Settings

Introduction

LumiFind comes with optimal default settings. Like every MIDILLI product, it allows users to customize them to their needs (almost everything). The Settings window provides a range of options to enhance your experience. In the following sections you will find detailed explanation of each and their default values in case you want to restore back to the original. The italic settings are only visible if Advanced Settings is enabled.

Currently it provides five sections:

Generic Settings
Model Settings
Search Settings
Analysis Settings
Visual Settings
Danger Zone

Generic Settings

Settings that apply to the entire software.

App Language

The language to be used for the LumiFind itself. The default value is set on the Welcome Wizard. This value does not affect the search language. Changing will require restart of the program. Current options are English (US), English (UK), Chinese, Dutch, French, German, Italian, Spanish, Turkish.

Show Advanced Settings

By default, LumiFind is set up for daily users. However, if you would like to fine-tune some settings, you can check this box to display the advanced options. Settings written in italics will be only shown if this option is checked.

Model Settings

Enable Document Model

Checking the box loads the document model at startup and activates the analysis of document files. Changing this setting requires restarting LumiFind.

AI Model for Documents

Specifies which model to use for document analysis. Its definition is shown directly below. Changing the model requires re-analysis of all document files. If you are using the Pro Edition, voice and video analyses must also be repeated. You will be asked to confirm the deletion of existing analysis data before the change is applied. To see the default available models, see this page.

The model size is displayed next to the model name, if it is not found locally, it needs to be downloaded once. Check the download location here.

If you would like to add or use another model not listed in the list, press "Custom" button and follow instructions on this page.

Enable Image Model (Pro Edition)

Checking the box loads the image model at startup and activates the analysis of image files. Changing this setting requires restarting LumiFind.

AI Model for Images

Specifies which model to use for image analysis. Its definition is shown directly below. Changing the model requires re-analysis of all image files. You will be asked to confirm the deletion of existing analysis data before the change is applied. To see the default available models, see this page.

The model size is displayed next to the model name, if it is not found locally, it needs to be downloaded once. Check the download location here.

If you would like to add or use another model not listed in the list, press "Custom" button and follow instructions on this page.

Enable Voice Model (Pro Edition)

Checking the box loads the voice model at startup and activates the analysis of voice files. Changing this setting requires restarting LumiFind.

AI Model for Voice

Specifies which model to use for voice and video analysis. Its definition is shown directly below. Changing the model requires re-analysis of all voice and video files. You will be asked to confirm the deletion of existing analysis data before the change is applied. To see the default available models, see this page.

The model size is displayed next to the model name, if it is not found locally, it needs to be downloaded once. Check the download location here.

Voice model also uses the document model to enable semantic search in the transcript.

If you would like to add or use another model not listed in the list, press "Custom" button and follow instructions on this page.

Enable Video Voice Model (Pro Edition)

Checking the box loads the voice model at startup and activates the analysis of video files to extract the transcript. Changing this setting requires restarting LumiFind.

There is no separate model selection for videos since it uses the model defined for the Voice.

Enable Video Frame Detection (Pro Edition)

Checking this enables the analysis of the video frames for the objects inside the frames. By default, every 25th frame (if a video is 25 FPS, this means 1 frame per second) is analyzed. This value can be changed in Analysis Settings -> Frame Sample Rate. You can also change the confidence threshold if some objects are not detected. To see the default available detectors, see this page.

Video Voice Analyzer and Video Frame Analyzer work independently. If both Video Voice Model and this option are enabled, videos are analyzed twice.

Video Frame Detector (Pro Edition)

Currently, only a set of detectors can be used in LumiFind. By default, it is set to opencv_ssd_coco. Detector size is displayed next to its name, if it is not found locally, it needs to be downloaded once. Check the download location here.

Selecting one detector will display a short description below.

Search Settings

Max Results

Defines the maximum number of results that can be displayed in the result window. Increase it if the results are not satisfactory. Default: 100

Max Results Per File

Specifies the maximum number of search results that will be displayed for each individual file. Default: 1

File Formats To Search

Determines which file types will be included in the search. If a new format is added in the Analysis Settings, it will automatically appear here. To add a new format, type the extension starting with a dot (e.g., .txt) and press "Add". To remove a format from the search results, select it from the table and press "Remove". If a format is not already in the Analysis Settings, adding it here will not display it. To temporarily hide a file format from the search results, use the "Filter..." button in the Search Mode.

File Size Limits

Sets the minimum and maximum file sizes that LumiFind will display in the search results. Files outside this range will be ignored. Default is between 0 and 100 MB.

Oldest File

Specifies the oldest file to include in search results. This setting affects search only, not indexing.
For example, if you indexed files from the last 5 years but want to see results only from this year, select a date using the date picker.
On Linux, the date must be entered manually in YYYY-MM-DD format. Default: 1970-01-01.

See Analysis Settings -> Oldest File for specifying date for analyses.

Detail Level

Specifies the depth of search for files.

Metadata and Content (default): Searches both metadata (e.g., file name, creation date, or other file properties not related to the actual content, similar to the operating system's search) and the file content itself using the selected model.
Metadata Only: Searches only the file's metadata without considering the content.
Content Only: Focuses solely on the file content, leveraging the model for deeper and more intelligent search results. Metadata will be ignored. For example, if a file is named abc.txt and you search for "abc", the file will only be found if the term "abc" or semantically related content exists within the document. If not, it will not appear in the search results. Similarly, a partial path name can also be searched if you are actually looking for a folder.

Result Min Score

Specifies the minimum relevance score a document or an image must have to appear in search results. Lower scores may include less relevant results and higher scores may end up not showing any files at all. Default: 0

Max Image Results (Pro Edition)

Determines how many top-matching images will be displayed for each image search query. Default: 5

Analysis Settings

File Formats to Analyze

Determines which file types will be included in the analysis. If a new format is added in this section, it will automatically be added to Search Settings as well. To add a new format, type the extension starting with a dot (e.g., .txt) and press "Add". To remove a format from being analyzed, select it from the table and press "Remove". If a format is in the Search Settings, but not here, it will not be analyzed.

File Watcher to Auto-Start Analysis

If enabled, LumiFind monitors included folders for new, modified, or removed files as well as the individually tracked files. When a change is detected, analysis starts automatically.
The scan interval can be adjusted using the File Watching Interval setting. Default: No (disabled)

File Watching Interval

Determines the interval for automatic analysis if enabled. If multiple file changes are detected within this period, analysis runs only once. Default: 60 seconds.

File Size Limits

Sets the minimum and maximum file sizes that LumiFind will process. Files outside this range will be ignored. Default is between 0 and 100 MB.

Oldest File

Specifies the oldest file to include in analysis. This setting affects indexing only, not searching.
For example, if you would like to index files only from the last 5 years, select a date using the date picker.
On Linux, the date must be entered manually in YYYY-MM-DD format. Default: 1970-01-01.

See Search Settings -> Oldest File for specifying date for searches.

Document Chunk Size

Determines the maximum size of each document chunk when splitting files for analysis. Smaller chunks may improve search accuracy. Default: 500

Advantages:

Improved search accuracy: Smaller chunks help the system match queries more precisely.

Memory efficiency: Processing smaller pieces reduces memory usage compared to handling an entire document at once.

Better context capture: Key points are less likely to be lost.

Disadvantages:

Potential context loss: If chunks are too small, the meaning of longer sentences or paragraphs may be split.

Increased processing: More chunks mean more embeddings and computations.

Document Chunk Overlap

Specifies how much overlap there should be between consecutive document chunks. Overlap helps preserve context across chunks. Default: 50

Advantages:

Preserves context: Helps maintain meaning across chunk boundaries.

Improved search relevance: Overlapping ensures queries can match content that spans chunks.

Disadvantages:

More data to process: Overlap increases the total number of chunks.

Potential redundancy: Repeated content may be processed multiple times.

Document Batch Size

Sets the number of document chunks processed together in a single batch. Larger batch sizes may speed up processing but use more memory. If you encounter out-of-memory errors, consider decreasing this value. Default: 1000

Process Email Attachments

If an email contains an attachment readable as a document, also include it in the analysis. Default: Yes

Image Batch Size (Pro Edition)

Determines how many images are processed together in a single batch. Larger batches may improve throughput but consume more resources. Default: 2

Enable Thumbnail Generation (Pro Edition)

Enables thumbnail generation during analysis. This is helpful when the network or mapped storage is detached after analysis. If a thumbnail exists and Visual Settings -> Display Thumbnails in Search Results is enabled, selecting a result will display the thumbnail without needing access to the original file or storage location. Default: Yes

Voice Chunk Duration (sec) (Pro Edition)

Specifies the length in seconds for each segment of voice or video files during analysis. Shorter chunks may improve accuracy for long recordings. Default: 30 seconds.

Show Current File Being Analyzed

When enabled, displays the file currently being analyzed in the interface. Default: No.

Treat Images as Documents

If enabled, image files included in File Formats to Analyze will be treated like documents, extracting any text or visual information where applicable. Default: No.

Warning: This will significantly increase the analysis time due to each image being processing again for document analysis.

Note: Windows users need to install Tesseract and GhostScript as described on this page. For Mac and Linux users, these tools are installed automatically.

Enable OCR Fallback for PDFs

If enabled, LumiFind will attempt OCR (Optical Character Recognition) on PDFs that cannot be read natively, allowing extraction of text from scanned documents. Default: No.

Warning: This will significantly increase the analysis time for each PDF file due to the additional processing required.

Note: Windows users need to install Tesseract and GhostScript as described on this page. For Mac and Linux users, these tools are installed automatically.

Auto Save Logs to File

Enabling this will automatically save everything that LumiFind reports during session into a file. The saved logs can be found under:

on Windows: C:\Users\%username%\.lumifind\logs\module_name_logs_YYYYmd_HHMMSS.txt
on macOS and Linux: ~/.lumifind/logs/module_name_logs_YYYYmd_HHMMSS.txt

File contents will obey the settings in Log Level.

Frame Sample Rate

Determines how often a frame is analyzed. Default is 25, which is about 1 frame per second if video is 25 FPS. If video scenes change faster, you can reduce this value. However, reducing this value will increase the analysis time.

Object Confidence Threshold

The confidence value between 0 and 1 for the frame detector to tag an object as a known object. Default 0.25 (25% confidence). Higher values will give more accurate object results, but the detectors may miss some objects.

Visual Settings

Display Thumbnails in Search Results

When enabled, thumbnails appear after selecting an image from the results. If the images contain sensitive content, you can disable this option by choosing No. Default: Yes.

Display Original Images as Fallback

When Display Thumbnails in Search Results is enabled, the system first looks for a generated thumbnail in the analysis data. If none is found, this setting determines whether the original file is shown as a fallback thumbnail, which requires access to its original location, or whether a no thumbnail found message is displayed instead. The interface also indicates whether the shown image is a generated thumbnail or the original file. Default: No.

Date Format

Specifies how dates are displayed in LumiFind. Options include:

DD.MM.YYYY – Day.Month.Year. E.g., 26.11.2025 (Default)
MM/DD/YYYY – Month/Day/Year. E.g., 11.26.2025
YYYY-MM-DD – Year-Month-Day. E.g., 2025-11-26

Time Format

Specifies how time is displayed in LumiFind. Options include:

HH:mm:ss – 24-hour format with seconds. E.g., 23:37:45 (Default)
HH:mm – 24-hour format without seconds. E.g., 23:37
hh:mm:ss AM/PM – 12-hour format with AM/PM and seconds. E.g., 11:37:45 PM

Add Timestamps to Logs

Adds timestamps to the logs displayed on the interface and exported to the file. Display format uses Date Format and Time Format chosen in the settings. Default: Yes

File Size Unit

Determines the unit used to display file sizes. Options include B, KB, MB, and GB. Default: MB

Log Level

Specifies the level of detail shown in the Logs. Available options:

DEBUG – Shows detailed debugging information. Might be useful to get support from us.
INFO – Shows general informational messages (Default).
WARNING – Shows warnings about potential issues.
ERROR – Shows only error messages.

Danger Zone

The Danger Zone contains settings that can significantly affect LumiFind's behavior or data. Make changes here with caution, as they may result in data loss or require reconfiguration.

Delete Document Model Data

Removes all stored document analysis data. After this action, every document must be analyzed again before it becomes searchable.

Delete Image Model Data (Pro Edition)

Clears all stored image embeddings and analysis results. Images will need to be reprocessed before they can appear in search results.

Delete Voice Model Data (Pro Edition)

Deletes all indexed voice and audio analysis data. Voice files must be reanalyzed to restore search functionality.

Delete Video Model Data (Pro Edition)

Removes all video analysis and indexing data. Videos will require full reprocessing before they can be searched again.

Open Settings Folder

Opens the application settings folder. Not dangerous at all. It's simply here because we had no better place to put it. Feel free to take a peek if you're curious about how tidy things are behind the scenes.

Reset LumiFind Settings

Deletes the LumiFind's settings file and restores the application to its initial state with the Welcome Wizard. Your analysis data will remain untouched.