### Initialize OCRProcessor with Different Model (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Imports the `OCRProcessor` class and creates a new instance, specifying a different Ollama model (`llama3.2-vision:11b`) to be used for subsequent OCR operations. Requires the `ollama_ocr` library and the specified model installed in Ollama.

```python
from ollama_ocr import OCRProcessor

# Create an instance
ocr = OCRProcessor(model_name='llama3.2-vision:11b')


```

--------------------------------

### Initialize OCRProcessor and Process PDF for Text (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Initializes the `OCRProcessor` with a specified model (`granite3.2-vision`), processes a single PDF file to extract text, and prints the result. Requires the `ollama_ocr` library and the specified model installed in Ollama.

```python
from ollama_ocr import OCRProcessor

# Create an instance
ocr = OCRProcessor(model_name='granite3.2-vision')

# Test with an image (replace with your image path)
result = ocr.process_image(
    image_path="input\pdf.pdf",
    format_type="text",
    language="eng",
)
print(result)
```

--------------------------------

### Install Ollama-OCR Dependencies

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

Installs the required Python packages listed in the requirements.txt file using pip.

```bash
pip install -r requirements.txt
```

--------------------------------

### Installing Ollama OCR Package

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

This command installs the Ollama OCR Python package using pip, making it available for use in your Python projects.

```bash
pip install ollama-ocr
```

--------------------------------

### Initialize OCRProcessor with Different Model

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Imports the `OCRProcessor` class and creates a new instance, specifying a different Ollama model name ('llama3.2-vision:11b') for subsequent processing tasks.

```python
from ollama_ocr import OCRProcessor

# Create an instance
ocr = OCRProcessor(model_name='llama3.2-vision:11b')
```

--------------------------------

### Process Single Image for Key-Value Output

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file. It specifically requests the output to be formatted as key-value pairs and prints the resulting structure.

```python
# Test with key-value format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="key_value"
)
print(result)
```

--------------------------------

### Perform Batch Processing and Print Statistics

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Initiates batch processing on a specified input directory using the initialized `OCRProcessor`. It then prints the summary statistics obtained from the batch processing results.

```python
# Test batch processing
batch_results = ocr.process_batch('input')
print(batch_results['statistics'])
```

--------------------------------

### Process Single Image for Structured Output

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file. It requests the output in a structured format and prints the resulting structured data.

```python
#  structured format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="structured"
)
print(result)
```

--------------------------------

### Process Single Image for Key-Value (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file (`img.png`), requesting the output in "key_value" format, and prints the resulting structured data. Assumes `OCRProcessor` has been initialized.

```python
# Test with key-value format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="key_value"
)
print(result)
```

--------------------------------

### Print Detailed Batch Processing Statistics (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Prints a formatted summary of the batch processing statistics obtained from the `batch_results` dictionary, including total, successful, and failed counts. Assumes `process_batch` has already been called and `batch_results` is available.

```python
# Print statistics
print("\nProcessing Statistics:")
print(f"Total images: {batch_results['statistics']['total']}")
print(f"Successfully processed: {batch_results['statistics']['successful']}")
print(f"Failed: {batch_results['statistics']['failed']}")
```

--------------------------------

### Initialize OCRProcessor and Process Single Image for Text

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Initializes the `OCRProcessor` with a specified Ollama model and processes a single image file (e.g., PDF) to extract text. It prints the resulting text output.

```python
from ollama_ocr import OCRProcessor

# Create an instance
ocr = OCRProcessor(model_name='granite3.2-vision')

# Test with an image (replace with your image path)
result = ocr.process_image(
    image_path="input\pdf.pdf",
    format_type="text",
    language="eng"
)
print(result)
```

--------------------------------

### Process Single Image for Text Output

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file. It requests the output in a plain text format and prints the extracted text.

```python
# Text
result = ocr.process_image(
    image_path="input\img.png",
    format_type="text"
)
print(result)
```

--------------------------------

### Process Single Image for JSON Output

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file. It requests the output to be formatted as a JSON object and prints the resulting JSON string.

```python
#  json format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="json"
)
print(result)
```

--------------------------------

### Iterate and Print Text from Successful Batch Results

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Loops through the successfully processed files contained within the batch results. For each file, it prints the file path followed by the extracted text.

```python
# Get text from all successfully processed images
for file_path, text in batch_results['results'].items():
    print(f"\nFile: {file_path}")
    print("-" * 50)
    print(f"Extracted Text: {text}")
```

--------------------------------

### Perform Batch Processing and Print Statistics (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Uses the initialized `OCRProcessor` to process all images within a specified directory ('input') in batch mode and prints the statistics summary from the results. Requires a directory containing images and an initialized `OCRProcessor` instance.

```python
# Test batch processing
batch_results = ocr.process_batch('input')
print(batch_results['statistics'])
```

--------------------------------

### Process Single Image for Structured Output (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file (`img.png`), requesting the output in "structured" format, and prints the resulting structured data. Assumes `OCRProcessor` has been initialized.

```python
#  structured format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="structured"
)
print(result)
```

--------------------------------

### Process Single Image for Text (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file (`img.png`), requesting the output in "text" format, and prints the extracted plain text. Assumes `OCRProcessor` has been initialized.

```python
# Text
result = ocr.process_image(
    image_path="input\img.png",
    format_type="text"
)
print(result)
```

--------------------------------

### Process Single Image for JSON (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Uses the initialized `OCRProcessor` to process a single image file (`img.png`), requesting the output in "json" format, and prints the resulting JSON structure. Assumes `OCRProcessor` has been initialized.

```python
#  json format
result = ocr.process_image(
    image_path="input\img.png",
    format_type="json"
)
print(result)
```

--------------------------------

### Print Detailed Batch Processing Statistics

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Accesses and prints detailed statistics from the results of a batch processing operation, including the total number of images processed, successfully processed images, and failed images.

```python
# Print statistics
print("\nProcessing Statistics:")
print(f"Total images: {batch_results['statistics']['total']}")
print(f"Successfully processed: {batch_results['statistics']['successful']}")
print(f"Failed: {batch_results['statistics']['failed']}")
```

--------------------------------

### Check and Print Batch Processing Errors

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example_notebooks/example.ipynb

Checks if the batch processing results contain any errors. If errors are present, it iterates through them and prints the file path and the specific error message for each file that failed processing.

```python
# Check if there were any errors
if batch_results['errors']:
    print("\nErrors:")
    for file_path, error in batch_results['errors'].items():
        print(f"Error in {file_path}: {error}")
```

--------------------------------

### Iterate and Print Extracted Text from Batch Results (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Loops through the `results` dictionary within the `batch_results` object, which contains the extracted text for each successfully processed file, and prints the file path and its corresponding text. Assumes `process_batch` has been called and `batch_results` is available.

```python
# Get text from all successfully processed images
for file_path, text in batch_results['results'].items():
    print(f"\nFile: {file_path}")
    print("-" * 50)
    print(f"Extracted Text: {text}")


```

--------------------------------

### Check and Print Batch Processing Errors (Python)

Source: https://github.com/imanoop7/ollama-ocr/blob/main/example.ipynb

Checks if the `errors` dictionary within `batch_results` is not empty. If errors exist, it iterates through them and prints the file path and the associated error message for each failed file. Assumes `process_batch` has been called and `batch_results` is available.

```python
# Check if there were any errors
if batch_results['errors']:
    print("\nErrors:")
    for file_path, error in batch_results['errors'].items():
        print(f"Error in {file_path}: {error}")
```

--------------------------------

### Run Streamlit Application

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

Launches the Streamlit web application by executing the app.py file.

```bash
streamlit run app.py
```

--------------------------------

### Clone Ollama-OCR Repository

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

Clones the Ollama-OCR repository from GitHub and navigates into the newly created directory.

```bash
git clone https://github.com/imanoop7/Ollama-OCR.git
cd Ollama-OCR
```

--------------------------------

### Navigate to Application Directory

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

Changes the current directory to the source directory where the main application file (app.py) is located.

```bash
cd src/ollama_ocr
```

--------------------------------

### Processing Single File with Ollama OCR

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

This Python code snippet demonstrates how to initialize the OCRProcessor and process a single image or PDF file using a specified Ollama model, output format, and optional custom prompt and language.

```python
from ollama_ocr import OCRProcessor

# Initialize OCR processor
ocr = OCRProcessor(model_name='llama3.2-vision:11b', base_url="http://host.docker.internal:11434/api/generate")  # You can use any vision model available on Ollama
# you can pass your custom ollama api

# Process an image
result = ocr.process_image(
    image_path="path/to/your/image.png", # path to your pdf files "path/to/your/file.pdf"
    format_type="markdown",  # Options: markdown, text, json, structured, key_value
    custom_prompt="Extract all text, focusing on dates and names.", # Optional custom prompt
    language="English" # Specify the language of the text (New! 🆕)
)
print(result)
```

--------------------------------

### Processing Batch Files with Ollama OCR

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

This Python code snippet shows how to use the OCRProcessor for batch processing of multiple image or PDF files within a directory, including options for parallel processing, recursive search, preprocessing, custom prompts, and language specification.

```python
from ollama_ocr import OCRProcessor

# Initialize OCR processor
ocr = OCRProcessor(model_name='llama3.2-vision:11b', max_workers=4)  # max workers for parallel processing

# Process multiple images
# Process multiple images with progress tracking
batch_results = ocr.process_batch(
    input_path="path/to/images/folder",  # Directory or list of image paths
    format_type="markdown",
    recursive=True,  # Search subdirectories
    preprocess=True,  # Enable image preprocessing
    custom_prompt="Extract all text, focusing on dates and names.", # Optional custom prompt
    language="English" # Specify the language of the text (New! 🆕)
)
# Access results
for file_path, text in batch_results['results'].items():
    print(f"\nFile: {file_path}")
    print(f"Extracted Text: {text}")

# View statistics
print("\nProcessing Statistics:")
print(f"Total images: {batch_results['statistics']['total']}")
print(f"Successfully processed: {batch_results['statistics']['successful']}")
print(f"Failed: {batch_results['statistics']['failed']}")
```

--------------------------------

### Pulling Required Ollama Models

Source: https://github.com/imanoop7/ollama-ocr/blob/main/README.md

These commands pull specific vision language models from the Ollama library, which are required by the Ollama OCR package to perform text extraction from images and PDFs.

```bash
ollama pull llama3.2-vision:11b
ollama pull granite3.2-vision
ollama pull moondream
ollama pull minicpm-v
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.