Skip to content

A PostgreSQL extension to create chunk tables for existing text data, and populate them with embeddings using your favourite LLM.

active 2025-12-022026-08-12 (UTC)

Complete coverage26,562 / 26,562 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
113
Pushes
53
Pull requests
3
Issues
7
Stars
11
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 254 days from 2025-12-02 to 2026-08-12. Pushes: 53 total, peak 7 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 7 total, peak 3 in a day. Comments: 18 total, peak 3 in a day. Stars: 11 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
dpage514203
coderabbitai[bot]20009
mason-sharp8600
syedkazim1106014
AntTheLimey4210
danolivo2200
susan-pgedge2110
Copilot1001
bonesmoses1000
codacy-production[bot]1001

Recent activity

Latest issues, pull requests and releases

  • Issue#24mason-sharp2026-08-05 22:05
    Orphaned chunks/embeddings when source rows are DELETEd or table is TRUNCATEd
  • Issue#27dpage2026-06-01 08:59
    Model selection: support per-table models and handle model change on populated embedding tables
  • Issue comment#22coderabbitai[bot]2026-05-29 00:35
    Expose count_tokens() and add refresh_token_counts() helper
  • Issue comment#22syedkazim1102026-05-29 00:35
    Expose count_tokens() and add refresh_token_counts() helper
  • Issue#19AntTheLimey2026-05-26 21:35
    Auto-set api_url based on provider setting
  • Issue comment#18syedkazim1102026-04-30 23:04
    Add tiktoken integration for accurate token counting
  • Issue comment#18syedkazim1102026-04-25 19:06
    Add tiktoken integration for accurate token counting
  • Issue comment#17codacy-production[bot]2026-04-13 09:36
    SPOC-471: fix Codacy-reported security concerns
  • Issue comment#14dpage2026-04-09 18:55
    Add Gemini provider, custom URLs, local providers, and extra headers
  • Pull request#13syedkazim1102026-04-08 00:02
  • Issue comment#13syedkazim1102026-04-06 07:25
    Add hybrid BM25 + dense vector search with Reciprocal Rank Fusion
  • Issue comment#11coderabbitai[bot]2026-02-12 14:29
    Support any single-column primary key type for vectorized tables
  • Pull request#11AntTheLimey2026-02-07 17:23
  • Issue#10bonesmoses2026-02-02 18:00
    Queue Processing Doesn't Start Until SIGHUP
  • Issue comment#8dpage2026-01-31 07:48
    Feature Request: Derive embedding dimension size from current model.
  • Issue#9dpage2026-01-30 21:14
    Feature Request: Check for existing chunks when enabling chunking.
  • Issue#5dpage2026-01-30 21:10
    Apparent Postgres SPI Bug in Queue Cleanup Code
  • Issue#4dpage2026-01-30 21:07
    Clarify that pgedge_vectorizer.databases parameter is required for standard operation.
  • Issue comment#4dpage2026-01-30 21:07
    Clarify that pgedge_vectorizer.databases parameter is required for standard operation.
  • Issue comment#2coderabbitai[bot]2026-01-13 12:08
    Add Hybrid and Markdown Chunking Strategies with Automatic Fallback
  • Pull request#1susan-pgedge2025-12-17 17:05

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 11 stars here means stars gained during the window, not the repo's star count.