A lightweight, optimized vector database built on Val Town's SQLite (powered by Turso/libSQL). Supports any OpenAI-compatible embedding provider.

Provider	Env Vars	Default Model	Dimensions
Nebius (default)	NEBIUS_API_KEY	Qwen3-Embedding-8B	4096
OpenAI	OPENAI_API_KEY	text-embedding-3-small	1536
OpenRouter	OPENROUTER_API_KEY	openai/text-embedding-3-small	1536
Custom	EMBEDDING_API_KEY + EMBEDDING_API_URL	(configurable)	(configurable)

Metric	Value
Storage per record	~22 KB
Max records per 1GB	~47,500
Avg embedding time	~460ms
Recommended maxDistance	0.6 - 0.65

# Set the provider (nebius, openai, openrouter)
EMBEDDING_PROVIDER=openai
OPENAI_API_KEY=sk-...

EMBEDDING_API_URL=https://your-api.com/v1/embeddings
EMBEDDING_API_KEY=your-key
EMBEDDING_MODEL=your-model
EMBEDDING_DIM=1536

Method	Endpoint	Description
POST	/upsert	Insert/update {id, text, meta?}
POST	/search	Search {query, k?, maxDistance?}
POST	/delete	Delete {id}
GET	/get?id=...	Get single record
GET	/list?limit=...	List record IDs

Method	Endpoint	Description
GET	/ping	Health check
GET	/stats	Detailed storage stats
GET	/seed?n=100	Seed N synthetic records
GET	/calibrate?q=...	Suggest distance thresholds
POST	/reindex	Recreate optimized index
POST	/clear?confirm=yes	Delete ALL records

Distance	Meaning	Action
0.0 - 0.4	Very similar	Always include
0.4 - 0.6	Related	Include (tight mode)
0.6 - 0.7	Somewhat related	Include (balanced mode)
0.7+	Likely unrelated	Filter out

Default recommendation: maxDistance: 0.64

import * as db from "https://esm.town/v/kamenxrider/slimarmor/vectordb.ts";

// Check provider
console.log(db.getProviderInfo());

await db.setup();
await db.upsert("doc-1", "Your text here", { category: "notes" });
const results = await db.search("search query", 10, 0.64);

⚠️ Important: If you switch providers or models, the embeddings will be incompatible. You'll need to:

1. Clear existing data: POST /clear?confirm=yes
2. Set new provider env vars
3. Re-insert your data

• Runtime: Val Town (Deno)
• Database: Val Town SQLite (Turso/libSQL with DiskANN)
• Embeddings: Any OpenAI-compatible API
• Index: Cosine similarity, max_neighbors=64, compress_neighbors=float8

MIT