yujunjun/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2025-12-05 03:18:59 +00:00
Code Issues Packages Projects Releases Wiki Activity
100 Commits 32 Branches 29 Tags
Commit Graph

100 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Nathan Evans
ac504e31a0
Add stricter filtering and tests for cli data directory discovery (#910) 
* Add stricter filtering and tests for cli data directory discovery

* Semver

* Ignore ruff on error type

* Format

* Fix for windows paths

* Fix for windows paths

* Uncomment blob tests

* Sort by timestamp name instead of modified date

* Format

* Add additional folder name test
 2024-08-13 17:34:14 -06:00
Alonso Guevara
d68e323193
Disable fail fast on tests (#911) 2024-08-13 12:20:14 -06:00
Alonso Guevara
f9c1bdd748
Release v0.3.0 (#912) v0.3.0 2024-08-12 18:14:52 -06:00
Alonso Guevara
4b9f268604
Fix/query embedding (#909) 
* fix strategy config in entity_extraction

* should not post token list to the embedding model

* fix embedding in local query

* add sembersioner

* remove strategy

---------

Co-authored-by: KylinMountain <kose2livs@gmail.com>
 2024-08-12 17:12:51 -06:00
benx13
3f31af80d2
typo summarize prompt (#907) 
* typo in  entity_summarization prompt

* typo in summarize prompt

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-12 16:03:08 -06:00
Andres Morales
5a7dbaa051
Fix sort_context max_tokens & max_tokens param in verb (#888) 
* Fix sort_context max_tokens & max_tokens param in verb

* Fix sort_context for windows test

* add semversioner file

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-12 15:55:31 -06:00
Josh Bradley
238f1c2adc
Implement prompt tuning API (#855) 
* initial setup commit

* cleanup API and CLI interfaces

* move datatype definition to types.py

* code cleanup

* add semversioner file

* remove unused import

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-12 15:09:00 -06:00
Josh Bradley
4bcbfd10eb
Implement query api (#839) 
* initial API redesign

* typo fix

* update docstring

* update docsring

* remove artifacts caused by the merge from main

* minor typo updates

* add semversioner check

* switch API to async function calls

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-12 13:40:10 -06:00
Alonso Guevara
7fd23fa79c
Stabilize smoke tests for query community context building (#908) 
* Stabilize smoke tests for query community context building

* Fix CODEOWNERS
 2024-08-12 13:17:40 -06:00
Alonso Guevara
073f650ba9
Fix/json dumps ascii (#873) 
* Ensure ascii false in json dumps, support for non ASCII chars

* Format

* Semver
 2024-08-09 17:05:48 -06:00
Alonso Guevara
7376f149d2
Release v0.2.2 (#872) v0.2.2 2024-08-08 16:48:47 -06:00
dependabot[bot]
85a5a61340
Bump tenacity from 8.5.0 to 9.0.0 (#823) 
Bumps [tenacity](https://github.com/jd/tenacity) from 8.5.0 to 9.0.0.
- [Release notes](https://github.com/jd/tenacity/releases)
- [Commits](https://github.com/jd/tenacity/compare/8.5.0...9.0.0)

---
updated-dependencies:
- dependency-name: tenacity
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-08-08 16:39:15 -06:00
dependabot[bot]
c88dbb3575
Bump json-repair from 0.25.3 to 0.26.0 (#824) 
Bumps [json-repair](https://github.com/mangiucugna/json_repair) from 0.25.3 to 0.26.0.
- [Release notes](https://github.com/mangiucugna/json_repair/releases)
- [Commits](https://github.com/mangiucugna/json_repair/compare/0.25.3...0.26.0)

---
updated-dependencies:
- dependency-name: json-repair
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-08 15:27:13 -06:00
Alonso Guevara
c451aa0093
Update smoke tests (#861) 
* Run smoke tests on 4o

* Shorten dulce for smoke tests

* Update secrets for consistency
 2024-08-08 13:07:44 -06:00
Dayenne Souza
1e10bd342e
Re-enable smoke tests (#848) 
* add smoke tests again

* add smoke tests separated action

* add patch version

* disable blob test

* blob conn again

* add file as cache type

* remove cache type enterely

* increase timeout

* remove comment

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-07 12:23:46 -06:00
Nathan Evans
c749fe2a15
Docs updates aug06 (#852) 
* Remove outdated references to entity resolution

* Clarify covariate extraction

* Minor edits from other PR feedback

* Remove duplicate line

* Semver

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-06 16:31:47 -07:00
Ha Trinh
8a1221e0e4
Fix community context builder for local search (#850) 
* add a check for empty context

* remove log and format code

* add changelog

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-06 16:08:45 -07:00
Alonso Guevara
53268406fe
Release v0.2.1 (#835) v0.2.1 2024-08-05 18:45:28 -06:00
Alonso Guevara
bd326d2614
Only repair broken responses (#834) 
* Only repair broken reponses

* Format
 2024-08-05 18:25:08 -06:00
Ha Trinh
482246528d
fix json parsing logic and warning message (#833) 
* fix json parsing logic and warning message

* amended warning message

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-08-05 16:31:36 -06:00
Alonso Guevara
7b656af50c
Fix embeddings loading on local search cli (#831) 
* Fix embeddings loading on local search cli

* Update lockfile

* Update rules in ruff check
 2024-08-05 16:00:31 -06:00
Alonso Guevara
487cb96376
Repair json when LLM returns faulty responses on non json mode (#801) 
* fixed json issue

* change to use try_parse_json_object onlu

* pyproject add json-repair

* add check extra description before and after json object

* json.loads() before repire_json, based on jbradley1 suggestion.

* Fix json parsing and formatting

* semver

* Nicer tuple parsing

---------

Co-authored-by: paulg <paul.guo@iag.com.au>
 2024-08-01 19:38:50 -06:00
Alonso Guevara
9020df1770
Update prompt tune prompts (#794) 
* Update prompts in prompt tune

* Update prompt tuning meta prompts

* Semver

* Formatting

* Update examples
 2024-08-01 17:27:08 -06:00
Ha Trinh
7e1529ac19
fix community context builder (#783) 
fix and refactor community context builder

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-30 20:14:40 -06:00
Gabriel Nieves-Ponce
d26491a622
Gnievesponce/query client vectore store (#771) 
* added default title_column and collection_name values for workflows using the vector store option

* incorporated vector database support to the query client

* Updated docuemnatation to reflect the new query client param.

* Fixed ruff formatting

* added new poetry lock file

---------

Co-authored-by: Gabriel Nieves-Ponce <gnievesponce@microsoft.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-30 17:59:04 -06:00
Gabriel Nieves-Ponce
fc9f29dccd
added default title_column and collection_name values for workflows u… (#677) 
* added default title_column and collection_name values for workflows using the vector store option

* update poetry lockfile

* fixed ruff formatting

* ran semversioner

---------

Co-authored-by: Gabriel Nieves-Ponce <gnievesponce@microsoft.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
Co-authored-by: Josh Bradley <joshbradley@microsoft.com>
 2024-07-30 17:46:58 -06:00
dependabot[bot]
da100c7acf
Bump poethepoet from 0.26.1 to 0.27.0 (#764) 
Bumps [poethepoet](https://github.com/nat-n/poethepoet) from 0.26.1 to 0.27.0.
- [Release notes](https://github.com/nat-n/poethepoet/releases)
- [Commits](https://github.com/nat-n/poethepoet/compare/v0.26.1...v0.27.0)

---
updated-dependencies:
- dependency-name: poethepoet
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-07-30 17:17:28 -06:00
dependabot[bot]
ddbe7e1d80
Bump lancedb from 0.10.2 to 0.11.0 (#763) 
Bumps [lancedb](https://github.com/lancedb/lancedb) from 0.10.2 to 0.11.0.
- [Release notes](https://github.com/lancedb/lancedb/releases)
- [Changelog](https://github.com/lancedb/lancedb/blob/main/release_process.md)
- [Commits](https://github.com/lancedb/lancedb/compare/python-v0.10.2...python-v0.11.0)

---
updated-dependencies:
- dependency-name: lancedb
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-07-30 16:53:22 -06:00
dependabot[bot]
a1506ad26e
Bump textual from 0.72.0 to 0.74.0 (#762) 
Bumps [textual](https://github.com/Textualize/textual) from 0.72.0 to 0.74.0.
- [Release notes](https://github.com/Textualize/textual/releases)
- [Changelog](https://github.com/Textualize/textual/blob/main/CHANGELOG.md)
- [Commits](https://github.com/Textualize/textual/compare/v0.72.0...v0.74.0)

---
updated-dependencies:
- dependency-name: textual
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-30 16:26:15 -06:00
Ha Trinh
70bd2d9a55
Fix default entity extraction prompt (#781) 
* fixed default entity extraction prompts

* minor changes and formatting

* add missing parenthesis and changelog

* Updating dictionary

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-30 15:41:10 -06:00
Nathan Evans
4c181a5390
Update issues-autoresolve.yml (#780) 
Switch the logic to only look for awaiting_response label
 2024-07-30 11:35:55 -06:00
dependabot[bot]
64fe754397
Bump pytest from 8.3.1 to 8.3.2 (#761) 
Bumps [pytest](https://github.com/pytest-dev/pytest) from 8.3.1 to 8.3.2.
- [Release notes](https://github.com/pytest-dev/pytest/releases)
- [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pytest-dev/pytest/compare/8.3.1...8.3.2)

---
updated-dependencies:
- dependency-name: pytest
  dependency-type: direct:development
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-29 16:27:24 -06:00
Chris Trevino
56db78ae38
system -> assistant (#773) 
* system -> assistant

* semver
 2024-07-29 14:56:55 -07:00
dependabot[bot]
5eb58b6826
Bump openai from 1.37.0 to 1.37.1 (#760) 
Bumps [openai](https://github.com/openai/openai-python) from 1.37.0 to 1.37.1.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-python/compare/v1.37.0...v1.37.1)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-29 14:53:27 -06:00
dependabot[bot]
da5ed4baf4
Bump actions/stale from 5 to 9 (#759) 
Bumps [actions/stale](https://github.com/actions/stale) from 5 to 9.
- [Release notes](https://github.com/actions/stale/releases)
- [Changelog](https://github.com/actions/stale/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/stale/compare/v5...v9)

---
updated-dependencies:
- dependency-name: actions/stale
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-07-29 14:34:13 -06:00
Chris Trevino
9d99f323ea
Add encoding model to entity/claim extraction config sections (#740) 
* Add encoding-model configuration to entity & claim extraction

* add change note

* pr updates

* test fix

* disable GH-based smoke tests
 2024-07-26 15:05:08 -07:00
Chris Trevino
8565cd66c5
Update the ConfigReader to allow for empty chunk-by arrays (#742) 2024-07-26 14:38:44 -07:00
Chris Trevino
4c229afec8
add encoding model to text-chunking config (#743) 
* add encoding model to text-chunking config

* revert groupby fix, handled in other pr

* revert environment reader update for other pr
 2024-07-26 14:15:17 -07:00
Nathan Evans
971e7d91f5
Update issue templates for more explicit guidance (#738) 2024-07-26 14:52:14 -04:00
Chris Trevino
f5c9c2bee0
Add History input to cache-key, cache data (#736) 
* Update caching llm to use history inputs

* formatting

* linting

* update glean sections to have continuous history
 2024-07-26 09:26:37 -07:00
Chris Trevino
4e6589b614
fix config reader to allow for zero gleans (#735) 2024-07-26 09:11:34 -07:00
Chris Trevino
41451675ba
Add user input to history tracking (#734) 
add user input to history tracking
 2024-07-26 09:11:18 -07:00
Alonso Guevara
61b5eea347
Fix version numbering on publication (#701) 2024-07-24 22:02:52 -06:00
Alonso Guevara
c8aefb23cb
v0.2.0 (#700) 
* v0.2.0

* Update 0.2.0.json

* Update CHANGELOG.md
v0.2.0 		2024-07-24 23:02:03 -04:00
Alonso Guevara
ac6f240e29
Add autoresolve and update publish workflows (#698) 2024-07-24 19:54:11 -06:00
王俊
60520dc8c3
fix the llm organization parameter is ineffective during queries (#612) 
* fix the organization parameter is ineffective during queries

* add semver impact document

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
 2024-07-24 15:52:01 -06:00
Alonso Guevara
2a95e6771c
Update issue templates (#675) 
* Update issue templates

* Quick fix

* Quick fix

* Template fix

* Remove required
 2024-07-24 14:01:44 -06:00
Kapil Sachdeva
e8df283b24
fix - in run_local_search(), avoid re-reading create_final_nodes.parquet file (#592) 2024-07-24 15:26:37 -04:00
Julian Whiting
a1138216f0
Fix/few shot selection (#530) 
* try to always use at least 3 few shot examples

* add args for auto tune

* use context-based KNN to select most relevant chunks

* enforce at least 3 few shot examples for generated prompts

* utils for content-based KNN

* sem version

* fix callback arg

* fixes

* switch back to no op callbacks

* make n few shot, user controlled. default to 2"
 2024-07-24 13:24:00 -06:00
Josh Bradley
2ddee65c29
Read/write files as binary utf-8 (#639) 2024-07-24 13:28:22 -04:00