Pre-release
This release is a pre-release and may not be stable for production use.
A minimal, local-first AI workbench and retrieval-augmented generation (RAG) platform powered by SQLite.
Notice: Pre-Alpha
This package is currently in active pre-alpha development (0.0.0a0). The public API, storage layers, and local-first container runtimes are being actively stabilized.
- Repository: github.com/mesotron-dev/velites
- Author: mesotron.dev
Architecture Highlights
- Hypermedia Frontend: Server-rendered UI using FastAPI, Jinja2, and HTMX, eliminating client-side JavaScript build pipelines and heavy SPA frameworks.
- Dual In-Process Vector Engine: Leverages SQLite C-extensions directly—sqlite-vector for immediate linear scans and vec1 (IVFADC + OPQ) for scalable approximate nearest neighbor search.
- Embedded Storage & Caching: Utilizes local database primitives and embedded key-value caching to manage document chunks, scraping caches, and conversational state without external database servers.
- Minimal Runtime Footprint: Designed around a single-process model packaged on a minimal distroless container base, eliminating background runtime daemons.
Anticipated Use Cases & Applications
- Privacy-First Document Intelligence: Query local PDF archives, private research notes, and internal documentation entirely in-process, ensuring zero data leaves your local host.
- Resource-Constrained Environments: Deploy embedded semantic retrieval to lightweight VPS nodes, developer containers, and local edge hardware where multi-container RAG stacks cannot easily run.
- Semantic Codebase Search: Index repository source trees and API documentation for fast, in-process symbol and context retrieval.
- Embedded Domain Workbenches: Function as an embeddable vector and hybrid retrieval engine for downstream tools, automated pipelines, and specialized local assistants.
License
Licensed under the Apache License, Version 2.0. See LICENSE for details.
1 maintainer
Release files for velites 0.0.0a0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| velites-0.0.0a0.tar.gz | 9.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| velites-0.0.0a0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 20.4 kB
Release files / velites-0.0.0a0.tar.gz
| Download URL | velites-0.0.0a0.tar.gz |
|---|---|
| Size | 9.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6eb800f8c5c87a789df195b9ca0bbe816682f6328379d0724be17d0761b71252
|
|
BLAKE2b-256 checksum How to use checksums |
3d21ca61ea6fb8880679a9bd82aed3d73a680398a5d27e300143d3532c97b6dc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"44","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / velites-0.0.0a0-py3-none-any.whl
| Download URL | velites-0.0.0a0-py3-none-any.whl |
|---|---|
| Size | 10.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4807b05a3fe0ab8112039623798efde0abb89daef7f6c0751e6272dacb94c36e
|
|
BLAKE2b-256 checksum How to use checksums |
817ecef32d20994f4601058eac21523b69a391e838c6e503d2041929382476d8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"44","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
