Lexia-style web app with RAG

• Separate interface, API, corpus, embeddings, and generative model.
• Create a reusable local RAG architecture for different domains.
• Design prompts that require answers with sources and clear boundaries.
• Prepare the app for a local demo and for deploying the web part on Vercel.

The application map

Before coding, view the system as a chain of small pieces:

user -> web interface -> API -> RAG retriever -> sources -> prompt with rules -> LLM -> cited answer

What we are going to build

The final project will have these pieces:

• A web interface with a query box, answer, sources, and history.
• A Node.js backend with endpoints to query, search, and check index status.
• A corpus folder with chunked documents.
• Local embeddings generated with LM Studio, Ollama, or an OpenAI-compatible server.
• Semantic retrieval and keyword search.
• A system prompt that requires citations and abstention when sources are missing.

Step 1: define your domain

Don't start with code. Start with the product. Fill in this brief:

App name:
User:
Problem:
Sources:
Tone:
Response format:
Boundaries:

Example for an educational version:

Name: EduLexia
User: vocational training teachers and students
Problem: answer questions about course materials
Sources: notes, rubrics, syllabi, and exercises
Tone: clear, practical, and pedagogical
Format: brief answer, steps, sources, and suggested task
Boundaries: don't invent syllabus content or grades

Step 2: create the project foundation

To learn the pattern from Lexia, clone the repository and run it locally:

git clone https://github.com/aulafy/lexia.git
cd lexia
cp .env.example .env
npm start

Key configuration variables:

PORT=5174
LM_BASE=http://127.0.0.1:1234/v1
CHAT_MODEL=gemma-3-12b-it
EMBED_MODEL=bge-m3
USE_RERANK=0
TOP_K=6

Step 3: connect a local model runtime

In LM Studio, load a chat model and an embeddings model. Enable the OpenAI-compatible local server at http://127.0.0.1:1234/v1.

curl http://127.0.0.1:1234/v1/models

Test embeddings:

curl -s http://127.0.0.1:1234/v1/embeddings \
  -H 'content-type: application/json' \
  -d '{"model":"bge-m3","input":["embedding test"]}'

Step 4: prepare your document library

For a first prototype, use a small JSON corpus. The important thing is that each chunk has text and a citation.

corpus/
  documentos.json

[
  {
    "id": "doc-001#p1",
    "titulo": "Course manual",
    "cita": "Course manual, section 1",
    "texto": "Fragment content...",
    "materia": "course"
  }
]

Step 5: generate the embeddings index

npm run embed

Expected files:

data/embeddings.bin
data/embeddings.ids.txt
data/embeddings.meta.json

Step 6: build the query API

The core route of a Lexia-style app is a RAG query:

POST /api/consulta

async function consulta(pregunta) {
  const fuentes = await retrieve(pregunta, 6);
  const prompt = buildPrompt(pregunta, fuentes);
  const respuesta = await chat(prompt);
  return { respuesta, fuentes };
}

Step 7: add hybrid retrieval

Lexia combines semantic search and keyword search. This is an important decision because technical domains have precise vocabulary.

• Embeddings: capture meaning.
• BM25 or lexical search: captures exact words.
• Authority weights: prioritize canonical sources.
• Optional reranker: reorders candidates when you need more precision.

Step 8: design the interface

The minimum interface should show:

• Query box.
• Mode selector: answer, draft, or search.
• Main answer.
• Retrieved sources with snippets.
• Local history.
• Index status and helpful error messages.

Retrieving sources...
Generating cited answer...
No index available. Run npm run ingest and npm run embed.
The local model isn't responding. Check LM Studio.

Step 9: responsible guardrails

Step 10: evaluate before publishing

Create five known questions and note which source should appear. Don't evaluate only whether the answer sounds good.

[
  {
    "pregunta": "What deadline do I have to submit the activity?",
    "fuente_esperada": "rubrica-entrega#p2"
  },
  {
    "pregunta": "How is the final project graded?",
    "fuente_esperada": "rubrica-final#p1"
  }
]

Simple metrics:

• Hit@3: the expected source appears among the top three.
• Hit@6: it appears among the top six.
• Cited answer: the answer includes references.
• Correct abstention: if there is no source, the app acknowledges it.

Step 11: prepare for Vercel

Vercel is perfect for publishing the web part and educational content. For a RAG app with local models, remember this separation:

• Static or Next.js web can be deployed on Vercel.
• The local model and embeddings live on your machine or private server.
• If you need a public demo, use sample data and a controlled remote backend.

npm run build
vercel deploy

Final challenge

Create a mini Lexia for your own domain:

• Choose a domain.
• Prepare 15 corpus chunks without sensitive data.
• Configure local model and embeddings.
• Create five evaluation questions.
• Customize the prompt.