Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product.

If you are familiar with RAGs, you know its usual flow.

Split the document into chunks, convert each chunk into a vector embedding, store them in a vector database, and retrieve the chunk most similar to the query.

But this approach has some blind spots.

So, to address some of these issues, there is a concept called Vectorless RAG.

Problem with Traditional RAG

The RAG we see works well for many use cases.

But basic chunk-based RAG can break down on long, structured, or reasoning-heavy documents.

A few pain points are:

• Fragmented context

  • Sometimes during chunking, related information can be sliced across different chunks.
  • This can separate a number from the sentence that explains it.

• Similarity isn't relevance

  • Vector search finds text that is semantically close to a query but not necessarily the text that actually answers it.

• Opaque retrieval

  • The similarity score doesn't tell you why a chunk was chosen. This can be a problem in fields like finance, where traceability matters.

What Does Vectorless RAG Do Differently?

Vectorless RAG can replace similarity-based retrieval with structure and reasoning. Rather than flattening a document into chunks and vectors, some approaches treat the document as a hierarchy, closer to a textbook with a table of contents than a bag of disconnected paragraphs.

The Building Blocks: What Makes It Up

• The Document Tree. Instead of chopping a document into random chunks, it's mapped out like a table of contents, with chapters, sections, and subsections, the same way you'd flip through a book.
• Section Summaries. Every branch of that tree gets a short summary describing what's inside it, so the system knows what each section is "about" without reading the whole thing.
• The Navigator (LLM Reasoning). Instead of a math formula comparing vectors, an LLM reads the tree and reasons through it step by step: "Is the answer likely in Section 2 or Section 5?" Then it drills into the right branch.
• Page/Section Pointers. Once the right section is found, the system knows exactly which page or part of the document it came from, so answers can be traced back to their exact source.

Issues with Vectorless RAG

• The cost of infrastructure can shift toward the cost of inference.
• Structure-dependent approaches can have difficulty with unstructured data.
• It's best understood as a complementary strategy.

Wrapping Up

Traditional RAG works well for many use cases, but it can have limitations when dealing with long and structured documents.

Vectorless RAG takes a different approach by using the structure of the document to navigate and retrieve relevant information.

It doesn't necessarily mean that vector search needs to be completely replaced. Depending on the use case, both approaches can work together, with each being useful for different types of data and retrieval needs.

Your team's attention is limited, and the deluge of AI-generated code is making it harder to keep production reliable and secure without slowing you down.

I'm building LiveReview, a blast-radius aware AI code review built for your business-critical systems.

Instead of presenting every diff with equal emphasis, LiveReview scores each change by blast radius — how far its impact reaches through your call graph — so you can focus attention where it actually matters.

Spend code review effort where business risk is highest — not spread evenly across every diff.

⭐ Star it on GitHub:

HexmosTech / LiveReview

Blast-Radius Aware AI Code Review for Business-Critical Systems

     

LiveReview: Blast-Radius Aware AI Code Review for Business-Critical Systems

LiveReview is an AI code reviewer that scores every hunk of a diff by blast radius: how far a change reaches through your call graph, how much persistent state it touches, and how well-tested it is. A 3-line change to a shared auth check can outrank a 300-line UI tweak. Your team's attention goes to the highest-risk code first, not spread evenly across every diff.

blast-radius-demo.mp4

LiveReview's Blast Radius & Review Priority scoring, live in the diff viewer.

The exact math, not a black box	Visualize blast radius at a glance	Every factor that feeds the score

How does Blast Radius scoring work? (a more technical explanation)

Here's the goal:

• A 3-line fix in a function used by 40 other files, that also writes to a database, should score high.
• A 300-line UI change in one file, fully covered by…

View on GitHub

Click below to try LiveReview with your codebase: