Embeddings, RAG and knowledge

How retrieval-augmented generation works in Aimogen Pro, the complete lifecycle from source to answer, and where each part is configured.

Embeddings let Aimogen Pro answer from your content rather than from what the model happens to remember. The technique is retrieval-augmented generation: index your content, retrieve the parts relevant to a question, and put those into the prompt.

Use Embeddings To Quickly Teach The AI Information About Your Business Or ProductsThe full embeddings workflow.Watch on YouTube

This tutorial was recorded before Aiomatic was renamed to Aimogen Pro. Some labels or interface elements may differ slightly from the current version.

The lifecycle#

StepWhat happensWhere you configure it
1. Choose a sourceA post, a file, a URL, or existing contentAdding content
2. ChunkLong text is split into pieces small enough to be usefulAutomatic
3. EmbedEach chunk becomes a vectorEmbedding models
4. StoreVectors go into a vector store, optionally namespacedVector stores
5. RetrieveA question is embedded and the closest chunks foundRetrieval
6. InjectThose chunks are added to the promptRetrieval
7. MaintainContent changes, so the index must be updatedTroubleshooting

What you need#

An embedding provider. OpenAI, Google or Ollama. See Embedding models.

A vector store. OpenAI Vector Stores, Pinecone, Qdrant or Chroma. See Vector stores.

The two are independent: you can embed with OpenAI and store in Qdrant.

Where it is used#

Retrieval is opt-in per context, under Settings › Embeddings › Enable Embeddings For. Each has its own checkbox and its own namespace field:

ContextSetting
Single post creatorembeddings_single
Bulk creator (whole post)embeddings_bulk
Bulk: titleembeddings_bulk_title
Bulk: sectionsembeddings_bulk_sections
Bulk: introductionembeddings_bulk_intro
Bulk: contentembeddings_bulk_content
Bulk: Q&Aembeddings_bulk_qa
Bulk: conclusionembeddings_bulk_outro
Bulk: excerptembeddings_bulk_excerpt
AI Content Editorembeddings_edit
Chatbot shortcodesembeddings_chat_short
[aimogen-article] shortcodeembeddings_article_short
Editing shortcodesembeddings_edit_short
Related contentembeddings_related
Assistantsembeddings_assistant
AI Formsembeddings_forms
OmniBlocksembeddings_omni

Each context also has a namespace field, which is what lets different features search different parts of the index.

Other things embeddings power#

Beyond answering questions, the same index drives:

When retrieval is the wrong tool#

A handful of facts belong in the chatbot Bot Context. Setting up a vector store for five facts is disproportionate.

The current page content is better injected with %%post_content_plain_text%% in a prompt.

Current events need internet access, not your archive.

A one-off document belongs in PDF chat, scoped to the conversation.

Retrieval earns its complexity when you have a substantial body of your own content that questions need to be answered from.

Cost#

Indexing is a one-off cost per document. Embedding models are cheap — indexing a thousand posts costs very little.

Retrieval adds a small embedding call per query, plus the retrieved chunks as input tokens on every affected request. That is the ongoing cost, and it scales with how many chunks you inject.

See Controlling cost.

Still stuck? Open a support ticket and include the diagnostics from Aimogen Pro › System & Logs › System Info.