LumiFind User Guide Documentation of MIDILLI Tech's AI-powered offline local semantic search tool for files with 100% privacy. Latest version: 1.6.0 Website: https://lumifind.midilli.tech Select a topic to read. Introduction LumiFind is the essential tool for anyone who struggles to remember where their documents, images, or other files are stored. Even if you forget the file name or its location, LumiFind helps you find it effortlessly. The name "LumiFind" is inspired by two words: Lumify (meaning to illuminate or make clear) and Find. LumiFind helps you find your files by making them visible and easy to discover, even when you don’t remember their name or location. If you work with notes, documents, videos, or emails in multiple languages, you may sometimes forget which language you used or where the file was saved. Perhaps even by your browser or office program without you noticing. LumiFind solves this problem for you. Powered by local AI, LumiFind works entirely on your device. Requires no subscriptions, no cloud, no tracking. You can focus on what truly matters, knowing your searches are private and secure. The AI runs locally, delivering fast results - even faster than you might expect. For slower devices, LumiFind offers optimized, smaller models to ensure smooth performance. So what kind of files can be searched? This will be explained in the following section: Features. Features LumiFind is designed for maximum flexibility and customization, just like other MIDILLI products. We build tools that we use ourselves every day, ensuring they meet real-world needs and deliver a seamless experience. Here are the features we have so far. The list may be incomplete: AI-powered semantic search: Finds files by meaning, not just filename. No expertise needed: Welcome Wizard helps you start optimal, with a few clicks. 100% offline and private: All processing happens on your device. No cloud, no tracking. Multi-language support: Search and results in 100+ languages. Built-in OCR: Scanned documents are not a dead end — LumiFind falls back to OCR when a PDF has no selectable text, and can even read text directly out of images. Bring your own model: Not locked into ours — use any compatible Hugging Face model for documents, images or voice. Supported file types: Documents: PDF, DOC, DOCX, PPT, PPTX, XLS, XLSX, TXT, MD, RTF, ODT, EPUB, HTML Images: JPG, PNG, JPEG Audio: MP3, WAV, FLAC, OGG, M4A, AAC, OPUS, WMA, AIFF Video: MP4, MKV, AVI, MOV, WEBM, FLV, WMV, MPEG, MPG, M4V, 3GP Email messages: EML and MSG emails, including attachments Source code Compressed files: Extract and analyze documents inside ZIP and TAR archives (.zip, .tar, .tar.gz, .tgz, .tar.bz2) Lightning fast: Searches millions of files in seconds. No cloud uploads: Your files are never sent to the cloud. Cross-platform: Works on Windows, macOS, and Linux. GPU acceleration: Have a capable graphics card? LumiFind can use it for noticeably faster indexing and searching. Console support: Works as a console application for remote servers without displays. Network & cloud drive support: Can analyze mapped drives (Dropbox, Google Drive, OneDrive, etc.). Excluding folders: Exclude one or more sub-folders to prevent LumiFind from analyzing these. Adding individual files for tracking: If you also have files scattered around your computer, you can also analyze them one-by-one and include during search. Incremental analysis: Only new or changed files are analyzed. Pause/Resume analysis: If it will take too long, you can temporarily pause and continue later. Checkpoints and backups: In case of unexpected interruptions or computer restarts, resume where you left off. Moved/renamed file detection: Automatically detects moved or renamed files. File watching: If changes detected on the folders or individual files, analysis can be automatically started. Metadata search: Want to search for a file and you know its name or (partially) its path? LumiFind can also act as operating system's own search, but much faster. Search photos by location: Thanks to EXIF geocoding, find photos by where they were taken — type a country or city name, even in your own language. Or the Camera model. Object detection in videos: LumiFind analyzes video frames and recognizes objects in them, so you can search for scenes, not just filenames. Spelling mistake tolerance: Finds files even with typos. Context understanding: Understands context, not just keywords. One-time license: No subscription. Pay once, use forever. Transferable device license: Move your license to a new device. Optional common analysis data: If you have multiple users of same files, you can just analyze once and use together. Family & team licenses: Special packages for multiple devices. Secure payment: Pay via secure methods: Stripe (Credit Cards, Bank Transfer), PayPal, Google Pay, Amazon Pay. Automatic updates: Built-in updater checks for new versions and installs them for you. User-friendly interface: Fast, modern, and easy to use. Demo & documentation: Video demo and comprehensive user manual available. Saw another feature that we miss here? Please let us know. Comparison: LumiFind vs the Rest Capability LumiFind Everything DocFetcher AnyTXT Copernic Cloud AI Search OS Built-in Searches File Contents ✅ Yes ⚠️ Content (slow/manual) ✅ Yes ✅ Yes ✅ Yes ✅ Yes ⚠️ Limited Filename Search ✅ Yes ✅ Instant ✅ Yes ✅ Yes ✅ Yes ⚠️ Limited ✅ Yes AI Semantic Search ✅ Yes ❌ No ❌ Keywords only ❌ Keywords only ⚠️ Cloud AI eklentisi ✅ Yes ❌ No Office Format Support ✅ 13+ formats ⚠️ Via IFilters ✅ Word, Excel, PDF ✅ Most office ✅ Wide range ⚠️ Varies ⚠️ Limited Content Example ✅ Yes ❌ No ⚠️ Basic ⚠️ Basic ✅ Yes ✅ Yes ❌ No File-Based Search ✅ Yes ❌ No ❌ No ❌ No ❌ No ❌ No ❌ No Related File Search ✅ Yes ❌ No ❌ No ❌ No ❌ No ❌ No ❌ No Custom AI Models ✅ Hugging Face ❌ N/A ❌ N/A ❌ N/A ⚠️ Gemini/OpenAI only ❌ Locked ❌ N/A Data Privacy ✅ 100% Local ✅ Offline ✅ Offline ✅ Offline ⚠️ AI sorguları bulut ❌ Cloud ⚠️ Mixed Multilingual ✅ 100+ langs ⚠️ Limited ⚠️ Limited ⚠️ Limited ⚠️ Limited ⚠️ Limited ❌ No Video Frame Search ✅ Built-in ❌ No ❌ No ❌ No ❌ No ❌ No ❌ No Audio Transcription ✅ Local ❌ No ❌ No ❌ No ✅ AI eklentisi ✅ Cloud ❌ No EXIF / GPS Photo Search ✅ City, country, camera ⚠️ Coords only ⚠️ Basic EXIF ❌ No ⚠️ Basic EXIF ⚠️ Location only ⚠️ Photos app only Network & Cloud Drives ✅ Yes ✅ Yes ⚠️ Manual folders ⚠️ Windows only ✅ Yes ⚠️ Own only ⚠️ Limited Pricing Model ✅ One-time ✅ Free ✅ Free (OSS) ✅ Free ❌ ~$29/yr ❌ Subscription ✅ Free Quick Usage Excited to use LumiFind? We are also excited to tell more about it. However, as the page intends, we will not go into details here. To start using it, we need to follow four steps: Registration Quick Settings with Welcome Screen Analysis Search Registration LumiFind requires you have a valid license to use it. Upon first start, you will need to enter your registration information. This info will be sent you via email. You can select the language you prefer for this process. Simply click "Register" button. The dialog will let you enter the registration key and the email address attached with the key. If it is the first time activation of the license, the key must exactly match the email that was used for the purchase. No internet access? Click here. If your computer does not have an internet access, or behind a proxy, you can select "Activate Offline" button. In that case you will be given a device code, and this needs to be entered on https://lumifind.midilli.tech/activate. It will also be copied to your clipboard so that you do not need to memorize it. We assume you have an internet connection. Enter the information and press "Activate". If activation is successful, you will get a message and the "Welcome Screen" will be shown. If you encounter any issues, you can press the "Collect Support Information" button to copy some data for us to review, and send this information to us by pasting it into your email client. Welcome Screen LumiFind will be ready in three easy steps. This screen will guide through the minimal and optimal settings for your device. Here you can also pick a language which will be default for the application itself. In the first step, you need to select your models. Depending on your hardware and your files, pick appropriate one(s) and select "Next". You can change later. We recommend you start with the smallest ones since they require one-time download. If you e.g., do not need image search or voice model for now, you can deactivate by unchecking "Enable ... Search" buttons above. However, a model must be chosen. If a search is not active, its model will not be downloaded. Depending on your license, you will see only the applicable models available for you. E.g., if you own Document Edition, you will not be able to select image or voice/video models. In the second step, you need to select the types you are interested in. You can add/remove types later. We recommend that you start with the minimal set of file types to get used to the tool. You can also add custom extensions which will be treated as documents (such as source code formats). Once you are fine with settings, select "Next" for the final step to review fine-tune settings. In the final step, you can review and adjust optional fine-tuning settings to personalize your LumiFind experience. All of these options, along with additional configuration controls, are always accessible later via Settings, so you can change them anytime. You may customize the settings now or keep the default configuration. When ready, click "Start Using LumiFind" to complete the setup. Analysis Mode After settings are saved, LumiFind will start its main interface in Analysis Mode. It may require some time to download all necessary model files and load these files. Please be patient. The status can be seen in the Logs. If you did not activate some of the models in the Welcome Wizard, they will not be downloaded. Here, you need to select some folders to analyze.  You can select "Browse" button, type the direct path, or use the tree view below to navigate. Once you are happy with the directory, press "Include 'Folder Name' in Analysis" button. Only then LumiFind will be able to see its contents. You can also individually add your file(s) scattered around you computer by using "Add individual file(s)". If you would like to exclude a folder located under an included folder, you can do so by browsing it and pressing "Exclude 'Folder Name' from Analysis" button. You can also include a remote folder (e.g., NAS) if they are also accessible from your computer. You can add as many as you like. You are not happy with one folder? Then select it under Included Folders list and press "Remove Selected from List". If "Start Analysis" button is pressable, it means you are ready to go. Click and wait. To see what LumiFind is doing in detail, press Toggle Logs to open the log panel:  Search Mode After analysis is complete, switch to "Search Mode" by pressing the green button in the middle, the blue button on the top right, or the F3 key. Here you can directly type what you are looking for or select any kind of file from the supported types, select the search type and start searching. Depending on the chosen model, the document, voice, and video searches can also be performed in multiple languages. You can also select a file and also add some keywords to narrow down your search. You can click the "Filters..." button to narrow down your search. For example, if you know the image you are looking for is not a PNG file, you can simply uncheck the PNG format. Likewise, if you are searching only by file name, you can set the "Detail Level" to "Only Metadata". All search-related settings are explained in the Search Mode section. You can also Press Ctrl + E (Windows, Linux) or Cmd + E (macOS) to switch to Search Mode and focus search input directly. Alternatively, you use  Ctrl/Cmd + 1..5 to switch to this mode, set the search type and focus on the search field. You should be seeing the results instantly. If the result is an image, selecting once shows a thumbnail on the bottom right (if enabled in Settings). Double-clicking on a result will open the file. You can also toggle its preview by using "Preview" button, or locate it in the file browser by using "Reveal in File Manager" button. Using "Show Related Files" button, you can display other similar files, semantically similar to the selected file. Your search queries will be saved into the search history on the right. You can double-click on one to repeat the search, delete the selected one, or clear all. If you want to change LumiFind settings, press "Settings" button on the top right. This was the basics. Please see other sections to learn more about the tool.  Download & Installation Installing LumiFind is easy. Check the installation guide for your operating system below or select it using the navigation on the left. Download LumiFind for your operating system here: https://lumifind.midilli.tech/download If you don't have a license, get LumiFind edition you need: https://lumifind.midilli.tech/pricing/ Requirements LumiFind is tested in many devices and here are the minimum system requirements to run it: Requirement Minimum Recommended Graphical Console Operating System Windows 10, macOS 11, Linux (Ubuntu 20.04) Windows 11+, macOS 13, Linux (Ubuntu 25.04) x x Screen resolution 1366x768 1980x1080+ x Processor (CPU) Dual-core Quad-core+ x x Memory (RAM) 4 GB 8+ GB (if all models enabled) x x Disk Space 2 GB + Model Size 4+ GB + Model Size x x Windows Double-click  LumiFind-x.x.x.msi to start installation and follow the instructions. First, you need to accept our license: You can choose to install only for you (does not require administrator rights), or for all users in the computer (requires administration rights). Clicking "Next" will show you the default location to install based on your choice in the previous step. You can use the "Change..." button to set a different path. Finally, click "Next" and then "Install" to install the files and create "LumiFind" icon in the Start Menu. x.x.x is the LumiFind's version number macOS Double-click the LumiFind-x.x.x-macOS.dmg. You will most likely get an error for the DMG being not from a verified user. In that case, you can right-click and select Open. This will show another false warning: Press Open again and wait until the verification is complete. [TODO] x.x.x is the LumiFind's version number Linux Currently, we provide Debian-based Linux binaries. Double click the lf_x.x.x-1~ubuntu-questing_amd64.deb file and enter your password. Depending on your distribution, you can follow the instructions. If you are installing on a server, use: sudo dpkg -i lf_x.x.x-1~ubuntu-questing_amd64.deb. If you have other Linux distribution and would like to install LumiFind there, let us know. x.x.x is the LumiFind's version number Release History LumiFind Release History 1.6 Blog: LumiFind 1.6 Release Notes: Performance overhaul with smarter metadata search and a changed layout Release Date: 05 October 2026 Highlights: Performance overhaul for heavy analyses and faster rescans. More information in the logs when operations take longer. Single-line status bar added, summarizing what LumiFind is actually doing. Fix for corrupted files stopping the analysis. Photos can be searched using GPS and EXIF data including city, country, camera model. Console mode for Windows is added. Improved offline mode and model checks, including detection of corrupted downloads. Improved analysis mode window layout. Updated libraries with the latest fixes. 1.5 Blog: LumiFind 1.5 Release Notes: File Search, Related Files, Multi-Model Search, Exporting Results Release Date: 01 July 2026 Highlights: Multi-model search is implemented Search based on a selected file is implemented Exporting search results in different file formats possible Find related files is implemented Whisper v3 is available as a default model Update dependencies Updated to Python 3.14 for latest security patches and updates 1.4 Blog: LumiFind 1.4 Release Notes: Smarter Filters, Safer Indexing and Better Control Release Date: 01 March 2026 Highlights: Better file-type-aware filtering Improved metadata search consistency Analysis backups (including optional thumbnails) Checkpoint system for automatic resume after interruption Shared analysis folders available for all editions Fine-tune controls surfaced earlier, including on Welcome screen Reorganized search settings for better workflow Independent video-frame and audio handling Timestamp improvements for voice and video audio Configurable internal storage folders Dependency updates and performance optimizations Ability to download private models from Hugging Face Localization corrections and stability fixes 1.3 Blog: LumiFind 1.3 Release Notes: 3GP Format, Pause/Resume Analysis and More Release Date: 08 February 2026 Highlights: Added support for 3GP video format Pause / resume analysis controls Improved logging system Refined scoring behavior Indexing made safer and more predictable Localization improvements and multiple bug fixes 1.2 Blog: LumiFind 1.2 Release Notes: Smarter Search, Video Frames, and File Watcher Release Date: 10 January 2026 Highlights: Smarter search improvements New video frame detector feature File watcher that monitors folders and tracked files Oldest file filter added Better metadata and search setting handling Multiple fixes for layout, localization, and analysis issues 1.0.0 Blog: LumiFind 1.0 is Released Release Date: 11 December 2025 Highlights: First major public release ePUB support added Update checking on all platforms Automatic updater for Windows New privacy controls Keyboard shortcuts Improved console mode Email attachment indexing Localization updates Many minor bug fixes Pre-1.0 Updates (Informal / Interim Releases) Unofficial Update (Post-1.0, fast follow) Blog: LumiFind Gets Another Update. Yes that quick! Date: 02 December 2025 Highlights: Excluded folder support Per-file tracking Custom model support Log export and automatic log creation Button to open folder of result item Dutch, Italian, Mandarin Chinese localizations License troubleshooting helper Faster incremental analysis and stability improvements Kickstarter & Early History Initial Launch / Early Access Blog: LumiFind Ships Early. Here Is What Happened So Far Date: 25 November 2025 Highlights: LumiFind shared publicly following successful Kickstarter Tool provides semantic local search across documents, images, audio, video User Interface About graphical user interface (GUI) components of LumiFind. Welcome Screen Introduction Welcome Screen or Welcome Wizard will guide you through the optimal settings if the LumiFind is running on this device for the first time. Document Edition Pro Edition The language you pick here will be the default language for the LumiFind for the upcoming launches. However, you can change it later via Settings. In three steps, you can start using LumiFind. Step 1: Choosing Models Depending on your device's specifications (CPU, RAM, available disk space) and the types of files you work with, you can choose any of the available models. The wizard will enable the "Next" button once all required models have been selected. For example, if you only work with English documents, you can start with the smallest Document Search model. If you frequently search through documents containing many abbreviations or academic language, you might want to choose the Multilingual (High Quality) model instead. To learn more on default models available in LumiFind, see: Default models included with LumiFind You can change your selected models later in Settings, but keep in mind that files must be reanalyzed whenever a model changes. For instance, if you switch to a different Image Model, all previous image analyses must be deleted and recreated. Tip: Start with a small set of files to find the model that works best for you. Each model has its own strengths and limitations. If you want to use a custom model, you can add it manually through the settings. This will be covered in the Using custom models section in Advanced Use pages. Models only need to be downloaded once. After that, they will be loaded automatically each time LumiFind starts. If you are not interested in a particular type of analysis, for example Image Search, you still need to select a model for it, but you can disable it by unchecking "Enable Image Search". When disabled, the model will not be downloaded or loaded, which helps reduce resource usage. This is especially useful for devices with limited performance. Step 2: Choosing File Types LumiFind supports many file types and can extract text or other information from them. However, enabling more formats will increase the analysis time. It is recommended to begin with the minimum set of file types until you become familiar with the tool and be confident with the model of your selection. You can always add or remove file types later in Settings. Depending on your LumiFind Edition, some file types may be preselected automatically. You can read the descriptions and the corresponding file extensions below each option. If you want to include a file type, enable it using the "Enable" switch in the top right. If you are not interested in a particular type, or if it is not relevant to your workflow, you can disable it at any time. The "Others" section is a free-form field where you can enter additional file extensions that LumiFind does not list by default but can still read. For example, if you want to search through your program's source code, you can type extensions separated by commas such as .cpp, .c, .h, .hpp. Select "Enable" to include these formats. You can also add readable formats like Markdown ( .md, .markdown) in the same way. Warning: If you add a format that is not readable as plain text, LumiFind will still attempt to extract content from it. This may take longer and produce poor results. To avoid issues, simply open the file type in a text editor first to verify that it is readable. If you enable "Compressed Files", LumiFind will extract the archive and look for documents inside it. Since image, audio, and video compression is already very high, compressed files are only considered during document analysis. Step 3: Fine-Tune Settings LumiFind started as a simple idea to help users find files faster. Over time, it evolved and introduced many powerful settings to enhance the overall user experience. To keep the setup process simple while still offering flexibility, we included some of these advanced options as an optional third step. In this step, you can review the settings and adjust them if needed. Each option includes a short description explaining what it does and how it can be used. More settings will be available after setup in Settings Window. Once you are satisfied with your selections, click "Start Using LumiFind". If you want to return to previous steps, use the "Back" button in the lower left. Main Window Introduction The Main Window is the primary interface where you will spend most of your time. It contains two sections: Analysis Mode and Search Mode. Analysis Mode allows you to select the folders that LumiFind will scan and analyze. You can use F2 on the keyboard as shortcut to switch to this mode. Search Mode becomes available once you have completed at least one analysis. It enables you to search through your data quickly and intelligently. F3 key is the shortcut to switch to this mode. Analysis Mode This mode scans the allowed folders and individually tracked files and creates an index of the selected file formats using the active models configured in the Welcome Wizard or Settings. To use the search functionality, you must complete at least one analysis with an analyzer. You can also activate this view by using View -> Analysis Mode or pressing  F2. Analysis Mode will have the following layout: Refer to the image above and the numbered areas. Each section is explained below. File, View, and Help menus. File: Create Backup opens a dialog to back the analysis data up as described here. Settings opens the settings window and Exit quits the program. View: Displays options to switch between Analysis and Search mode. Actions: Lists quick shortcuts to switch to Search mode and focus on search field, including changing the search type. Help: This menu lets you open the LumiFind website, access the online documentation (Shortcut: F1), check for software updates, and open both the License Manager and the About window. Settings and mode selection buttons. The Settings button becomes available once LumiFind is ready. You can also use Ctrl + , on Windows/Linux and Cmd + , on macOS to open it. The currently viewed folder, along with a "Browse" button for quick navigation. It is also possible to paste a path and press Enter. Subfolders within the currently viewed directory. Buttons to add a folder in a list in item 6, or to remove it from that list. Included Folders: The list of folders that LumiFind will analyze. Excluded Folders: Folders that LumiFind will not crawl into. Tracked Files: Individual files to analyze and track for changes. A summary of the current settings which are going to be used when analysis starts. Buttons to "Start" or "Stop" the analysis, and a button to switch to "Search" mode. The Status panel, which shows information about ongoing actions. You can toggle log visibility with "Toggle Logs", clear them with "Clear Logs", or export to a file by pressing "Export Logs" button. You can also automatically export logs for each session if you enable Settings -> Analysis Settings -> Auto Save Logs to File. Depending on the models you have chosen in the Welcome Wizard or in the Settings window, and their enabled statuses, LumiFind will load them. This may take some time, but it happens only once at each startup. The "Start Analysis" button will be enabled when everything is ready, and a "LumiFind is ready!" message will appear in the Logs (8). If this is your first time starting, you will need to select some folders via (3) or (4) and include them into (6) to start analysis. Alternatively, use "Add individual file(s)" button to select one or more files to analyze and track the changes. On Windows and Linux, you can use  Ctrl + Left-click to select multiple files at once. On macOS, use  Cmd + Left-click. If you want to exclude a folder, browse via (3) or (4) and press "Exclude '' from Analysis" button. During analysis, Tracked Files will have precedence, then the Excluded Folders and finally the Included Folders. This means, if you have an individually tracked file and it is inside an excluded folder, this file will be analyzed. Similarly, if you included a folder, but excluded its one of sub-folders, those sub-folders will not be crawled hence the files inside will not be analyzed.  LumiFind can only access folders and files that you allow it to see. You can change the current folder by selecting one in the tree view below (6) or by pressing the "Browse..." button. Once you are happy with a folder, press "Include '' in Analysis" (5). To remove a folder, select it from a list and press "Remove Selected" above the list (5). You can also include remote folders. On Windows, they start with \\. In that case, the include button will indicate that it is a remote folder. On macOS and Linux, remote folders are only possible if they are mounted and accessible via Finder or a file browser (e.g., Nautilus, Dolphin). Similarly, if you want to include Cloud storage folders such as Dropbox, Google Drive, or OneDrive, simply browse to them and include them in the analysis. Once you have included all the folders or files you need, press the "Start Analysis" button and grab some coffee (or water, or anything you like). LumiFind now uses checkpoint system. Progress is saved periodically during analysis. If you stop the process using "Stop Analysis" or an unexpected interruption occurs, analysis can resume from the last checkpoint instead of starting over. If you would like to temporarily pause the analysis to resume later, you can press "Pause" button. Once you decide to continue analysis, you can use the "Resume" button. If you completed at least one analysis, then, on future launches, LumiFind will automatically switch to Search Mode to save an extra click. Hint: To get familiar with the tool, it is recommended to start with a small set of folders and file types. This makes it easier to switch between models until you find the one that works best for you. Search Mode This mode requires that you have at least one model enabled (via Welcome Wizard, or Settings) and performed at least one analysis. You can also activate this view by pressing F3. If you want to activate this view and directly focus on search input, press Ctrl + E (Windows, Linux) or Cmd + E (macOS). You can also use Ctrl/Cmd + 1..5 to switch to this mode and set the search type, then focus on the search file in one key combination. Upon the next launches, this mode will open by default, making your searches one click faster. After LumiFind is ready, type the query you want to search for and select the type of search. Depending on your edition and the active models, only the available options will be shown. You can choose from the following options: Document Search Image Search Voice Search Video Audio Search Video Frame Search Before running a search, you can refine the scope using the "Filters..." button. Using Filters Here you can: Include or exclude specific folders Include or exclude file formats for the active search type Adjust path-related options Apply search-related settings directly within Search Mode Changes in the filter section are stored. This means you do not have to change them each time. However, folder selection applies only to the current search. Below each setting is explained: 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 mode will also search within the EXIF data of an image if exists, such as GPS coordinates and camera. So searching for a country or city may also give results. Metadata Only: Searches only the file's metadata without considering the content, only file name, the path, and EXIF data are considered. 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. 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 Image Results (Pro Edition) Determines how many top-matching images will be displayed for each image search query. Default: 10 Max Results Per File Sets the maximum number of search results shown per individual file. For example, if a document is identified as an 'invoice' across multiple pages, this setting controls how many times it will appear in the results. Default: 1. 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. Result Min Score Specifies the minimum relevance score a document, voice, video audio, and video frames 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 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. After adjusting filters, click "Search" to run the query with your selected configuration, or press Enter. Performing Search After starting the search, results will appear within seconds if matches are found. For Document, Voice, or Video Audio results, the Content area displays the relevant text. If it is not clearly visible, you can resize the columns by dragging their borders. For the image results, no content is displayed in the Content area. Instead, selecting an image result once will show a thumbnail in the bottom right of the window if thumbnail generation is enabled in the Settings -> Analysis Settings -> Enable Thumbnail Generation during analysis and the Visual Settings -> Display Thumbnails in Search Results is set to Yes. Depending on the settings and availability, either "Thumbnail" or "Original" message will be shown above the image to indicate its source. Each search is saved in the Recent Searches area on the right. The time of the search and the type of search will also be displayed. You can double-click a search query to run it again.  For all files, you can use "Reveal in File Manager" button to locate the file in the file system using the default file browser. Double-clicking a result will open the file with the default application associated with that file type on your system. "Show Related Files" opens a new dialog that lists files semantically similar to the currently selected file. It uses AI-powered embedding similarity (not keyword matching) and searches across your entire index within the same media type. Results are ranked by relevance score, and you can configure the number of results directly. While this dialog is open, it is also possible to view other files by single-clicking. Double-clicking will start a relevance search for the selected file. License Manager LumiFind requires an active license to be used. The "LumiFind License Manager" is the tool to set up your license on your devices. At the first startup, you will be provided with the following screen: You can select the language to be used throughout the activation. The License Manager needs an active internet connection for the activation and or release of the license. If you are having difficulties while registration, you can press "Collect Support Information" button. This will copy the required information into your clipboard to assist you. This will have no confidential information about your files, but mandatory parameters and their values. Please send this information along with the problem description to our contact email address. Registration Press "Register" to open the window to enter the registration info. Online Activation Enter the "Registration Key" and the "Email" and press "Activate". If it is the first time activation of the license, the key must exactly match the email that was used for the purchase. After matching information, you will be seeing the success message and the Welcome Screen will start, if it is first time running on this device. Offline Activation If you are in a company and behind a proxy, or if the device does not have an active internet connection, you can press "Activate Offline" button. This will create a unique device code that needs to be used for the activation using another device. It will also be copied to your clipboard. Save it or note it down and open https://lumifind.midilli.tech/activate on the other device which has an internet connection. Enter the registration information in the respective fields and press "Activate". If everything is correct, you will be given a link to download your license file. You can either download the license.json file and transfer it to the device where LumiFind is installed, or copy the content below and create the file manually. Then place it: on Windows:  C:\Users\%username\.lumifind\license.json on macOS/Linux:  ~/.lumifind/license.json Note: The file must exactly have the name license.json or the license will not be found. Then click "OK". If you closed the license window, restart LumiFind. Then, Welcome Wizard should start. Viewing License Information The License Manager can be used to view the current license information, such as the available features and the expiration date if exists. It can be opened by using Help -> LumiFind License Manager.  If you have an active license, you can also release it to transfer to your other devices. When requested, or to get support, you can press "Collect Support Information" button. This will copy the required information into your clipboard to assist you. This will have no confidential information about your files, but mandatory parameters and their values. Please send this information along with the problem description to our contact email address. Looking for LumiFind Software License? Check this page: License and Third-Party Notices Releasing License If you have changed your device and want to transfer your license to another device, you can release the license. Open the License Manager by going to Help -> LumiFind License Manager. An active internet connection is required to release a license. It is not possible to deactivate a license offline, as LumiFind does not actively check license validity. Once a license is released, it can be registered using any email; it does not have to be the same email used during the initial activation. Deleting license.json does not release the license and causes an error while activating it again. Please do not delete unless instructed by the support team. Settings Window See Settings page. 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. You can also access this page by using the "Help" button in this window. 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. Automatically Check for Updates on Startup LumiFind introduces exciting features with each release, improves the user experience, and sometimes optimizes the analysis. You can always check for updates via Help -> Check for Updates..., but enabling this option will perform the check automatically for you. Note that updates must be downloaded manually; this feature only displays them in the Logs. Create Backup You can back up your analysis data if your archive is large, you want to try another model, or you need to move your data to another computer. Use the "Create Backup" button to do this. You can also include image thumbnails if you have the Pro edition. The button lets you choose a folder and filename for the backup ZIP file and shows when the last backup was made. If your backup is older than one month, you will also be notified. Instructions for restoring a backup are in another section. Model Settings Settings related to models used in the LumiFind. Enabling models will require the restart of the program, whereas disabling will not. Changing models will also require re-analysis of the files in that type to take effect, which mostly means the deletion of the original analysis data. To keep everything clean, you may consider restarting LumiFind. 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. Audio/Video Language Code By default, LumiFind's Voice Models assume that voice clips and video audio tracks can be in any language. If the recording is noisy, the language may sometimes be detected incorrectly. To improve accuracy and speed up transcription, you can enter the 2-letter language code for your files. If you are unsure which code to use, check this Wikipedia page: https://en.wikipedia.org/wiki/List_of_ISO_639_language_codes. Some examples are: de (German), en (English), es (Spanish), fr (French), tr (Turkish). 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 the detector is not found locally, it needs to be downloaded once. Check the download location here. Selecting one detector will display a short description below. Hugging Face Token Default models available in LumiFind are public repositories. If you would like to access private model repositories on the Hugging Face, you can create one by clicking here and enter into this field. It is optional and empty by default. Search Settings Settings related to Search Mode of LumiFind. These settings can be found under Search Mode -> Filters. Analysis Settings Settings related to Analysis Mode of LumiFind. Many of the changes will only take effect for the next analyses. 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. Video 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. Video 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. 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. Checkpoint Interval Stores the current analysis state after every X files, as specified in the next field. This is useful when processing large datasets, as it prevents the analysis from starting over if something unexpected happens. Default: 50. Set to 0 to disable. Visual Settings Settings related to user interface behavior of LumiFind. 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. Set Folders LumiFind allows you to change all folders used to store analysis data and model data. These folders are explained here if you want to learn more. This option can be useful if you want to share analysis data with other users or if you need to store the data in a different location. The option becomes visible in the bottom left when you enable Show Advanced Settings under Generic Settings. To change a folder, click the folder icon on the right and select a new location. You can also change the location of the Database File, which stores metadata about the files. Click the folder icon and choose a new file name and location. You can also use shared folders on network shares, or mounted drives as paths. Note that changing these settings will not move existing folders to the new location. The new locations will only be used for future analyses. If you are satisfied with the changes, click "Save". The settings will be applied after the press "Save" on the settings as well. Shared Analysis Data can be used if you have multiple licenses and want to share analysis data between them. More details are explained here. Analyzers Information on analyzers in LumiFind: Document Analyzer, Image Analyzer, Voice Analyzer, and Video Analyzer [Under Construction] Advanced Use To get the most out of your new tool. Many of these settings are targeted for advanced users, and for those who would like to fine-tune settings to maximize the accuracy and the quality of the search results. If the Settings Window is not enough, feel free to check these pages out. Default models included with LumiFind Introduction LumiFind uses a collection of specialized AI models to analyze documents, images, voice recordings, and videos. Each model is downloaded once and then reused, and larger models generally offer better accuracy at the cost of higher memory and processing needs. Document Models These models handle text understanding and semantic search. Each one is downloaded once. Larger models generally provide better accuracy but require more memory and processing power. If you are using the Pro Edition, voice and video analysis will also use the selected document model for their text processing steps. all-MiniLM-L6-v2 ~90MB Fast and lightweight. Ideal for general text search, support articles, notes and low resource systems. paraphrase-multilingual-MiniLM-L12-v2 ~420MB Better semantic accuracy across many languages. Good for mixed-language documents and everyday multilingual search. distiluse-base-multilingual-cased-v2 ~540MB Cased model that preserves capitalization. Useful for academic papers, technical documents, abbreviations and proper nouns. paraphrase-multilingual-mpnet-base-v2 ~1.1GB Highest accuracy among the defaults. Best for large knowledge bases, precise semantic matching and deep contextual search. Image Models These models extract visual features from images for similarity search and cross modal search. Larger models detect finer details but need more resources. Currently, image search can only be done in English- clip-vit-base-patch32 ~615MB Balanced speed and accuracy. Suitable for most general-purpose image search tasks. clip-vit-large-patch14 ~1.5GB Higher accuracy for detailed images. Best for design libraries, product databases and visually complex datasets. siglip-base-patch16-224 ~820MB Strong performance especially on semantic similarity. Good for modern datasets and multilingual text to image matching. Voice Models These models transcribe audio into text before it can be searched. Bigger models offer noticeably higher accuracy, especially for long or noisy recordings.  Video files will also use these models for their audio tracks. whisper-tiny ~151MB Very fast. Works well for clean audio, short notes and quick transcriptions on low resource systems. whisper-base ~290MB Better accuracy while staying lightweight. Good for everyday recordings, meetings and clear speech. whisper-small ~967MB Stronger performance in noisy environments. Good for interviews, lectures and field recordings. whisper-medium ~3.06GB High accuracy across multiple languages. Great for professional transcriptions and detailed audio analysis. whisper-large-v2 ~6.19GB Highest accuracy. Best for multilingual projects, long recordings, and scenarios requiring maximum transcription quality. Video Frame Detectors Videos consist of multiple images (maybe you know that already) called frames. LumiFind can analyze the frames with the given intervals to extract the object(s) in that frame. To do that, it needs frame detectors. opencv_ssd ~23MB It is a fast and small model which can detect 20 common objects and can also run on older hardware. It can detect these objects: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor opencv_ssd_coco ~180MB It is slightly bigger than opencv_ssd, but can detect 80 different common objects. It can detect these objects: person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake, chair, couch, potted plant, bed, dining table, toilet, tv, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush detr / detr_resnet50 ~160MB This is a model from Facebook, which is slower, but good at detecting objects. If accuracy is more important than speed. It can detect the same objects as opencv_ssd_coco offers, but with higher accuracy. mediapipe_object ~5MB Another small model from Google, which is battery friendly and can also work on older laptops. It can detect the same objects as opencv_ssd_coco offers, but with lower accuracy. Your Own Models You can add your own AI models to LumiFind to customize analysis for your specific needs. For instructions on how to do this, see this page. Once added, these models can be selected alongside the default ones. Using custom models Introduction Sometimes the best model for your files isn't in any predefined list. That's why we added full custom model support. You're free to plug in the exact model you want, from lightweight text encoders to large instruction-tuned transformers, and seamlessly use it inside your workflow. This gives you the freedom to experiment, optimize for speed or accuracy, and adapt your pipeline to any future model without waiting for updates. Steps LumiFind has a simple requirement for any custom model you want to use: The model must match the analysis type you assign it to. A document model should only be used for text based analysis and an image model should only be used for image workflows. Because automatic type validation is not available yet, we trust you to pick the correct model for each category. Adding your own model is straightforward. Go to the model page on Hugging Face, locate the identifier in the format organization/model-name or username/model-name, and copy it. The copy icon on the page (highlighted in blue in the image below) gives you the exact string you need. You will often also find the information below what this model can be used for. This may give you a hint on which type of files you can use with this model. Below you can click to find the example models for a specific type: Document Models Image Models Voice Models Then, open the Settings window in LumiFind, click the "Custom" button next to the model selectors you want to replace, paste the identifier, and click "OK". The entered model will now be seen in the dropdown. Once you save your settings, it will be used in the next restart of the app. If you enter a private repository, a hugging face token must be entered via Settings and enabling Show Advanced Settings. Note: Currently, we cannot estimate how big the model is. If you press "Files and versions" tab on the model page, the total size will be shown. See an example below: Important: It is recommended to load models only from organizations/developers you trust. LumiFind cannot verify whether a model contains malicious code or if it is fully safe. In the "Files and versions" tab, some models include a "Safe" label. Selecting this label will display the results of the available virus scan reports. Warning (and a long one): Changing a model means all data that depends on that model must be reanalyzed. For instance, switching to a custom document model will clear all document related analysis. If you have the Pro Edition, this includes voice and video entries, since they both rely on document embeddings. Likewise, setting a custom voice model resets video analysis because video also uses voice embeddings. This keeps your results consistent and ensures your new model is applied everywhere it matters. Another warning: We are trying to integrate as many models as possible, but some models may not be supported. Since we cannot support all available models, please try and let us know why an unsupported model must be integrated in the next versions. Dealing with documents as images LumiFind has a feature called: "Treat Images as Documents". If this feature is enabled under Settings -> Analysis Settings, the images found under the "Included Folders" will be treated as documents and the text will be extracted for quick search. For Mac and Linux users, this will work out-of-the-box. However, Windows users need to install third-party tools to achieve that. On Windows: Open a PowerShell and type: winget install -e --id UB-Mannheim.TesseractOCR (This tool is provided by Library of University Mannheim: https://ub-mannheim.github.io/Tesseract_Dokumentation/) Download Ghostscript and install from: https://ghostscript.com/releases/gsdnld.html (Unfortunately, this needs to be done manually) Both tools are free and open-source. You can check their requirements on their websites. See also: Dealing with scanned documents Dealing with scanned documents LumiFind has a feature called: "Enable OCR fallback for PDFs". If this feature is enabled under Settings -> Analysis Settings, the PDFs found under the "Included Folders" will be further scanned with OCR tool to extract the text from them. This will significantly prolong the analysis time. Therefore, it is first recommended to start without this feature on. For Mac and Linux users, this will work out-of-the-box. However, Windows users need to install third-party tools to achieve that. On Windows: Open a PowerShell and type: winget install -e --id UB-Mannheim.TesseractOCR (This tool is provided by Library of University Mannheim: https://ub-mannheim.github.io/Tesseract_Dokumentation/) Download Ghostscript and install from: https://ghostscript.com/releases/gsdnld.html (Unfortunately, this needs to be done manually) Both tools are free and open-source. You can check their requirements on their websites. See also: Dealing with documents as images Console mode Introduction LumiFind offers a console mode for servers or remote computers such as Network Attached Storage (NAS). Most of these devices do not have a monitor, therefore, a graphical user interface (GUI) cannot be shown. The console mode for LumiFind can work completely in the terminal. At the first startup, it asks you to register, then create the minimal settings file, then offers a set of options. The console mode is written in plain Python and can be expanded if you are comfortable with programming. Features Unfortunately, not every feature in the GUI version is available for the easy use, but the core functionalities can be used. Here are the features it has so far: License Management: Activation, renewal, release, and validation of your LumiFind license. Interactive Setup: Guided creation of a minimal settings file, gated by your license features. Semantic Indexing: Analyze and index documents, images, voice, and video files (as permitted by your license). Semantic Search: Search indexed data by content, supporting multiple data types. Data Management: Clear analyzed data for any supported type. Settings Management: Create, reset, show, and validate your configuration. Non-Interactive Automation: Run indexing or search directly from the command line with flags. Config Validation: Check your settings file for completeness and correctness. Usage LumiFind can be used in Linux and macOS devices in Console mode easily. On Linux installations the lf command is available; on macOS use the packaged application binary with the same flags. Under Windows, you need to locate the LumiFind.exe and run it on console using the command under Requirements. Requirements Internet access for license activation and model downloads. Read/write access to ~/.lumifind/ for config and database files. To start in console mode, on Linux and macOS, run: lf --console on Windows, you need to open a terminal (e.g., pwsh or powershell) then go to the installation folder (e.g., cd C:\Program Files\MIDILLI Tech\LumiFind). Finally run the LumiFind using the following command: .\LumiFind.exe --console First Run Flow License Check: On startup, LumiFind checks your license. If missing or invalid, you are prompted to activate with your license key and email. If the check fails, the program exits with code 1. Settings Setup: If no settings file exists (or you use --setup), LumiFind guides you through creating a minimal configuration: Index folder location File formats to analyze Log export preference Feature enablement (Documents, Images, Voice, Video) based on your license Model selection (with defaults, overridable). See default supported models, or how to use your own model. Main Menu: After setup, LumiFind presents an interactive menu for all major operations. Auto-detected system language: English =========================================== Welcome to LumiFind Console Mode! Website: https://lumifind.midilli.tech Backend Version: 1.5.0 Frontend Version: 1.5.0 This software is copyrighted. =========================================== 🤖 Loading model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 📂 Found on device. Loading from cache............. Model will run on: cpu ✅ Model loaded successfully! 📂 Found on device. Loading from cache... 🤖 Loading model: openai/clip-vit-base-patch32... Model will run on: cpu ✅ Model loaded successfully! Model will run on: cpu 🤖 Loading model: openai/whisper-small 📂 Found on device. Loading from cache........... Model will run on: cpu Database folder not found: ~/.lumifind/lumifind_db, will assume fresh installation What do you want to do? 1. Analyze Documents 2. Search Documents 3. Clear Analyzed Data 4. License Manager 5. Settings (create/show) q. Exit Enter choice (1/2/3/4/5/q): The interactive menu also includes submenus for License Manager (renew / release / status) and Settings (create/reset / show current file). Non-Interactive Flags LumiFind supports automation via command-line flags. Append the flag after enabling the console mode: lf --console --flaghere Flag Description --setup Run guided setup to create/reset your settings file. --validate-config Validate your settings file for required sections, types, and JSON serializability. Exit code 0 = valid, 1 = problems found. --index Start indexing using the actual settings immediately and exit. --search "" --type Run a search for the given query and type, print results as a table, then exit. --license-manager Open the graphical License Manager window on its own (useful for desktop automation). --welcome-wizard Open the graphical Setup Wizard on its own. Cannot be combined with --license-manager (exit code 2). --update Launch the built-in updater interface directly. Search types The --type flag accepts values 0– 4: Value Searches 0 Documents (default) 1 Images 2 Voice recordings 3 Video audio 4 Video frames Note: The interactive menu prompt lists types 0–3 only, but type 4 (video frames) is fully valid when passed via --type 4. Example: lf --console --search "sunset at the beach" --type 1 Exit codes Code Meaning 0 Operation completed successfully. 1 License check failed, settings file missing, invalid configuration, or search error. 2 Incompatible flags combined ( --license-manager together with --welcome-wizard). Exit codes make the non-interactive flags safe to use in cron jobs, systemd timers or NAS scheduling tools — simply check whether the command returned 0. Changing Settings To get the most of the LumiFind, you can edit the settings file located under ~/.lumifind/settings.json. Each setting is documented on the Settings File page. After saving the changes do not forget to validate using --validate-config. Extending LumiFind The console mode is written in Python and can be extended for automation, integration, or custom workflows. You can add new flags, automate menu actions, or integrate with other systems. Using GPU instead of CPU For Enterprise users, GPU support with fallback to CPU comes with the deployment. Home users can also enable it, but must use the console version of LumiFind. Here are the steps: Download the Advanced version packaged for your operating system (as ZIP). Unzip somewhere on your computer. Make sure you have Python and PIP installed (https://pip.pypa.io/en/ stable/installation/#ensurepip ) Then on that folder open a command window, navigate to that folder and run: pip install torch torchvision --index-url https://download.pytorch.org/ whl/cu126 Tip: On Windows, you can right click on the navigation bar of the Explorer, and press Edit Address, then type powershell to quickly open terminal in this folder. Then run: pip install -r requirements.txt Finally start LumiFind with: python -m lf --console You should then see that the application will run on CUDA similar to below: Folders and Files As a user, you might occasionally want to see where a specific file is stored. Sometimes it's simple curiosity, other times you may want to inspect logs, review saved settings, or work directly with the files for troubleshooting or development. And since LumiFind is privacy-focused software, everything is kept transparent so you can always see what is on your computer and why it is there. Application Logs (system locations) While running, LumiFind writes background logs with names following the pattern lf.YYYYMMDD_HHMM_XXX.log. Depending on how LumiFind was installed, these are stored at: Operating System Location Comment Windows %LocalAppData%\MIDILLI Tech\LumiFind\Logs\ Only exists if installed for the current user. Windows C:\Program Files\MIDILLI Tech\LumiFind\Logs\ Only exists if installed for all users. macOS / Linux ~/.lumifind/logs/ Auto-saved session logs appear here when enabled (see below). The .lumifind Folder Operating System Path Windows C:\Users\%username%\.lumifind macOS / Linux ~/.lumifind This is the default folder for settings, license files, analysis metadata and analysis contents. Tip: Settings → Open Settings Folder opens this directory directly. Files and folders inside .lumifind File / Folder Purpose Comment settings.json Contains user settings for LumiFind. Can be edited manually, but with care! See Settings File. license.json Contains device- and user-bound license information. If deleted or tampered with, the license cannot be activated again. Licenses must be released only using the License Manager. search_history.json Lists the last performed search queries. If you are using console mode, history will not be kept. lumifind_db.sqlite3 Database keeping track of analyzed files and their metadata. Usually small in size. Default location may vary between installation types (directly under .lumifind, or inside the index folder). Its path can be changed via the db_file setting in settings.json. lumifind_db/ Folder holding the actual analysis data for documents, images, voice and videos. May grow as the number of analyzed files increases. Location can be changed via the index_folder setting in settings.json. thumbnails/ Smaller versions of the analyzed images, used both for detecting changes and displaying them in the interface. Follows the same folder structure as the indexed content. Can be relocated via the thumbnail_folder setting. models/ Cached copies of downloaded AI models (embedding, transcription and detection models). Can be relocated via the models_folder setting. .pt Object detection model weights downloaded on demand for frame analysis. Stored at the root of .lumifind; safe to delete, they will be re-downloaded when needed. manifest.json Cached update information used by the built-in updater. Refreshed automatically when checking for updates. logs/ Folder storing important information and error logs in the event of a problem. If you enable Settings → Auto Save Logs, session logs also appear here after each run. Inside the Index Folder (lumifind_db) Besides your analysis data, LumiFind keeps small marker files here: File Purpose .lumifind_indexing.lock Temporary marker while an indexing operation is running, preventing concurrent index writes. .lumifind_readonly Marker indicating the index is currently read-only (e.g. during maintenance or after an interrupted operation). Note: Do not delete marker or database files manually while LumiFind is running. If an indexing operation was interrupted unexpectedly, remove the lock markers only after making sure no LumiFind process is active. Model files from Hugging Face OS Folder Purpose Windows C:\Users\%username%\.cache\huggingface Model files downloaded from Hugging Face. Linux/macOS ~/.cache/huggingface Model files downloaded from Hugging Face. Settings File LumiFind stores every user preference in a single JSON file: settings.json. This page documents every key LumiFind reads, its type, default value and purpose. So, you can safely review, back up or hand-tune your configuration (for example on headless servers running Console mode). File Location Operating System Path Windows %UserProfile%\.lumifind\settings.json macOS / Linux ~/.lumifind/settings.json The fastest way to open the folder is Settings → Open Settings Folder. For a full overview of the directory see Folders and Files. Edit with care! Invalid values can prevent indexing or searching from working. Before editing: close LumiFind, keep a backup copy of the file, and run a validation afterwards (see Validating the file). Keys marked as managed are written automatically by the app and should not be edited by hand. Structure Overview { "generic": { ... }, "model_info": { ... }, "indexing_settings": { ... }, "search_settings": { ... }, "visual_settings": { ... } } All five top-level sections are required; the validator complains if any of them is missing. A few extra keys ( last_folder, last_updated) are added automatically by the app. Section: generic Key Type Default Description language string "en" Interface language code. auto_detect boolean true Detect and use the operating system language on first run. fallback_language string "en" Fallback language for missing translations. auto_check_updates boolean true Check for updates when the application starts. advanced_mode boolean false Show advanced options in the Settings window. backup_include_thumbnails boolean true Include thumbnails when creating settings backups. last_backup_date string "" Managed. Timestamp of the last backup. Section: model_info Key Type Default Description doc_model_enabled boolean true Enable the document embedding model. doc_model_name string sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 Hugging Face model used for document embeddings. See default models and custom models. image_model_enabled boolean false Enable image search. image_model_name string openai/clip-vit-base-patch32 Hugging Face model used for image embeddings. voice_model_enabled boolean false Enable voice transcription and search. voice_model_name string openai/whisper-tiny Hugging Face Whisper model used for transcription. video_model_enabled boolean false Enable video search (audio track analysis). frame_model_enabled boolean false Enable frame detection (object detection inside videos/images). frame_detector_type string opencv_ssd_coco Object detector. Supported values include opencv_ssd_coco, detr, yolov8n, yolov8s. frame_model_size number | null null Optional override of the estimated download size shown in the interface. whisper_language_code string "" Force transcription language (e.g. "en", "tr"). Empty = auto-detect. hugging_face_token string "" Access token for gated or private Hugging Face models. Feature switches are gated by your license. If a feature is not part of your license, enabling its switch has no effect. Section: indexing_settings Paths and files Key Type Default Description index_folder path ~/.lumifind/lumifind_db Root folder holding all analysis data. db_file path ~/.lumifind/lumifind_db.sqlite3 SQLite database file tracking analyzed files. The GUI Setup Wizard may place it inside the index folder instead. thumbnail_folder path ~/.lumifind/thumbnails Folder for thumbnail images. models_folder path ~/.lumifind/models Folder where downloaded models are cached. image_cache_folder path = index folder Optional separate location for the image embedding cache. file_formats list of strings (see example) File extensions to analyze, e.g. ".pdf", ".jpg". Analysis parameters Key Type Default Description doc_batch_size integer 1000 Documents processed per batch. image_batch_size integer 5 Images processed per batch (GUI wizard uses 10). chunk_size integer 500 Text chunk size in characters. chunk_overlap integer 50 Overlap between consecutive text chunks. voice_chunk_duration integer 30 Audio chunk length in seconds. frame_sample_rate integer 5 Analyze one frame every N seconds. Must be a positive integer (GUI wizard uses 25). frame_sampling_enabled boolean true Enable frame sampling during video indexing. object_confidence_threshold number (0–1) 0.5 Minimum confidence for detected objects (GUI wizard uses 0.25). Feature toggles Key Type Default Description process_email_attachments boolean true Index attachments found in email files. pdf_ocr_fallback boolean false Use OCR when a PDF contains no extractable text. See Dealing with scanned documents. treat_images_as_documents boolean false OCR images and index them as documents. See Dealing with documents as images. enable_exif_geocoding boolean true Reverse-geocode GPS coordinates from EXIF metadata. enable_thumbnails boolean true Generate thumbnails for analyzed images. auto_export_logs boolean false Save session logs to the logs folder after each run. show_file_info boolean false Show detailed file information in results. Maintenance and file watching Key Type Default Description file_watching_enabled boolean false Watch folders for changes and update the index automatically. file_watching_interval integer 60 Polling interval in seconds. checkpoint_interval integer 0 Save an indexing checkpoint every N files; 0 disables checkpoints. oldest_file_date date string "1970-01-01" Skip files created before this date while indexing. Managed keys — do not edit: indexed_folders, excluded_folders, tracked_files (lists maintained by the app) and previous_doc_model (used internally during model changes). Section: search_settings Key Type Default Description max_results integer 100 Maximum number of results returned per search. max_results_per_file integer 1 Maximum matches returned per file. min_score number 0 Discard results below this similarity score. use_metadata_mode integer 0 How image search balances metadata against visual content: 0 = balanced (default), 1 = prioritize metadata filters, 2 = prioritize visual matching. image_top_k integer 5 Number of candidate images considered per query stage. metadata_boost_weight number 0.3 Weight given to metadata matches when ranking. min_file_size_mb number 0.0 Ignore files smaller than this size. max_file_size_mb number 100.0 Ignore files larger than this size (GUI wizard uses 250). oldest_file_date date string "1970-01-01" Exclude files created before this date from results. file_formats list of strings (mirror of indexing) Restrict searches to these extensions. Section: visual_settings Key Type Default Description log_level string "INFO" Logging verbosity (e.g. DEBUG, INFO, WARNING). date_format string "YYYY-MM-DD" Date display format (GUI wizard uses DD.MM.YYYY). time_format string "HH:mm:ss" Time display format. file_size_unit string "MB" Preferred unit for file sizes. show_thumbnails boolean true Show thumbnails in result lists. show_original_images boolean false Show original images instead of thumbnails where possible. add_timestamps boolean true Display timestamps next to entries. Example: minimal settings.json This is what Console mode's guided setup produces: { "generic": { "language": "en" }, "model_info": { "hugging_face_token": "", "doc_model_enabled": true, "doc_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", "image_model_enabled": false, "image_model_name": "openai/clip-vit-base-patch32", "voice_model_enabled": false, "video_model_enabled": false, "frame_model_enabled": false, "frame_detector_type": "opencv_ssd_coco", "frame_model_size": null }, "indexing_settings": { "index_folder": "~/.lumifind/lumifind_db", "db_file": "~/.lumifind/lumifind_db.sqlite3", "thumbnail_folder": "~/.lumifind/thumbnails", "models_folder": "~/.lumifind/models", "file_formats": [".txt", ".md", ".pdf", ".docx"], "doc_batch_size": 1000, "image_batch_size": 5, "chunk_size": 500, "chunk_overlap": 50, "pdf_ocr_fallback": false, "treat_images_as_documents": false, "auto_export_logs": false, "show_file_info": false, "enable_exif_geocoding": true, "frame_sample_rate": 5, "object_confidence_threshold": 0.5 }, "search_settings": { "max_results": 100, "max_results_per_file": 1, "min_score": 0, "use_metadata_mode": 0, "file_formats": [".txt", ".md", ".pdf", ".docx"], "min_file_size_mb": 0.0, "max_file_size_mb": 100.0 }, "visual_settings": { "log_level": "INFO", "date_format": "YYYY-MM-DD", "file_size_unit": "MB" } } Note: Paths may be written either absolute or starting with ~/; LumiFind expands both. The GUI Setup Wizard creates the same structure but may pick different initial values for a few keys (batch sizes, sampling rate and date format). Validating the file After editing, always validate: lf --console --validate-config The check reports: All five required sections exist. generic.language is a string; index_folder, db_file are string paths; file_formats is a list. frame_detector_type is a string and frame_model_enabled is a boolean (when present). frame_sample_rate is a positive integer. object_confidence_threshold is a number between 0 and 1. The whole file is valid JSON and fully serializable. Exit code 0 means valid, 1 means problems were found (details printed to the console). Resetting to defaults Console mode: run lf --console --setup, or choose menu option Settings (create/show) → Create/Reset. GUI: re-run the Setup Wizard via --welcome-wizard or reinstall/reset from Settings. License and Third-Party Notices Introduction Last updated: 26.02.2026 We are obliged to tell you about licenses that LumiFind and its libraries use. Project License LumiFind is a commercial software product developed by MIDILLI Tech. It is licensed for use only with valid purchase or subscription. Redistribution, sharing, or resale of LumiFind is strictly prohibited except through official MIDILLI Tech channels. Licenses may be activated on multiple devices owned by the licensee, subject to MIDILLI Tech's activation policy. Resale or transfer of licenses is strictly prohibited. The software, its source code, components, and design are the exclusive property of MIDILLI Tech and may not be altered, reverse-engineered, or decompiled. Use of LumiFind is permitted only to the license owner. License terms may be updated by MIDILLI Tech; continued use of LumiFind constitutes acceptance of the latest license terms. Third-Party Dependencies & Licenses This software incorporates third-party open-source libraries. Each component is used in accordance with its respective license. The software provider performs due diligence when selecting, integrating and updating these components. However, all third-party components are provided as is by their original authors, without warranties of any kind. Users can review the corresponding licenses included with the product. The software provider ensures that the overall product is maintained, updated and supported within reasonable industry standards. This project uses the following Python packages. Their licenses are listed below: Package | License | ------------------------|-------------| langchain | MIT | langchain-community | MIT | langchain_text_splitters| MIT | sentence-transformers | Apache-2.0 | chromadb | Apache-2.0 | pypdf | BSD-3-Clause| python-docx | MIT | python-pptx | MIT | msoffcrypto-tool | MIT | openpyxl | MIT | markdown | BSD-3-Clause| unstructured | Apache-2.0 | cryptography | Apache-2.0 | torchvision | BSD | librosa | ISC | moviepy | MIT | hf_xet | Apache-2.0 | ocrmypdf | MPL-2.0 | pypika | Apache-2.0 | unstructured_inference | Apache-2.0 | unstructured_pytesseract| Apache-2.0 | pdf2image | MIT | pyperclip | Apache-2.0 | sentencepiece | BSD | beautifulsoup4 | MIT | watchfiles | MIT | mediapipe | Apache-2.0 | Special Notice for MPL-2.0 (ocrmypdf) If you modify any files from ocrmypdf, you must make those modified files available under the MPL-2.0 license. For full license texts, see each package's repository or PyPI page. Use Cases LumiFind can help you in limitless ways. When searching is not enough, and finding really matters. Sometimes it helps you find a sentence in a document. Sometimes it helps you find a moment you thought was lost. Below we identified some use cases which LumiFind can help you. The list is of course not complete. The use cases are separated by users. We have identified so far: Researcher, Writer, Parent, Journalist, Lawyer, Programmer, Creator, Student, Archivist, Freelancer, Photographer. Let us know your story as well by writing to us. Select a search and user type on the left to see how LumiFind works for different needs across documents, images, voice and video. Document Search Use Cases Law Firms and Legal Professionals Use case: Searching massive case archives securely Law firms store thousands of documents. Case files, contracts, scanned evidence, emails. Finding a single sentence across years of cases is slow and risky. Especially when client data must never leave the office. LumiFind searches your entire local legal archive. PDFs, Word files, scans. No cloud. No data exposure. Because confidentiality is not optional. Academics and PhD Researchers Use case: Finding forgotten citations and concepts You remember the idea. You don't remember the paper. LumiFind searches across years of PDFs, notes, drafts and research material. So knowledge does not get lost inside folders. Research should move forward, not sideways. Journalists and Investigative Researchers Use case: Searching documents, transcripts and recordings Investigations grow over time. So do the files. LumiFind connects text, audio and video search in one local system. Find names, statements and connections without leaking sources. Trust depends on privacy. Software Developers Use case: Searching across old projects and documentation You wrote it. You just don't remember where. LumiFind searches code-related documents, specs, PDFs and notes across projects. Beyond your IDE. Because memory is not version controlled. Freelancers and Small Businesses Use case: Searching contracts, invoices and client communication Years of work. Hundreds of files. LumiFind lets you search your business memory locally. Without complex systems or cloud subscriptions. Simple tools for real work. Archivists, Historians and Collectors Use case: Searching digitized archives Scans, letters, photographs, notes. All digitized. All hard to navigate. LumiFind turns archives into searchable memory. Text and images, together. Preservation is not enough. Access matters. Privacy-Sensitive Users Use case: Searching personal and sensitive data Health documents. Personal files. Private recordings. LumiFind works entirely on your computer. No accounts. No uploads. Because some data should never leave home. Corporate Teams Without Enterprise IT Use case: Local document search without heavy infrastructure Not every team needs SharePoint. Not every company wants SaaS. LumiFind offers local search without setup complexity. A quiet alternative to big systems. Image Search Use Cases Designers and Creatives Use case: Finding visuals by describing them You don't remember the filename. You remember the feeling. A dark background. A minimal layout. A horse in motion. LumiFind lets you search your local image archive using words. Describe what you are looking for. LumiFind finds images that look similar. No tagging. No manual organization. Creativity should not depend on folder discipline. Researchers, Archivists and Collectors Use case: Searching large image collections by content Archives grow over time. Scans, photos, screenshots. You remember what is in the image, not where it lives. A document on a table. A specific object. A repeated visual pattern. LumiFind helps you search images by meaning. So archives become usable, not just stored. Preservation is only half the work. Finding is the other half. Everyday Memory and Screenshots Use case: Finding forgotten screenshots and photos Everyone has this folder. Screenshots of ideas, errors, receipts, inspiration. You know what you captured. You just don’t remember when. LumiFind lets you describe the image you are looking for. And finds it. Because "I'll remember later" rarely works. Voice and Video Search Use Cases Finding Your Baby's First "Dad" Use case: Searching video and audio archives for a single spoken word You have hundreds of short videos. Different phones, different folders, no filenames that help. You don't remember when it happened. You just know it happened once. With LumiFind, you search inside your local videos and audio recordings by sound. Not by watching. Not by guessing. By listening, automatically. Some moments are not stored in files. They are stored in voices. Finding a Voice You Thought Was Lost Use case: Searching old voice notes and videos of a loved one Years later, you remember a sentence. A word. A tone. You don't know which file it was in. But LumiFind lets you search your entire local archive by spoken words. Because sometimes, memory starts with a voice. Podcast Archives That Actually Stay Searchable Use case: Searching hundreds of podcast episodes by topic or sentence As your podcast grows, your archive becomes harder to navigate. "Which episode did we talk about this?" With LumiFind, you search spoken content directly. Across episodes. Across years. Your voice becomes searchable. Meeting Recordings You Can Finally Use Use case: Searching Zoom, Teams or Meet recordings for decisions Meetings are recorded. But nobody replays them. LumiFind lets you search for what was said, not when it was said. Decisions. Promises. Names. If it was spoken, it can be found. Journalists Searching Spoken Truth Use case: Searching interview recordings for exact statements Hours of interviews. One sentence that matters. LumiFind finds spoken words inside audio and video files. Without uploading anything. Without leaving traces. Because words matter only if you can find them. Video Creators and YouTubers Use case: Finding a specific moment by what was said, not by scrubbing timelines If you create videos, you know this workflow. Hours of footage. Multiple takes. Endless timeline scrubbing. You remember the moment. Not the timecode. Not the filename. The words. LumiFind searches inside your video files by spoken content. It analyzes audio locally and lets you jump directly to the moment where a word or sentence was said. No frame-by-frame scanning. No manual guessing. Just search what was spoken. Musicians and Sound Designers Finding Old Ideas Use case: Searching voice memos You once said, "this could be something". LumiFind helps you search your own creative memory. Before ideas disappear into silence. Personal Audio Journals and Therapy Notes Use case: Searching voice diaries and personal recordings You recorded how you felt. Not for others. For yourself. Months later, you want to understand your own journey. LumiFind lets you search your own voice. Private. Local. Yours. Education and Lecture Recordings Use case: Searching recorded lectures for specific concepts You don't remember which lecture it was. But you remember the sentence. LumiFind finds knowledge inside speech. So learning does not depend on perfect notes. Legal and Evidence-Based Audio Search Use case: Searching call recordings and statements One phrase can change everything. But only if you can find it. LumiFind searches spoken content locally. No cloud. No exposure. Disclaimer: The legal admissibility of audio or voice recordings depends on local laws and the context in which the recording was made. LumiFind does not provide legal advice and does not validate the legality, authenticity, or admissibility of recordings. Users are responsible for ensuring compliance with applicable laws and regulations. Video Search Without Watching the Video Use case: Jumping directly to spoken moments inside videos You don't need to scrub timelines. You don't need to watch hours of footage. Search the voice. Jump to the moment.