Fix/entity extraction strategy (#1046)

* fix strategy config in entity_extraction * update init content --------- Co-authored-by: KylinMountain <[email protected]>
microsoft · Aug 28, 2024 · 4801817 · 4801817
1 parent ee734e6
commit 4801817
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 0 deletions.
diff --git a/.semversioner/next-release/patch-20240712071506108985.json b/.semversioner/next-release/patch-20240712071506108985.json
@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "fix strategy config in entity_extraction"
+}
diff --git a/graphrag/config/create_graphrag_config.py b/graphrag/config/create_graphrag_config.py
@@ -429,6 +429,7 @@ def hydrate_parallelization_params(
                 or defs.ENTITY_EXTRACTION_ENTITY_TYPES,
                 max_gleanings=max_gleanings,
                 prompt=reader.str("prompt", Fragment.prompt_file),
+                strategy=entity_extraction_config.get("strategy"),
                 encoding_model=reader.str(Fragment.encoding_model),
             )
 

diff --git a/graphrag/index/init_content.py b/graphrag/index/init_content.py
@@ -89,6 +89,8 @@
   # container_name: <azure_blob_storage_container_name>
 
 entity_extraction:
+  ## strategy: fully override the entity extraction strategy.
+  ##   type: one of graph_intelligence, graph_intelligence_json and nltk
   ## llm: override the global llm settings for this task
   ## parallelization: override the global parallelization settings for this task
   ## async_mode: override the global async_mode settings for this task