Getting Started

Before using the application for the first time, please complete the following setup steps:

1. Configure OpenAI Settings

• Go to File → OpenAI settings.
• Enter and save your OpenAI API Key.

2. Configure MemoQ Server Connection

• Go to File → MemoQ configuration.
• Base Address: Enter your server URL (e.g., https://example.company.com).
  • Do not include the port number in the address field.
• Port: Enter the port number separately (e.g., 8081).
  • Example: If your server address is https://example.company.com:8081, enter https://example.company.com in Base Address and 8081 in Port.
• Login Credentials:
  • Create a user in MemoQ with Resource Lookup rights. (See MemoQ Documentation).
  • Enter this user's Username and Password in the configuration form.
• WS API Configuration (Optional):
  • If using the WS API, enter the WS API Port and WS API Key. You can find these details in your server deployment tool or by contacting MemoQ support.
• Important: Ensure the Resources API is enabled on your MemoQ server. It is free but may need to be activated by support.

3. Activate Software License

• Go to File → Software license.
• Copy the displayed value and email it to marton@edimart.com for activation.

Configuration Reference

File → MemoQ configuration

This menu allows you to manage connections to MemoQ servers.

• Multiple Logins / Nicknames:
  • You can configure and save multiple server logins (e.g., for connecting directly to different client servers).
  • Assign Nicknames to these connections to easily switch between them in the future.
• Projects Folder:
  • This folder is used for temporary storage of mqxliff files downloaded via the WS API.
  • It also stores translation logs and the translated mqxliff files.
  • This structure ensures traceability and logging for all processed jobs.
• Folder Size Warning:
  • Warn if folder size exceeds (MB): Set a threshold to receive alerts if your projects folder becomes too large, helping you manage disk space.
• Treat same-language files as one for internal examples:
  • Unchecked (Default): "On-the-fly" matches (internal fuzzy matches) are reset for each file.
  • Checked: PromptLoc MT builds a temporary Translation Memory (TM) from the raw machine translations as it processes the job. It reuses fuzzy and exact matches from this internal TM across all files in the batch (provided they share the same language pair). This improves consistency across multiple files in a single job.

File → OpenAI settings

Configure your connection to OpenAI and file paths.

• Embedding Model:
  • Define the specific embedding model to use for analyzing reference files (e.g., text-embedding-3-large).
• Performance Settings:
  • Embedding Batch Size: The number of segments sent to OpenAI in a single embedding request.
  • Max Concurrent Requests: The maximum number of parallel embedding requests to avoid API rate limits.
• Default Prompt Folder:
  • Specify the directory where your prompt templates are stored.
  • Tip: Use a shared network folder if multiple Project Managers (PMs) need to access the same set of standard prompts.

File → Advanced processing settings

Fine-tune how the Large Language Model (LLM) processes your translations.

• LLM Parameters:
  • Temperature: Controls randomness (0.0 - 1.0). Lower values make the output more deterministic.
  • Verbosity: Controls the verbosity level of the model's output (Low, Medium, High).
  • Reasoning Effort: Controls how much time reasoning models (like o1 or o3-mini) spend "thinking" before generating a response.
• Thresholds & Limits:
  • Match Rate Threshold (%): The minimum similarity score required for a TM match to be included as an example.
  • Ref. Similarity Threshold (%): The minimum cosine similarity score required for a reference segment to be included in the context.
  • References per Segment: The maximum number of reference segments to inject for each source segment.
• Processed Segment Status:
  • Choose the status to assign to segments after translation (e.g., "Machine Translated", "Edited", "Confirmed").
• Tag Mapping:
  • Determines whether tags in the LLM response should be mapped to the Source or Target segments.
  • The response will contain placeholders like {{1}}, {{2}}. These are replaced by the actual tag content from the chosen segment. Note that extra or missing tags are not resolved automatically.
• Populate JSON input schema:
  • Checked (Recommended): The application automatically injects segment data into a rich JSON structure.
  • Customize Fields: You can toggle which data fields to include (e.g., Source Text, Terms, MemoQ Examples) and rename the JSON keys used in the request to match your prompt template.
  • If data is missing for a specific field (e.g., no terms found for a segment), that property is omitted from the request to save tokens.
  • Note: For detailed instructions on prompting with this mode, see the Prompting Guide.

Interface & Operation Guide

Selecting a Source File or Project

• Local Mode (File or Folder):
  • File: Use the unified dropdown or click "Browse..." to select a single .mqxliff or .xliff file.
  • Folder: Select a folder containing multiple translation files. When a folder is selected, additional controls appear to let you navigate through the files (<, >).
  • Output: Translated files are saved in a PromptLocMT_Output subfolder within the source directory.
• Connected Project Mode:
  • Click Connect to Project to browse your MemoQ server.
  • Select a project and specific documents to download.
  • Download: Files are downloaded to your configured Projects Folder inside a timestamped subdirectory (e.g., ProjectsFolder\ProjectName_yyyy-MM-dd_HH-mm).
  • Output: Translated files and logs are saved in the same timestamped folder structure (PromptLocMT_Output\translated and ...\logs).
  • Server Update: When processing finishes, the translated file is automatically uploaded to the MemoQ server, and the document is updated.

Outputs and Logging

• Translated Files: Located in [SourceFolder]\PromptLocMT_Output\translated.
• Logs: Located in [SourceFolder]\PromptLocMT_Output\logs.
• UI Log: The application displays a real-time log of the process. You can click on log entries to see detailed JSON payloads and responses.

Prompt Selection & Client Metadata

• Prompt Dropdown: Select a prompt template from your configured Default Prompt Folder.
• Client Matching:
  • Prompt templates can contain a special metadata line: ### CLIENT METADATA: ClientName.
  • When you connect to a MemoQ project, the application reads the project's "Client" field.
  • Prompts that match the project's client are automatically prioritized (sorted to the top) in the dropdown list.
  • You can manually add client metadata to a prompt by selecting it while connected to a project; the application will ask if you want to add the current client to the template.