# georgia-tech-db/evadb

Database system for AI-powered apps

Repository: https://github.com/georgia-tech-db/evadb
Canonical: https://ross.abutalabs.com/products/evadb
Homepage: https://evadb.readthedocs.io/en/stable/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: eva, video-analytics, serving, database, labeling, object-detection, data-analysis, ai, chatgpt, langchain, auto-gpt, gpt4all, huggingface, llm, gpt-4, agent, hacktoberfest
Archived: true
Last push: 2024-05-17T16:33:06+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2915, "days_push": 838, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2673, forks 260 (observed 2026-08-28T04:07:09.615361+00:00)

## What it is
EvaDB is a Python database system for building AI-powered applications, exposing a SQL API that queries structured data, videos, and unstructured data with AI functions like object detection and LLM calls. It integrates with Hugging Face models and LLM frameworks to simplify AI app development into a few lines of code.

## Use cases
- run object detection queries over videos with sql
- build ai apps that query data with llm functions
- analyze video content using a database
- add ai-powered search over unstructured data
- query huggingface models from sql
- label and analyze datasets with ai models

## When to choose
- you want to combine sql queries with ai/llm functions in one system
- you need video analytics with object detection via a query interface
- you're prototyping ai apps in python with minimal code

## When to avoid
- you need a production-grade general-purpose oltp database
- you only need standard sql without ai functions
- you need extremely low-latency transactional workloads

## Facets
- artifact type: library
- maturity: active
- function: database, machine-learning, video-processing, rag, llm-inference, data-science
- domain: databases, artificial-intelligence, machine-learning, data-science
- platform: python, cross-platform
- tags: ai-powered-database, video-analytics, sql-api, llm-integration, object-detection, huggingface, sql, video

## Member repositories
- georgia-tech-db/evadb (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:09.615361+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:18:05.442524+00:00, confidence not recorded.
  - readme: https://github.com/georgia-tech-db/evadb (fetched 2026-08-28T04:07:09.615361+00:00, sha 48c30a2187c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.