Skip to main content
ModuleX uses retrieval-augmented generation (RAG) to ground answers in your own content. You upload documents to a knowledge base, ModuleX prepares them for search, and your chats, the Assistant, and your workflows can then retrieve the most relevant passages on demand — so responses cite your material instead of guessing. This page explains the ideas you need: what a knowledge base is, the difference between managed and bring-your-own storage, and the two halves of RAG — getting content in (ingest) and getting answers out (retrieval).

What a knowledge base is

A knowledge base is a named collection of your documents that ModuleX has prepared for search. Think of it as one searchable library: a set of product manuals, a policy handbook, or a folder of support articles. Each knowledge base carries its own settings for how documents are split and how they are turned into searchable vectors, so you can tune one library for long reference PDFs and another for short snippets — without affecting the rest.

Documents

The files you upload. Each one moves through the ingest pipeline and ends up searchable.

Chunks

Each document is split into smaller passages. Retrieval returns chunks, not whole files, so answers stay focused.

Embeddings

Every chunk is converted to a numeric vector that captures its meaning, which is what makes search by meaning possible.
You can manage knowledge bases in the app or over the API. For the hands-on walkthrough, see Knowledge overview and the Build a RAG knowledge base guide.
Throughout these docs the feature is called Knowledge (singular). A single library is a knowledge base, often shortened to KB.

Managed versus bring-your-own storage

When you create a knowledge base, you choose where the vectors live. This choice decides both who hosts the storage and how usage is billed.

Managed (modulexdb)

ModuleX hosts the vector storage for you with the built-in modulexdb provider. Nothing to set up. Ingest and retrieval are metered in credits.

Bring your own (BYOK)

Point a knowledge base at a vector store you already run. ModuleX reads and writes to it, and usage on your own store is not charged in credits — your provider bills you directly.

Managed knowledge: modulexdb

Managed knowledge bases use ModuleX’s hosted vector store, modulexdb. They are the fastest way to start because there is no external account to connect. Because ModuleX runs the storage and the embedding calls on your behalf, each retrieval and each document ingest spends credits (see How credits apply).

Bring your own key (BYOK)

If you already operate a vector database, you can connect it and keep your data in your own infrastructure. ModuleX supports these external knowledge providers:

Qdrant

Use a Qdrant cluster as your vector store.

Pinecone

Use a Pinecone index as your vector store.

MongoDB Atlas

Use MongoDB Atlas Vector Search.

Weaviate

Use a Weaviate instance as your vector store.
Billing in one line. Managed (modulexdb) knowledge is billed in credits. BYOK knowledge is uncosted by ModuleX — it is tracked for analytics only, and any charges come from your own provider. See Credits & metering.

Getting content in: ingest

Ingest is the one-time preparation each document goes through after you upload it. ModuleX runs it in the background so you can keep working while large files process.
1

Upload

You add a file to a knowledge base. Supported formats include PDF, Word (.docx / .doc), plain text, Markdown, HTML, CSV, JSON, Excel (.xlsx), and PowerPoint (.pptx).
2

Parse

ModuleX extracts the readable text from the file, whatever its format.
3

Chunk

The text is split into smaller passages using the knowledge base’s chunking settings, so each piece is a focused, retrievable unit.
4

Embed

Each chunk is converted into an embedding — a vector that represents its meaning — and stored alongside the text in the knowledge base.

Watching a document process

Every document reports its progress, so you always know whether it is ready to search.
A document moves through these states:
  • Pending — uploaded and waiting in the queue.
  • Processing — being parsed, chunked, and embedded.
  • Completed — fully ingested and ready to retrieve.
  • Failed — something went wrong during ingest. You can fix the source file and retry the document; retrying a document does not re-charge an unchanged ingest.
For managing and monitoring documents in the app, see Managing documents.

Getting answers out: retrieval

Retrieval happens every time something asks a question. ModuleX turns the question into an embedding, compares it against the stored chunks, and returns the closest matches. Those passages are then handed to the model so its answer is grounded in your content. ModuleX offers a few retrieval styles for different needs:

Semantic (vector) search

Finds chunks by meaning, even when the wording differs from the question. This is the default style.

Hybrid search

Blends meaning-based search with exact keyword matching, which helps with names, codes, and acronyms.

Multi-knowledge search

Searches several knowledge bases at once and merges the best results.

Context retrieval

Returns a ready-to-use block of text, assembled from the top chunks within a token budget, for dropping straight into a prompt.

Where retrieval shows up

You rarely call retrieval by hand. It runs wherever an answer should come from your own material:

Chat with your knowledge

Ask a question in chat and get an answer drawn from your documents.

The Assistant

The Assistant retrieves from your knowledge as one of the tools it can use.

Knowledge node

Add a step to a workflow that retrieves from a knowledge base.

Retrieving over the API

If you build on ModuleX directly, you can run a search against a knowledge base yourself. Authenticate every request with your API key and organization, exactly as on every other endpoint (see Authentication).
A successful search returns the matching chunks ranked by relevance:
Response
On a managed (modulexdb) knowledge base, a search that would exceed your plan allowance can return a billing denial instead of results — a 402, 403, or 429 response. See Usage gating & limits and Errors & status codes for the response shape and how to handle it.

How credits apply

Credits are only spent on managed (modulexdb) knowledge. BYOK knowledge bases are not charged by ModuleX. One credit is a small, fixed unit of managed usage (100 credits = $1.00). On a BYOK knowledge base, neither ingest nor retrieval spends credits. For the full pricing model — how credits are metered, the wallet, and overage — see Credits & metering and Billing & credits overview.

Plan limits

Your plan sets how many knowledge bases you can keep, how large each uploaded file can be, and how many documents each knowledge base holds. The values below come from the current subscription plan configuration.
The Pro knowledge-base count (3) is lower than Free (10) in the current plan configuration. This is a known inconsistency in the source data, shown here as-is — confirm the limit that applies to your organization on the Plans & pricing page before relying on it. The per-upload file size is set by your plan, not a single fixed cap.

Where to go next

Knowledge overview

Create and manage knowledge bases in the ModuleX app.

Build a RAG knowledge base

A start-to-finish guide: create a knowledge base, ingest documents, and query it.

Managed knowledge (modulexdb)

How ModuleX-hosted vector storage and retrieval work.

External knowledge providers

Connect Qdrant, Pinecone, MongoDB Atlas, or Weaviate.