Beta
Documentation

Documents & RAG

Document Management

Upload documents to your ThinkFleet workspace for retrieval-augmented generation (RAG). Your agent can search and reference uploaded documents when answering questions.

How It Works

  1. Upload — Upload documents through the dashboard (PDF, text, markdown, etc.)
  2. Processing — Documents are automatically chunked and embedded as vectors
  3. Storage — Chunks are stored in a vector database (PostgreSQL with pgvector)
  4. Retrieval — When your agent needs information, it searches relevant document chunks
  5. Generation — The agent uses retrieved context to generate informed responses

Document Categories

CategoryUse Case
ReferenceKnowledge base articles, manuals, guides
TrainingExamples for the agent to learn from
Writing StyleSamples that define tone and voice

Storage Limits

PlanDocument Storage
FreeNot available
Pro5 GB
Lifetime20 GB
Enterprise100 GB

Document Status

Documents go through a processing pipeline:

  • Pending — Uploaded, waiting for processing
  • Processing — Being chunked and embedded
  • Ready — Available for search and retrieval
  • Error — Processing failed (check document format)