Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[pull] main from microsoft:main #11

Merged
merged 196 commits into from
Nov 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
196 commits
Select commit Hold shift + click to select a range
4145167
Add user input to history tracking (#734)
darthtrevino Jul 26, 2024
4e6589b
fix config reader to allow for zero gleans (#735)
darthtrevino Jul 26, 2024
f5c9c2b
Add History input to cache-key, cache data (#736)
darthtrevino Jul 26, 2024
971e7d9
Update issue templates for more explicit guidance (#738)
natoverse Jul 26, 2024
4c229af
add encoding model to text-chunking config (#743)
darthtrevino Jul 26, 2024
8565cd6
Update the ConfigReader to allow for empty chunk-by arrays (#742)
darthtrevino Jul 26, 2024
9d99f32
Add encoding model to entity/claim extraction config sections (#740)
darthtrevino Jul 26, 2024
da5ed4b
Bump actions/stale from 5 to 9 (#759)
dependabot[bot] Jul 29, 2024
5eb58b6
Bump openai from 1.37.0 to 1.37.1 (#760)
dependabot[bot] Jul 29, 2024
56db78a
system -> assistant (#773)
darthtrevino Jul 29, 2024
64fe754
Bump pytest from 8.3.1 to 8.3.2 (#761)
dependabot[bot] Jul 29, 2024
4c181a5
Update issues-autoresolve.yml (#780)
natoverse Jul 30, 2024
70bd2d9
Fix default entity extraction prompt (#781)
ha2trinh Jul 30, 2024
a1506ad
Bump textual from 0.72.0 to 0.74.0 (#762)
dependabot[bot] Jul 30, 2024
ddbe7e1
Bump lancedb from 0.10.2 to 0.11.0 (#763)
dependabot[bot] Jul 30, 2024
da100c7
Bump poethepoet from 0.26.1 to 0.27.0 (#764)
dependabot[bot] Jul 30, 2024
fc9f29d
added default title_column and collection_name values for workflows u…
nievespg1 Jul 30, 2024
d26491a
Gnievesponce/query client vectore store (#771)
nievespg1 Jul 30, 2024
7e1529a
fix community context builder (#783)
ha2trinh Jul 31, 2024
9020df1
Update prompt tune prompts (#794)
AlonsoGuevara Aug 1, 2024
487cb96
Repair json when LLM returns faulty responses on non json mode (#801)
AlonsoGuevara Aug 2, 2024
7b656af
Fix embeddings loading on local search cli (#831)
AlonsoGuevara Aug 5, 2024
4822465
fix json parsing logic and warning message (#833)
ha2trinh Aug 5, 2024
bd326d2
Only repair broken responses (#834)
AlonsoGuevara Aug 6, 2024
5326840
Release v0.2.1 (#835)
AlonsoGuevara Aug 6, 2024
8a1221e
Fix community context builder for local search (#850)
ha2trinh Aug 6, 2024
c749fe2
Docs updates aug06 (#852)
natoverse Aug 6, 2024
1e10bd3
Re-enable smoke tests (#848)
dayesouza Aug 7, 2024
c451aa0
Update smoke tests (#861)
AlonsoGuevara Aug 8, 2024
c88dbb3
Bump json-repair from 0.25.3 to 0.26.0 (#824)
dependabot[bot] Aug 8, 2024
85a5a61
Bump tenacity from 8.5.0 to 9.0.0 (#823)
dependabot[bot] Aug 8, 2024
7376f14
Release v0.2.2 (#872)
AlonsoGuevara Aug 8, 2024
073f650
Fix/json dumps ascii (#873)
AlonsoGuevara Aug 9, 2024
7fd23fa
Stabilize smoke tests for query community context building (#908)
AlonsoGuevara Aug 12, 2024
4bcbfd1
Implement query api (#839)
jgbradley1 Aug 12, 2024
238f1c2
Implement prompt tuning API (#855)
jgbradley1 Aug 12, 2024
5a7dbaa
Fix sort_context max_tokens & max_tokens param in verb (#888)
andresmor-ms Aug 12, 2024
3f31af8
typo summarize prompt (#907)
benx13 Aug 12, 2024
4b9f268
Fix/query embedding (#909)
AlonsoGuevara Aug 12, 2024
f9c1bdd
Release v0.3.0 (#912)
AlonsoGuevara Aug 13, 2024
d68e323
Disable fail fast on tests (#911)
AlonsoGuevara Aug 13, 2024
ac504e3
Add stricter filtering and tests for cli data directory discovery (#910)
natoverse Aug 13, 2024
ba63eda
Bump pyyaml from 6.0.1 to 6.0.2 (#898)
dependabot[bot] Aug 14, 2024
1ec1d2f
Bump azure-storage-blob from 12.21.0 to 12.22.0 (#900)
dependabot[bot] Aug 14, 2024
36facbd
Bump textual from 0.74.0 to 0.76.0 (#901)
dependabot[bot] Aug 14, 2024
0b7c5a6
Add cast check on schema validation for community reports (#932)
AlonsoGuevara Aug 14, 2024
bd5be7b
Update issues-autoresolve.yml (#955)
natoverse Aug 16, 2024
4040f02
Update general_issue.yml (#956)
natoverse Aug 16, 2024
3c0a98c
Add preflight config file validations (#952)
KennyZhang1 Aug 16, 2024
84f9bae
Update 0-architecture.md (#961)
n-y-kim Aug 19, 2024
e4daf35
Fix gh-pages publishing (#976)
AlonsoGuevara Aug 19, 2024
a6238c6
Move embeddings target position (#938)
longyunfeigu Aug 20, 2024
62546a3
Add streaming support for local/global search (#944)
jgbradley1 Aug 20, 2024
5a781dd
Bump nltk from 3.8.1 to 3.9.1 (#966)
dependabot[bot] Aug 20, 2024
6b4de3d
Index API (#953)
dworthen Aug 20, 2024
8a9a2f7
Bump uvloop from 0.19.0 to 0.20.0 (#969)
dependabot[bot] Aug 20, 2024
98cabba
Notebook tests (#978)
natoverse Aug 20, 2024
f5b4d2f
Ci streamline (#988)
natoverse Aug 21, 2024
9c6f5e0
Release v0.3.1 (#1001)
AlonsoGuevara Aug 21, 2024
4b9fdc0
Add context data to query responses (#1003)
jgbradley1 Aug 22, 2024
dd71135
Change lancedb placement (#996)
KennyZhang1 Aug 22, 2024
cb0aae7
Add graphrag_import_neo4j_cypher Notebook (#593)
AlonsoGuevara Aug 23, 2024
b1d4ddd
Bump micromatch from 4.0.5 to 4.0.8 in /docsite (#1013)
dependabot[bot] Aug 23, 2024
13e17d2
Bump ruff from 0.5.7 to 0.6.2 (#1014)
dependabot[bot] Aug 24, 2024
e15df44
Ensure entity types to be str in prompt tune (#1015)
AlonsoGuevara Aug 24, 2024
55e74a0
Fix weight casting during graph extraction (#1016)
AlonsoGuevara Aug 24, 2024
fd8e56c
Update developer guide (#1029)
jgbradley1 Aug 26, 2024
4c2f537
Add missing config parameter for prompt tuning docs (#1017)
AlonsoGuevara Aug 26, 2024
a90d210
Improve search type hint (#1031)
jgbradley1 Aug 26, 2024
32c0cdf
Patch "past" dependency issues (#1033)
AlonsoGuevara Aug 26, 2024
75735bd
Release v0.3.2 (#1034)
AlonsoGuevara Aug 26, 2024
44fd35c
Update VectorStoreSearchResult score value range (#937)
longyunfeigu Aug 27, 2024
5d8e60c
Add source URL to the package (#927)
gukoff Aug 27, 2024
22df2f8
Fix/text unit code cleanup (#1040)
AlonsoGuevara Aug 27, 2024
1b51827
Fix INIT_YAML embeddings default settings (#1039)
TLongP Aug 28, 2024
da440f7
Bump pytest-asyncio from 0.23.8 to 0.24.0 (#1022)
dependabot[bot] Aug 28, 2024
89d1f02
Bump json-repair from 0.26.0 to 0.28.4 (#1044)
dependabot[bot] Aug 28, 2024
2f59701
Bump lancedb from 0.11.0 to 0.12.0 (#1024)
dependabot[bot] Aug 28, 2024
ee734e6
Bump textual from 0.76.0 to 0.78.0 (#1038)
dependabot[bot] Aug 28, 2024
4801817
Fix/entity extraction strategy (#1046)
AlonsoGuevara Aug 28, 2024
a304848
fix for issue 515 (#925)
fantom845 Aug 28, 2024
26bcdf3
docs: update manual_prompt_tuning.md (#963)
eltociear Aug 28, 2024
1e8bb40
Update indexer_adapters.py (#895)
guangxiangdebizi Aug 28, 2024
fb56b7a
Fix circular dependency on prompt tune api (#1054)
AlonsoGuevara Aug 29, 2024
0b1f7db
Bump notebook from 7.2.1 to 7.2.2 (#1055)
dependabot[bot] Aug 29, 2024
d13aec5
Bump jupyterlab from 4.2.4 to 4.2.5 (#1056)
dependabot[bot] Aug 29, 2024
e023882
Update Prompt Tuning docs (#1057)
AlonsoGuevara Aug 29, 2024
6fc452b
Update bash example in docs for prompt tune (#1059)
AlonsoGuevara Aug 29, 2024
7ffce8d
Fix img for autotune (#1060)
AlonsoGuevara Aug 29, 2024
3f98002
Fix img width (#1061)
AlonsoGuevara Aug 29, 2024
ab29cc2
Consistent config load_config (#1065)
dworthen Sep 3, 2024
2d45ece
fix setting base_dir to full paths when not using file system. (#1096)
dworthen Sep 4, 2024
044516f
Clean and organize run index code (#1090)
AlonsoGuevara Sep 5, 2024
27c5468
Load query from blob (#1095)
KennyZhang1 Sep 5, 2024
1b55972
Update create_pipeline_config.py (#1108)
dorbaker Sep 10, 2024
e7ee8cb
release v0.3.3 (#1116)
dworthen Sep 10, 2024
cdf5fc4
Deep copy txt units on local search to avoid race conditions (#1118)
AlonsoGuevara Sep 11, 2024
c0d535d
Fix summarization including empty descriptions (#1124)
AlonsoGuevara Sep 11, 2024
8a0bc05
Release v0.3.4 (#1125)
AlonsoGuevara Sep 11, 2024
7b8f5ba
Correct links to datashaper verbs in comments (#1068)
junho85 Sep 12, 2024
fcfa7b1
Update factories.py to allow the usage of the request timeout ChatOpe…
nriviera Sep 12, 2024
8c7f0df
Fix duplicates in community context builder (#1131)
AlonsoGuevara Sep 12, 2024
cb4f2b4
Fix seeded random gen on clustering step (#1132)
AlonsoGuevara Sep 12, 2024
2de302f
Verb merge nre1 (#1140)
natoverse Sep 16, 2024
d22c0e7
Covariate collapse (#1142)
natoverse Sep 16, 2024
f7f96c3
Cleanup cli (#1127)
jgbradley1 Sep 17, 2024
a473265
Collapse verbs: create_final_text_units (#1143)
natoverse Sep 17, 2024
aa5b426
Collapse final communities workflow (#1150)
natoverse Sep 18, 2024
594084f
Improve and cleanup logging output of indexing (#1144)
jgbradley1 Sep 18, 2024
1091079
Fix seed init in clustering (#1156)
AlonsoGuevara Sep 18, 2024
3b09df6
Migrate towards using static output directories (#1113)
dworthen Sep 18, 2024
ac234f4
Fix prompt tune output path on cli (#1157)
AlonsoGuevara Sep 19, 2024
95409ff
Remove lancedb_dir redundant assignments (#1163)
longyunfeigu Sep 19, 2024
96a2460
Release v0.3.5 (#1166)
AlonsoGuevara Sep 19, 2024
84fb14c
Chore/dependency cleanup (#1169)
AlonsoGuevara Sep 19, 2024
bd2c1da
Bump path-to-regexp from 6.2.1 to 6.3.0 in /docsite (#1130)
dependabot[bot] Sep 19, 2024
ae094bb
Collapse create final relationships (#1158)
natoverse Sep 19, 2024
b61c4ec
Bump JamesIves/github-pages-deploy-action from 4.6.3 to 4.6.4 (#1104)
dependabot[bot] Sep 20, 2024
16b4ea5
Release v0.3.6 (#1172)
AlonsoGuevara Sep 20, 2024
1dbcc42
Remove redundant code from error-handling code in GlobalSearch (#1170)
darthtrevino Sep 20, 2024
fb65989
Incremental indexing/update old outputs (#1155)
AlonsoGuevara Sep 20, 2024
f8ab1b3
Collapse create_final_nodes (#1171)
natoverse Sep 20, 2024
ea46820
Fix typo in documentation for customizability (#1160)
junho85 Sep 20, 2024
fbc483e
Collapse create base documents (#1176)
natoverse Sep 23, 2024
be7d3eb
Remove aggregate_df from final coomunities and final text units (#1179)
AlonsoGuevara Sep 23, 2024
1755afb
Collapse create base text units (#1178)
natoverse Sep 23, 2024
f518c8b
Collapse relationship embeddings (#1199)
natoverse Sep 24, 2024
dda4edd
Pandas-ify Create Base Documents (#1209)
AlonsoGuevara Sep 25, 2024
14750f4
Collapse create final documents (#1217)
natoverse Sep 25, 2024
0952014
Fix issue 1173 - Nested json parsing (#1218)
AlonsoGuevara Sep 25, 2024
73e709b
Collapse create final covariates (#1215)
natoverse Sep 25, 2024
3217013
Revisit create final text units (#1216)
natoverse Sep 25, 2024
ce71bcf
Collapse create final entities (#1220)
natoverse Sep 26, 2024
737a471
Pandas-ify Create Final Entities (#1225)
AlonsoGuevara Sep 26, 2024
0d348d6
Remove unused cols from final entities (#1226)
AlonsoGuevara Sep 27, 2024
00d5e77
Collapse create final community reports (#1227)
natoverse Sep 30, 2024
5220bb7
Collapse create base entity graph (#1233)
natoverse Sep 30, 2024
630679f
Collapse create summarized entities (#1237)
natoverse Oct 1, 2024
9070ea5
Collapse create base extracted entities (#1235)
natoverse Oct 1, 2024
f5c5876
Reorganize flows (#1240)
natoverse Oct 2, 2024
718d1ef
Migrate embedding operations (#1242)
natoverse Oct 3, 2024
61b3d6d
Migrate helper verbs (#1248)
natoverse Oct 9, 2024
d66901e
Update description of GRAPHRAG_CACHE_BASE_DIR in env_vars.md (#1213)
junho85 Oct 9, 2024
d4a0a59
Change config.json references to settings.json in the configuration d…
junho85 Oct 9, 2024
9fa6b91
Chore/community context clean (#1262)
AlonsoGuevara Oct 9, 2024
cd4f1fa
Adding fix per comment on Issue-692 (#1255)
sbhuttan Oct 9, 2024
ce8749b
Fix: Add await to LLM execution for async handling (#1206)
9prodhi Oct 9, 2024
d9a005c
Reorganize python package structure (#1214)
jgbradley1 Oct 10, 2024
fc9895f
Replace current docs by mkdocs (#1263)
andresmor-ms Oct 11, 2024
cb052a7
Dependency updates (#1272)
AlonsoGuevara Oct 12, 2024
137a5cd
Fix/docs auto prompt img (#1283)
andresmor-ms Oct 14, 2024
ce5b120
Collapse graph documents workflows (#1284)
natoverse Oct 15, 2024
fc502ee
Fix cookie consent script missing (#1292)
andresmor-ms Oct 17, 2024
1f70d42
Empty workflow returns (#1291)
natoverse Oct 17, 2024
6aae386
Perf optimizations in map_query_to_entities() (#1276)
mmaitre314 Oct 21, 2024
e0840a2
Fix vector store logic and refactor audience parameter (#1259)
KennyZhang1 Oct 21, 2024
8a6d4e6
DRIFT Search (#1285)
AlonsoGuevara Oct 21, 2024
8d8c67d
fix typo. Update documentation URLs for consistency (#1298)
junho85 Oct 21, 2024
77e7777
Fix drift search edge cases over small input sets (#1310)
AlonsoGuevara Oct 22, 2024
3df6f8c
Allow ci/cd to skip draft PRs (#1314)
jgbradley1 Oct 23, 2024
ac09e0a
Feature/optimize count relationships (#1312)
AlonsoGuevara Oct 23, 2024
94f1e62
Rework workflow architecture (#1311)
natoverse Oct 24, 2024
d6e6f5c
Convert CLI to Typer app (#1305)
jgbradley1 Oct 24, 2024
083de12
Auto-generate CLI doc pages (#1325)
jgbradley1 Oct 25, 2024
83026bd
Remove duplicated entried from relationships and nodes (#1333)
AlonsoGuevara Oct 29, 2024
0cc79b9
Add backwards compatibility patch for vector store (#1334)
jgbradley1 Oct 29, 2024
7235c6f
Add Incremental Indexing v1 (#1318)
AlonsoGuevara Oct 30, 2024
8302920
move mkdocs-typer to devdeps (#1331)
darthtrevino Oct 30, 2024
17658c5
New workflow to generate embeddings in a single workflow (#1296)
gaudyb Nov 1, 2024
634e3ed
Transient entity graph (#1349)
natoverse Nov 5, 2024
68dfcee
Updated the variable names within the for-loop to differentiate betwe…
nievespg1 Nov 5, 2024
d9f985a
Drift Search CLI, API, Docs and Example Notebook (#1348)
AlonsoGuevara Nov 5, 2024
1557ce3
Fix init defaults for vector store and img in drift docs (#1357)
AlonsoGuevara Nov 5, 2024
83bd5ce
Fix content embedding container name (#1358)
AlonsoGuevara Nov 5, 2024
80c0c7b
Update Incremental Indexing to new embeddings workflow (#1359)
AlonsoGuevara Nov 5, 2024
635c211
Fix Community ID loading for DRIFT search over existing indexes (#1360)
AlonsoGuevara Nov 6, 2024
a6d9b0c
Release v0.4.0 (#1361)
AlonsoGuevara Nov 6, 2024
9762f33
Add visualization guide (#1340)
jgbradley1 Nov 6, 2024
0394b55
Update CI/CD - skip running unit tests on documentation-only PRs (#1371)
jgbradley1 Nov 6, 2024
2047c15
Fix styling and misalignment on drift docs (#1373)
AlonsoGuevara Nov 6, 2024
a8ccded
Fix file path issue in the viz guide (#1372)
jgbradley1 Nov 6, 2024
1661672
Fix optional covariates check in incremental indexing (#1374)
AlonsoGuevara Nov 6, 2024
3d79de9
Raise error on empty deltas for incremental indexing (#1375)
AlonsoGuevara Nov 6, 2024
baa261c
[bugfix]Fix query error with --streaming (#1368)
KylinMountain Nov 6, 2024
20c1202
Feat/update cli (#1376)
AlonsoGuevara Nov 7, 2024
ba50caa
Release v0.4.1 (#1387)
AlonsoGuevara Nov 8, 2024
e534223
Implement dynamic community selection for global search (#1396)
AlonsoGuevara Nov 12, 2024
c8c354e
Artifact cleanup (#1341)
natoverse Nov 13, 2024
51912b2
Move prompts (#1404)
natoverse Nov 14, 2024
c90166c
Add Parquet as part of the default emitters when not present (#1407)
AlonsoGuevara Nov 14, 2024
0a58010
Fix documentation for generate_indexing_prompts (#1336)
jeffbaumes Nov 14, 2024
ec9cdcc
fix typo. Correct the wording "global search" to "drift search" in dr…
junho85 Nov 14, 2024
425dbc6
Docs update (#1408)
natoverse Nov 15, 2024
9b4f24e
First cut at config cleanup (#1411)
natoverse Nov 15, 2024
22a57d1
Improve CLI speed with lazy imports (#1319)
jgbradley1 Nov 16, 2024
6d21ef2
Release v0.5.0 (#1415)
AlonsoGuevara Nov 18, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
11 changes: 11 additions & 0 deletions .gitattributes
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
*.txt text eol=lf
*.md text eol=lf
*.yml text eol=lf
*.html text eol=lf
*.py text eol=lf
*.toml text eol=lf
.gitattributes text eol=lf
.gitignore text eol=lf
*.lock
CODEOWNERS text eol=lf
LICENSE text eol=lf
69 changes: 0 additions & 69 deletions .github/ISSUE_TEMPLATE.md

This file was deleted.

9 changes: 5 additions & 4 deletions .github/ISSUE_TEMPLATE/bug_report.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,11 +7,12 @@ body:
- type: checkboxes
id: existingcheck
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the bug you encountered.
label: Do you need to file an issue?
description: Please help us manage our time by avoiding duplicates and common questions with the steps below.
options:
- label: I have searched the existing issues
- label: I have checked [#657](https://github.com/microsoft/graphrag/issues/657) to validate if my issue is covered by community support
- label: I have searched the existing issues and this bug is not already filed.
- label: My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
- label: I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.
- type: textarea
id: description
attributes:
Expand Down
9 changes: 9 additions & 0 deletions .github/ISSUE_TEMPLATE/feature_request.yml
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,15 @@ labels: ["enhancement"]
title: "[Feature Request]: <title>"

body:
- type: checkboxes
id: existingcheck
attributes:
label: Do you need to file an issue?
description: Please help us manage our time by avoiding duplicates and common questions with the steps below.
options:
- label: I have searched the existing issues and this feature is not already filed.
- label: My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
- label: I believe this is a legitimate feature request, not just a question. If this is a question, please use the Discussions area.
- type: textarea
id: problem_description
attributes:
Expand Down
9 changes: 5 additions & 4 deletions .github/ISSUE_TEMPLATE/general_issue.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,11 +7,12 @@ body:
- type: checkboxes
id: existingcheck
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the bug you encountered.
label: Do you need to file an issue?
description: Please help us manage our time by avoiding duplicates and common questions with the steps below.
options:
- label: I have searched the existing issues
- label: I have checked [#657](https://github.com/microsoft/graphrag/issues/657) to validate if my issue is covered by community support
- label: I have searched the existing issues and this bug is not already filed.
- label: My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
- label: I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.
- type: textarea
id: description
attributes:
Expand Down
4 changes: 0 additions & 4 deletions .github/dependabot.yml
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,6 @@
# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
version: 2
updates:
- package-ecosystem: "npm" # See documentation for possible values
directory: "docsite/" # Location of package manifests
schedule:
interval: "weekly"
- package-ecosystem: "pip" # See documentation for possible values
directory: "/" # Location of package manifests
schedule:
Expand Down
76 changes: 16 additions & 60 deletions .github/workflows/gh-pages.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,44 +2,22 @@ name: gh-pages
on:
push:
branches: [main]

permissions:
contents: write

env:
POETRY_VERSION: 1.8.3
PYTHON_VERSION: "3.11"
NODE_VERSION: 18.x
POETRY_VERSION: '1.8.3'
PYTHON_VERSION: '3.11'

jobs:
build:
runs-on: ubuntu-latest
env:
GH_PAGES: 1
DEBUG: 1
GRAPHRAG_LLM_TYPE: "azure_openai_chat"
GRAPHRAG_EMBEDDING_TYPE: "azure_openai_embedding"
GRAPHRAG_API_KEY: ${{ secrets.OPENAI_API_KEY }}
GRAPHRAG_API_BASE: ${{ secrets.GRAPHRAG_API_BASE }}
GRAPHRAG_API_VERSION: ${{ secrets.GRAPHRAG_API_VERSION }}
GRAPHRAG_LLM_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_LLM_DEPLOYMENT_NAME }}
GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME }}
GRAPHRAG_CACHE_TYPE: "blob"
GRAPHRAG_CACHE_CONNECTION_STRING: ${{ secrets.BLOB_STORAGE_CONNECTION_STRING }}
GRAPHRAG_CACHE_CONTAINER_NAME: "cicache"
GRAPHRAG_CACHE_BASE_DIR": "cache"
GRAPHRAG_LLM_MODEL: gpt-3.5-turbo-16k
GRAPHRAG_EMBEDDING_MODEL: text-embedding-ada-002
# We have Windows + Linux runners in 3.10 and 3.11, so we need to divide the rate limits by 4
GRAPHRAG_LLM_TPM: 45_000 # 180,000 / 4
GRAPHRAG_LLM_RPM: 270 # 1,080 / 4
GRAPHRAG_EMBEDDING_TPM: 87_500 # 350,000 / 4
GRAPHRAG_EMBEDDING_RPM: 525 # 2,100 / 4
GRAPHRAG_CHUNK_SIZE: 1200
GRAPHRAG_CHUNK_OVERLAP: 0
# Azure AI Search config
AZURE_AI_SEARCH_URL_ENDPOINT: ${{ secrets.AZURE_AI_SEARCH_URL_ENDPOINT }}
AZURE_AI_SEARCH_API_KEY: ${{ secrets.AZURE_AI_SEARCH_API_KEY }}
GRAPHRAG_API_KEY: ${{ secrets.OPENAI_NOTEBOOK_KEY }}
GRAPHRAG_LLM_MODEL: ${{ secrets.GRAPHRAG_LLM_MODEL }}
GRAPHRAG_EMBEDDING_MODEL: ${{ secrets.GRAPHRAG_EMBEDDING_MODEL }}

steps:
- uses: actions/checkout@v4
Expand All @@ -56,42 +34,20 @@ jobs:
with:
poetry-version: ${{ env.POETRY_VERSION }}

- name: Use Node ${{ env.NODE_VERSION }}
uses: actions/setup-node@v4
with:
node-version: ${{ env.NODE_VERSION }}

- name: Install Yarn dependencies
run: yarn install
working-directory: docsite

- name: Install Poetry dependencies
- name: poetry intsall
shell: bash
run: poetry install

- name: mkdocs build
shell: bash
run: poetry run poe build_docs

- name: Install Azurite
id: azuright
uses: potatoqualitee/[email protected]

- name: Generate Indexer Outputs
run: |
poetry run poe test_smoke
zip -jrm docsite/data/operation_dulce/dataset.zip tests/fixtures/min-csv/output/*/artifacts/*.parquet

- name: Build Jupyter Notebooks
run: poetry run poe convert_docsite_notebooks

- name: Build docsite
run: yarn build
working-directory: docsite
env:
DOCSITE_BASE_URL: "graphrag"

- name: List docsite files
run: find docsite/_site
- name: List Docsite Contents
run: find site

- name: Deploy to GitHub Pages
uses: JamesIves/[email protected].3
uses: JamesIves/[email protected].4
with:
branch: gh-pages
folder: docsite/_site
clean: true
folder: site
clean: true
9 changes: 7 additions & 2 deletions .github/workflows/issues-autoresolve.yml
Original file line number Diff line number Diff line change
Expand Up @@ -3,22 +3,27 @@ on:
schedule:
- cron: "30 1 * * *"

permissions:
actions: write
issues: write
pull-requests: write

jobs:
close-issues:
runs-on: ubuntu-latest
permissions:
issues: write
pull-requests: write
steps:
- uses: actions/stale@v5
- uses: actions/stale@v9
with:
days-before-issue-stale: 7
days-before-issue-close: 5
stale-issue-label: "stale"
close-issue-label: "autoresolved"
stale-issue-message: "This issue has been marked stale due to inactivity after repo maintainer or community member responses that request more information or suggest a solution. It will be closed after five additional days."
close-issue-message: "This issue has been closed after being marked as stale for five days. Please reopen if needed."
exempt-issue-label: "triage"
any-of-labels: "awaiting_response"
days-before-pr-stale: -1
days-before-pr-close: -1
repo-token: ${{ secrets.GITHUB_TOKEN }}
30 changes: 0 additions & 30 deletions .github/workflows/javascript-ci.yml

This file was deleted.

Loading