]`: The prompt template to use (default: `detailed`).
-- `--model-name TEXT`: The language model to use.
-- `--anonymized-entities PATH`: Path to a file with a list of entities to anonymize.
-
-**Models**:
-- **Google**: `gemini-2.5-pro`, `gemini-2.5-flash` (default), `gemini-2.5-flash-lite`.
-- **Ollama**: `gemma:7b`, `phi4-mini`.
-- **Hugging Face**: `openai/gpt-oss-20b`, `mistralai/Mistral-7B-Instruct-v0.1`, `HuggingFaceH4/zephyr-7b-beta`.
-
-### Examples
-
-**Basic anonymization**:
-```bash
-pdf-anonymizer run document.pdf
-```
-
-**Custom model and prompt**:
-```bash
-pdf-anonymizer run notes.md --model-name phi4-mini --prompt-name simple
-```
-
-### Deanonymize
-
-The `deanonymize` command reverts anonymization using a mapping file.
-
-```bash
-pdf-anonymizer deanonymize ANONYMIZED_FILE MAPPING_FILE
-```
-
-**Arguments**:
-- `ANONYMIZED_FILE`: Path to the anonymized text file.
-- `MAPPING_FILE`: Path to the JSON mapping file.
-
-**Example**:
-```bash
-pdf-anonymizer deanonymize \
-    data/anonymized/document.anonymized.md \
-    data/mappings/document.mapping.json
-```
-
-This will create a deanonymized version of the file at `data/deanonymized/document.deanonymized.md`.