kanshan/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-01-14 00:57:23 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Fix/drift search reduce (#1948)
Some checks are pending
gh-pages / build (push) Waiting to run
Details
Python CI / python-ci (ubuntu-latest, 3.10) (push) Waiting to run
Details
Python CI / python-ci (ubuntu-latest, 3.11) (push) Waiting to run
Details
Python CI / python-ci (windows-latest, 3.10) (push) Waiting to run
Details
Python CI / python-ci (windows-latest, 3.11) (push) Waiting to run
Details
Python Integration Tests / python-ci (ubuntu-latest, 3.10) (push) Waiting to run
Details
Python Integration Tests / python-ci (windows-latest, 3.10) (push) Waiting to run
Details
Python Notebook Tests / python-ci (ubuntu-latest, 3.10) (push) Waiting to run
Details
Python Notebook Tests / python-ci (windows-latest, 3.10) (push) Waiting to run
Details
Python Publish (pypi) / Upload release to PyPI (push) Waiting to run
Details
Python Smoke Tests / python-ci (ubuntu-latest, 3.10) (push) Waiting to run
Details
Python Smoke Tests / python-ci (windows-latest, 3.10) (push) Waiting to run
Details
Spellcheck / spellcheck (push) Waiting to run
Details

Browse Source 
* Fix Reduce Response for non streaming calls

* Semver
This commit is contained in:
Alonso Guevara 2025-05-23 08:07:09 -06:00 committed by GitHub
parent 7fba9522d4
commit f1e2041f07
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.semversioner/next-release/patch-20250522234310308717.json Normal file
View File

@ -0,0 +1,4 @@
{
"type": "patch",
"description": "Fix Drift Reduce Response for non streaming calls"
}

2
graphrag/query/structured_search/drift_search/search.py
View File

@ -386,7 +386,7 @@ class DRIFTSearch(BaseSearch[DRIFTSearchContextBuilder]):
model_response = await self.model.achat(
prompt=query,
history=search_messages,
model_parameters=llm_kwargs,
model_parameters=llm_kwargs.get("model_params", {}),
)
reduced_response = model_response.output.content