Skip to content

RAG Stack - Multi component setup for a RAG system

active 2026-03-012026-08-14 (UTC)

Partial coverage20,534 / 26,290 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
263
Pushes
113
Pull requests
12
Issues
10
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 167 days from 2026-03-01 to 2026-08-14. Pushes: 113 total, peak 15 in a day. Pull requests: 12 total, peak 3 in a day. Issues: 10 total, peak 4 in a day. Comments: 8 total, peak 5 in a day. Stars: 0 total, peak 0 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
wilke136111123
Copilot8205

Recent activity

Latest issues, pull requests and releases

  • Pull request#313wilke2026-08-10 22:09
  • Issue comment#301wilke2026-08-08 01:32
    feat(ingest): JATS/OA ingest plane — loader metadata pass-through, shard planner, jats-extract CWL
  • Pull request#292wilke2026-08-07 20:29
  • Issue#291wilke2026-08-07 19:46
    feat(collections): per-collection size cap (max chunks) — the actual limit for personal collections
  • Issue#290wilke2026-08-07 16:46
    feat(collections): per-user collection quota enforced on ACQUISITION (create AND transfer), alongside the per-tenant cap
  • Issue#288wilke2026-08-07 16:35
    docs(adr-0003): correct the measured collection-cost figures — threads and mmaps are misattributed
  • Issue#285wilke2026-08-07 16:33
    bug(collections): DELETE purge=false orphans the physical stores — unbounded DoS that MAX_COLLECTIONS cannot see
  • Pull request#233wilke2026-08-04 01:00
  • Pull request#157wilke2026-07-05 05:18
  • Pull request#152wilke2026-07-05 03:16
  • Pull request#153wilke2026-07-05 02:58
  • Issue#134wilke2026-07-03 23:22
    IngestionPipeline.ingest: per-doc delete-prior is not atomic — a fully-quarantined doc in a multi-doc source loses its prior data
  • Pull request#121wilke2026-07-03 05:09
  • Pull request#120wilke2026-07-03 05:08
  • Issue comment#71wilke2026-07-01 16:23
    ingest_jsonl: bounded look-ahead + --batch-retries; and #66 phase-2 (--chunk-concurrency)
  • Issue#43wilke2026-06-30 21:07
    Chunkers: size by tokens (not chars), saner defaults, hard context cap
  • Issue comment#27wilke2026-06-30 01:43
    Reranker: deeper-pool retrieval is unconditional when enabled (no per-request opt-out)
  • Issue#30wilke2026-06-30 01:36
    Add sentence/word-aware and semantic chunkers (Chunker protocol)
  • Issue#28wilke2026-06-30 01:03
    Reranker: SidecarReranker duplicates SidecarEmbedder HTTP boilerplate
  • Pull request#37wilke2026-06-30 00:47
  • Issue#31wilke2026-06-30 00:31
    ingest_jsonl re-ingest on a large collection loses data: filtered delete-before-upsert times out (ResponseHandlingException)
  • Pull request#22wilke2026-06-29 23:26
  • Issue#28wilke2026-06-29 22:47
    Reranker: SidecarReranker duplicates SidecarEmbedder HTTP boilerplate
  • Pull request#17wilke2026-06-26 22:33
  • Pull request#2wilke2026-03-01 22:45

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.