Skip to main content

PaveDB — A lightweight, pluggable vector search microservice.

Project description

PaveDB — A lightweight, pluggable vector search microservice.

Upload → chunk → index (with metadata) → search via REST and CLI.

Highlights

  • Multi-tenant collections: /collections/{tenant}/{name}
  • Upload and search TXT, CSV, and PDF
  • Deterministic provenance: every hit returns doc id, page, offset, snippet
  • Metadata filters on search ({"filters": {"docid": "DOC-1"}})
  • REST and CLI entry points
  • Health/metrics endpoints + Prometheus exporter
  • Pluggable embeddings and stores; default stack is local FAISS + SBERT

Requirements

  • Python 3.10–3.14

Install (PyPI)

python -m venv .venv
source .venv/bin/activate
pip install pavedb

CPU-only deployments can use the PyTorch CPU wheel index:

pip install "pavedb[cpu]" \
  --index-url https://download.pytorch.org/whl/cpu \
  --extra-index-url https://pypi.org/simple

Quickstart

# Start the server (installed entry point)
pavesrv

# Or run with uvicorn manually if you prefer:
uvicorn pave.main:app --host 0.0.0.0 --port 8086

Auth defaults to none only for dev. For production, set static auth:

export PAVEDB_AUTH__MODE=static
export PAVEDB_AUTH__GLOBAL_KEY="your-secret"

Minimal config (optional)

By default PaveDB runs with sensible local defaults. For a user install, customize ~/pavedb/config.yml:

vector_store:
  type: faiss
embedder:
  type: sbert
auth:
  mode: static
  global_key: ${PAVEDB_GLOBAL_KEY}

Then export:

export PAVEDB_GLOBAL_KEY="your-secret"

If you keep the file elsewhere, point the runtime at it explicitly:

export PAVEDB_CONFIG=/path/to/config.yml

CLI example

pavecli create-collection demo books
pavecli ingest demo books demo/20k_leagues.txt --docid=verne-20k \
  --metadata='{"lang":"en"}'
pavecli search demo books "captain nemo" -k 5

REST example

# Create a collection
curl -X POST http://localhost:8086/collections/demo/books \
  -H "Authorization: Bearer your-secret"

# Upload a TXT document
curl -X POST http://localhost:8086/collections/demo/books/documents \
  -H "Authorization: Bearer your-secret" \
  -F "file=@demo/20k_leagues.txt" -F "docid=verne-20k" \
  -F 'metadata={"lang":"en"}'

# Search (GET, no filters)
curl -G --data-urlencode "q=hello" \
  -H "Authorization: Bearer your-secret" \
  http://localhost:8086/collections/demo/books/search

# Search (POST, with filters)
curl -X POST http://localhost:8086/collections/demo/books/search \
  -H "Authorization: Bearer your-secret" \
  -H "Content-Type: application/json" \
  -d '{"q":"captain nemo","k":5,"filters":{"docid":"verne-20k"}}'

License

AGPL-3.0-or-later — (C) 2025, 2026 Rodrigo Rodrigues da Silva rodrigo@flowlexi.com

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pavedb-0.9.1.tar.gz (191.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pavedb-0.9.1-py3-none-any.whl (146.8 kB view details)

Uploaded Python 3

File details

Details for the file pavedb-0.9.1.tar.gz.

File metadata

  • Download URL: pavedb-0.9.1.tar.gz
  • Upload date:
  • Size: 191.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for pavedb-0.9.1.tar.gz
Algorithm Hash digest
SHA256 68f5b493251286c6d2580c8fb0d8668784f9e7fe390fdd589f4a237a68d88bdb
MD5 3f27396ca8e3d2158dc09a80db00d212
BLAKE2b-256 ada075ef234d1a9ff81e610bc4baf32064bdf81b4a4cc13880552b90b77bdbaa

See more details on using hashes here.

File details

Details for the file pavedb-0.9.1-py3-none-any.whl.

File metadata

  • Download URL: pavedb-0.9.1-py3-none-any.whl
  • Upload date:
  • Size: 146.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for pavedb-0.9.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ffd7e29de1d20823da58a03a5e6adc55f0efe0fa93262201d003572844c58b87
MD5 0ba9ef8843d9ba056bccc5884ee3a470
BLAKE2b-256 6a4fd56835cd8f6cb712be08e62130d59159f5ae77b27d8f1213d37d92cb325f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page