Skip to content

GraphRAG4OpenWebUI 将 Microsoft 的 GraphRAG 技术集成到 Open WebUI 中,提供多功能的信息检索 API。它结合了本地、全球和网络搜索,用于高级问答系统和搜索引擎。该工具简化了开放 Web 环境中基于图形的检索集成。

active 2024-07-152026-05-23 (UTC)

Partial coverage16,025 / 19,966 hourly files (80%) · 2 absent upstream · 3,940 failed, retryable2024-05-022026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
483
Pushes
24
Pull requests
0
Issues
15
Stars
347
Forks
75

Activity over time

Daily event counts in the loaded window

Line chart, 678 days from 2024-07-15 to 2026-05-23. Pushes: 24 total, peak 16 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 15 total, peak 3 in a day. Comments: 20 total, peak 5 in a day. Stars: 347 total, peak 16 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
win4r282404
xldistance9005
martinzhang7775002
shaoqing4044004
Zomun3001
SpikeYangRc3001
MrCui2001
rickywu1001
IvyWang1521000
daquanG221000
shizhaoyi-git1000
2408397851001

Recent activity

Latest issues, pull requests and releases

  • Issue#19daquanG222025-01-12 03:46
    能否将项目提交到docker,我觉得这样更方便部署?
  • Issue comment#182408397852025-01-09 04:48
    适配graphrag1.0.1,增加drift_search
  • Issue#17xldistance2024-12-22 02:13
    对graphrag0.5.0的适配
  • Issue#18xldistance2024-12-22 02:12
    适配graphrag1.0.1,增加drift_search
  • Issue#15SpikeYangRc2024-08-22 01:27
    When running, the interface will retry infinitely and no result will be output
  • Issue comment#15SpikeYangRc2024-08-13 05:27
    When running, the interface will retry infinitely and no result will be output
  • Issue comment#15xldistance2024-08-13 01:51
    When running, the interface will retry infinitely and no result will be output
  • Issue#15SpikeYangRc2024-08-12 03:33
    When running, the interface will retry infinitely and no result will be output
  • Issue comment#9shaoqing4042024-08-07 06:28
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue#9xldistance2024-08-07 06:16
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue comment#9xldistance2024-08-07 06:16
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue comment#13shaoqing4042024-08-07 05:38
    Question: Does this build the knowledge graph based on the chat history? Or only for uploaded documents?
  • Issue comment#14shaoqing4042024-08-07 05:37
    Question: how to set/where to find parquet files?
  • Issue comment#9shaoqing4042024-08-07 05:35
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue#14IvyWang1522024-08-07 05:22
    Question: how to set/where to find parquet files?
  • Issue comment#12xldistance2024-08-05 06:38
    Retrying request to /embeddings
  • Issue comment#12rickywu2024-08-05 00:41
    Retrying request to /embeddings
  • Issue comment#12xldistance2024-08-03 16:36
    Retrying request to /embeddings
  • Issue comment#10Zomun2024-07-29 02:17
    Ubuntu 运行 python graphrag3dknowledge.py 后未自动打开页面
  • Issue#10Zomun2024-07-29 02:17
    Ubuntu 运行 python graphrag3dknowledge.py 后未自动打开页面
  • Issue#10Zomun2024-07-29 01:45
    Ubuntu 运行 python graphrag3dknowledge.py 后未自动打开页面
  • Issue comment#9xldistance2024-07-26 01:30
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue#9xldistance2024-07-26 01:24
    全局搜索出错,json.loads(search_response)["points"]找不到key points
  • Issue#8shizhaoyi-git2024-07-25 06:38
    local search erro
  • Issue comment#6win4r2024-07-21 23:24
    local query的时候, web ui 总是有很大概率无法展示回答的内容.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 347 stars here means stars gained during the window, not the repo's star count.