fix: les

2026-06-17 07:15:32 +02:00
parent c023192113
commit ad8b25e70c
115 changed files with 6316 additions and 16971 deletions
--- a/Les16-RAG-Embeddings/Les16-Lesopdracht.md
+++ b/Les16-RAG-Embeddings/Les16-Lesopdracht.md
@@ -0,0 +1,277 @@
+# Les 15 — Lesopdracht
+## PDF Q&A app opzetten + eerste embeddings
+
+**Vak:** AI-Assisted Development
+**Opleiding:** NOVI Hogeschool Utrecht
+**Duur:** 30 min in-class
+**Status:** Tijdens de les afronden — daarna huiswerk uitbreiden
+
+---
+
+## Doel
+
+Aan het einde van deze opdracht heb je een werkende **PDF Q&A app**: je uploadt een PDF, hij wordt gechunked + embedded + opgeslagen in Supabase pgvector, en je kunt er vragen aan stellen die accuraat beantwoord worden op basis van de PDF.
+
+---
+
+## Vereisten
+
+- Node 20+, pnpm, git
+- Supabase account
+- OpenAI API key
+
+---
+
+## Stap 1 — Nieuwe Next.js app
+
+```bash
+pnpm create next-app@latest pdf-qa \
+  --typescript --tailwind --app --no-src-dir --import-alias "@/*"
+cd pdf-qa
+pnpm add ai @ai-sdk/openai zod @supabase/supabase-js unpdf
+```
+
+`.env.local`:
+
+```
+OPENAI_API_KEY=sk-...
+NEXT_PUBLIC_SUPABASE_URL=https://...supabase.co
+NEXT_PUBLIC_SUPABASE_ANON_KEY=eyJ...
+```
+
+---
+
+## Stap 2 — Supabase: pgvector + schema
+
+In Supabase SQL Editor:
+
+```sql
+-- 1. Extension activeren
+create extension if not exists vector;
+
+-- 2. Chunks tabel
+create table chunks (
+  id          bigserial primary key,
+  source      text not null,
+  page        int,
+  content     text not null,
+  embedding   vector(1536),
+  created_at  timestamp default now()
+);
+
+-- 3. HNSW index voor snelle search
+create index on chunks
+  using hnsw (embedding vector_cosine_ops);
+
+-- 4. RLS open voor demo
+alter table chunks enable row level security;
+create policy "demo open" on chunks
+  for all to anon using (true) with check (true);
+
+-- 5. Match function
+create or replace function match_chunks(
+  query_embedding vector(1536),
+  match_count int default 5
+)
+returns table (id bigint, content text, source text, similarity float)
+language sql stable as $$
+  select chunks.id, chunks.content, chunks.source,
+    1 - (chunks.embedding <=> query_embedding) as similarity
+  from chunks
+  order by chunks.embedding <=> query_embedding
+  limit match_count;
+$$;
+```
+
+---
+
+## Stap 3 — lib/embeddings.ts
+
+```typescript
+import { embed, embedMany } from "ai";
+import { openai } from "@ai-sdk/openai";
+
+export const embedModel = openai.textEmbeddingModel("text-embedding-3-small");
+
+export async function embedOne(text: string) {
+  const { embedding } = await embed({ model: embedModel, value: text });
+  return embedding;
+}
+
+export async function embedBatch(texts: string[]) {
+  const { embeddings } = await embedMany({ model: embedModel, values: texts });
+  return embeddings;
+}
+
+export function chunkText(text: string, size = 500, overlap = 50): string[] {
+  const chunks: string[] = [];
+  let i = 0;
+  while (i < text.length) {
+    chunks.push(text.slice(i, i + size).trim());
+    i += size - overlap;
+  }
+  return chunks.filter((c) => c.length > 0);
+}
+```
+
+---
+
+## Stap 4 — lib/supabase.ts
+
+```typescript
+import { createClient } from "@supabase/supabase-js";
+
+export const supabase = createClient(
+  process.env.NEXT_PUBLIC_SUPABASE_URL!,
+  process.env.NEXT_PUBLIC_SUPABASE_ANON_KEY!
+);
+```
+
+---
+
+## Stap 5 — Index endpoint
+
+`app/api/index/route.ts`:
+
+```typescript
+import { extractText } from "unpdf";
+import { embedBatch, chunkText } from "@/lib/embeddings";
+import { supabase } from "@/lib/supabase";
+
+export async function POST(req: Request) {
+  const formData = await req.formData();
+  const file = formData.get("file") as File;
+  if (!file) return Response.json({ error: "No file" }, { status: 400 });
+
+  const buffer = new Uint8Array(await file.arrayBuffer());
+  const { text } = await extractText(buffer, { mergePages: true });
+
+  const chunks = chunkText(text, 500, 50);
+  const embeddings = await embedBatch(chunks);
+
+  const { error } = await supabase.from("chunks").insert(
+    chunks.map((content, i) => ({
+      source: file.name,
+      content,
+      embedding: embeddings[i],
+    }))
+  );
+
+  if (error) return Response.json({ error: error.message }, { status: 500 });
+  return Response.json({ chunks: chunks.length, source: file.name });
+}
+```
+
+---
+
+## Stap 6 — Ask endpoint
+
+`app/api/ask/route.ts`:
+
+```typescript
+import { embedOne } from "@/lib/embeddings";
+import { supabase } from "@/lib/supabase";
+import { generateText } from "ai";
+import { openai } from "@ai-sdk/openai";
+
+export async function POST(req: Request) {
+  const { question } = await req.json();
+  const embedding = await embedOne(question);
+
+  const { data: chunks } = await supabase.rpc("match_chunks", {
+    query_embedding: embedding,
+    match_count: 5,
+  });
+
+  if (!chunks?.length) {
+    return Response.json({ answer: "Geen relevante info gevonden." });
+  }
+
+  const context = chunks
+    .map((c: any, i: number) => `[Source ${i + 1}: ${c.source}]\n${c.content}`)
+    .join("\n\n---\n\n");
+
+  const { text } = await generateText({
+    model: openai("gpt-4o-mini"),
+    prompt: `Beantwoord op basis van deze context. Als geen antwoord staat, zeg dat eerlijk.
+
+CONTEXT:
+${context}
+
+VRAAG: ${question}
+
+ANTWOORD:`,
+  });
+
+  return Response.json({ answer: text, sources: chunks });
+}
+```
+
+---
+
+## Stap 7 — Test in terminal
+
+`pnpm dev` in één terminal. In een ander:
+
+```bash
+# Index een PDF (Tim deelt voorbeeld-PDF in de les)
+curl -X POST http://localhost:3000/api/index \
+  -F "file=@./polderfest-lineup.pdf"
+# {"chunks": 30, "source": "polderfest-lineup.pdf"}
+
+# Stel een vraag
+curl -X POST http://localhost:3000/api/ask \
+  -H "Content-Type: application/json" \
+  -d '{"question": "Wie zijn de headliners?"}' \
+  | jq
+```
+
+Verwacht: JSON met `answer` (accuraat antwoord) en `sources` (welke chunks gebruikt).
+
+---
+
+## Eisen
+
+- [ ] pgvector extension actief in Supabase
+- [ ] `chunks` tabel + HNSW index + match_chunks function
+- [ ] 1 PDF succesvol geïndexeerd
+- [ ] 3 vragen werken met correcte antwoorden
+- [ ] In Supabase Table Editor: chunks zichtbaar met embedding kolom
+
+---
+
+## Tijdsindeling (30 min)
+
+| Stap | Tijd |
+|------|------|
+| 1 — Setup | 3 min |
+| 2 — Supabase schema | 5 min |
+| 3-4 — lib files | 5 min |
+| 5 — Index endpoint | 7 min |
+| 6 — Ask endpoint | 5 min |
+| 7 — Test | 5 min |
+
+---
+
+## Veelvoorkomende problemen
+
+| Symptoom | Oplossing |
+|----------|-----------|
+| `extension "vector" does not exist` | Supabase: Database → Extensions → enable vector |
+| `dimension mismatch` | Embed model en `vector(N)` moeten matchen — gebruik altijd `text-embedding-3-small` (1536) |
+| `match_chunks does not exist` | SQL function niet aangemaakt — stap 2 stuk 5 |
+| `embedMany` slow | Normaal voor grote PDFs — geduld of split batches |
+| RLS error op insert | `create policy` niet uitgevoerd — stap 2 stuk 4 |
+| PDF parsing leeg | Scan-PDF (image-based)? unpdf werkt op text-PDFs |
+
+---
+
+## Klaar? Verder met huiswerk
+
+Het huiswerk bouwt voort:
+
+- Eigen PDF + UI + RAG-tool in een agent
+- `RAG.md` met analyse + fail case
+- Bonus: hybrid search of streaming antwoord
+
+Zie `Les15-Huiswerk.md` of `Les15-Huiswerk.pdf`.