Letting a model look things up. Instead of answering from frozen memory, it fetches the relevant text first, then answers from that.
A base model answers from what it memorized during training, which is frozen and cannot include your private files or today's news. Retrieval-augmented generation, or RAG, fixes that by looking things up before answering.
The idea is simple: when a question comes in, first search a collection of documents for the relevant pieces, then hand those pieces to the model along with the question, and ask it to answer from them.
RAG has two steps. Retrieval searches your document collection for the passages most relevant to the question. Generation then feeds those passages to the model as context, so the answer is built from real, specific text rather than from hazy memory. The model still writes the answer; it just has the right material in front of it.
Documents are usually turned into embeddings, numerical representations of meaning, and stored in a vector database. A question is embedded the same way, and the system pulls the passages whose meaning is closest. This finds relevant content even when the wording differs from the question.
When the model is handed the actual source text and told to answer from it, it has far less need to invent. You can also show which passages the answer came from, so claims are checkable. It does not eliminate errors, but grounding answers in retrieved evidence makes them far more trustworthy.
Both add specialization, but they solve different problems. Fine-tuning changes how the model behaves. RAG changes what the model knows at answer time, and its knowledge updates the instant you update the documents. For "answer from this information", RAG is usually the right tool.
A base model is a student answering a closed-book exam from memory. RAG turns it into an open-book exam: before answering, the student is handed exactly the right pages, so the reply is grounded in the source instead of half-remembered.
RAG is the standard way to build an assistant over your own documents. Whether or not a given Berges AI feature uses retrieval, the principle is the same one it is built around: an answer grounded in real material beats a confident guess.
Try Berges AIIt lets a model answer from information it was never trained on, such as your private documents or recent events, and it grounds answers in real sources so they can be cited and checked.
For adding or updating knowledge, usually yes, because you just change the documents. Fine-tuning is better for changing behavior and style. Many systems use both.
No, but it reduces it a lot. If retrieval surfaces the wrong passages, or the model strays from them, errors can still slip through. Showing sources lets you catch those.