Quick start

Quick start

Get a working Veda cluster and run your first vector search in a few minutes. You need Docker with Compose and git — there is no published Veda image yet, so Compose builds the server from source in this repo.

Two API calls against a live Veda — create a collection, insert three sentences — then a search in plain English finds the right one without sharing a single keyword.

Get the repository

Compose builds Veda from this repo, so clone it first — docker compose has nothing to read otherwise.

bash
git clone https://github.com/kshitij2605/Veda.git
cd Veda

Start the core services

bash
# Copy and configure environment
cp .env.example .env

# Core services (Veda + MinIO + NATS)
docker compose up

The first up compiles the server, so expect it to take a few minutes and a few GB of disk. Later starts reuse the built image and come up in seconds.

This starts the Veda server, MinIO blob storage, and the NATS message queue:

ServiceURL
Veda APIhttp://localhost:6340
Niriksha dashboardhttp://localhost:5173
MinIO consolehttp://localhost:9001

Optional profiles

Add capabilities with Compose profiles:

bash
# With embedding service (HuggingFace TEI)
docker compose --profile embedding up

# With document OCR (FlashParse + GLM-OCR, text-only, ~8GB VRAM)
docker compose --profile ocr up

# With full OCR + VLM image captioning (~48GB+ VRAM)
docker compose --profile ocr --profile ocr-vlm up

# With self-hosted web crawl + meta-search (crawl4ai + searxng)
docker compose --profile web up
ProfileServicesGPU VRAMPurpose
embeddingHuggingFace TEI + Multimodal Embedding (vLLM)CPU + ~10GBText embedding (BGE-M3) + multimodal embedding (Qwen3-VL)
ocrFlashParse + GLM-OCR~8GBText/table/formula OCR from documents
ocr-vlmVLM (Qwen3.5-35B-A3B)~48GBImage captioning and classification (use with ocr)
webcrawl4ai + searxngCPUSelf-hosted web crawl + meta-search for web connectors & agentic web search
monitoringOTel Collector, Prometheus, Mimir, Tempo, Loki, GrafanaCPUMetrics, tracing, and log aggregation

Authenticate

Veda uses JWT authentication with role-based access (Admin, Editor, Viewer). Set VEDA_BOOTSTRAP_ADMIN_PASSWORD before the first start, then obtain a token:

bash
curl -X POST http://localhost:6340/v1/auth/login \
  -H "Content-Type: application/json" \
  -d '{"username": "admin", "password": "<your-bootstrap-password>"}'

Pass the returned JWT on subsequent requests as Authorization: Bearer $TOKEN.

Create a collection

bash
curl -X POST http://localhost:6340/v1/collections \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "name": "products",
    "fields": [
      {"name": "embedding", "type": "vector", "dimension": 768, "metric": "cosine"},
      {"name": "category", "type": "string", "filterable": true},
      {"name": "price", "type": "float64", "filterable": true},
      {"name": "description", "type": "string"}
    ]
  }'

Insert records

bash
curl -X POST http://localhost:6340/v1/collections/products/insert \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "records": [
      {
        "embedding": [0.1, 0.2, ...],
        "category": "electronics",
        "price": 299.99,
        "description": "Wireless headphones"
      }
    ]
  }'

With the embedding profile running you can skip pre-computing vectors entirely — see auto-embedding.

bash
curl -X POST http://localhost:6340/v1/collections/products/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "query": {"vector": {"field": "embedding", "values": [0.15, 0.22, ...]}},
    "limit": 10
  }'

Next steps