Conversation Parser

Import Queue

Batch import of conversation exports and documents with format validation and metadata extraction.

Import Queue

Batch import of conversation exports from ChatGPT, Claude, Gemini, and other AI platforms — plus documents, notes, and web clippings. Files are validated, metadata is extracted, and duplicates are detected before content enters the corpus.

Core Capabilities

Ingest Normalise Deduplicate
Drag-and-drop batch import for JSON, Markdown, HTML, and plain text. Automatic format detection, validation, and metadata extraction. Duplicate detection prevents redundant imports across your corpus.

The Problem We Solve

"Every AI platform exports in a different format"

ChatGPT exports JSON with one schema. Claude uses another. Gemini, Copilot, and others each have their own structure. The Import Queue normalises all of them into a consistent format before parsing begins.

"I have hundreds of exports and no way to batch-process them"

Manual import-one-at-a-time workflows don't scale. Drag in your entire archive — 10 files or 10,000 — and the Import Queue processes everything with progress tracking and error reporting.

"I keep importing the same conversations"

Without deduplication, re-importing an updated export creates duplicates. The Import Queue detects existing material and offers merge, skip, or replace options.

How It Works

  1. Drop — Drag files or folders into the Import Queue, or select from your file system
  2. Detect — Format detection identifies the source platform and file type automatically
  3. Validate — Each file is checked for structural validity, encoding issues, and completeness
  4. Extract — Metadata is pulled: dates, participants, topics, word counts, language markers
  5. Deduplicate — Content is compared against existing corpus material for exact and near-duplicate matches
  6. Queue — Valid imports enter the processing pipeline and flow into the Message Splitter for conversation parsing

What We Deliver

  • Batch import with drag-and-drop for any number of files
  • Format detection and validation for JSON, Markdown, HTML, and plain text
  • Platform-specific normalisation for ChatGPT, Claude, Gemini, and other exports
  • Automatic metadata extraction — dates, participants, topics, word counts
  • Import progress tracking with per-file status and error reporting
  • Duplicate detection with merge, skip, and replace options
  • Import history log showing every file processed and its disposition

Integration with Other Features

  • Message Splitter — Imported conversations flow directly to splitting and topic detection
  • Corpus Index — Imported material appears in the index the moment processing completes
  • Topic Clusters — New imports are automatically assigned to existing or new clusters

Related

→ Explore All Features

← BACK TO UNIVERSEALL PRODUCTS →