up

.github/workflows/r2r-full-py-integration-tests-graphrag.yml

@@ -53,4 +53,4 @@ jobs:
 
       - name: Run SDK GraphRAG Tests
         if: matrix.test_category == 'sdk-graphrag'
-        uses: ./.github/actions/run-sdk-graphrag-tests
+        uses: ./.github/actions/run-sdk-graphrag-tests

.github/workflows/r2r-light-py-integration-tests-graphrag.yml

@@ -56,4 +56,4 @@ jobs:
 
       - name: Run SDK GraphRAG Tests
         if: matrix.test_category == 'sdk-graphrag'
-        uses: ./.github/actions/run-sdk-graphrag-tests
+        uses: ./.github/actions/run-sdk-graphrag-tests

.github/workflows/run-r2r-full-py-integration-tests-graphrag-deduplication.yml

@@ -53,4 +53,4 @@ jobs:
 
       - name: Run SDK GraphRAG Tests
         if: matrix.test_category == 'sdk-graphrag'
-        uses: ./.github/actions/run-sdk-graphrag-deduplication-tests
+        uses: ./.github/actions/run-sdk-graphrag-deduplication-tests

docs/cookbooks/advanced-graphrag.mdx

@@ -175,4 +175,3 @@ You can check the status of the deduplication task using the hatchet dashboard o
 
 - Entities: [Entities](http://localhost:7272/v2/entities?collection_id=122fdf6a-e116-546b-a8f6-e4cb2e2c0a09&entity_level=collection)
 - Triples: [Triples](http://localhost:7272/v2/triples?collection_id=122fdf6a-e116-546b-a8f6-e4cb2e2c0a09&entity_level=collection)
-

docs/cookbooks/contextual-enrichment.mdx

@@ -1,2 +1 @@
 # Contextual Chunk Enrichment
-

docs/cookbooks/graphrag.mdx

@@ -426,4 +426,4 @@ Feel free to reach out to us at [email protected] if you have any questions or
 
 # Advanced GraphRAG Techniques
 
-If you want to learn more about the advanced techniques that we use in GraphRAG, please refer to the [Advanced GraphRAG Techniques](./advanced-graphrag.mdx) page.
+If you want to learn more about the advanced techniques that we use in GraphRAG, please refer to the [Advanced GraphRAG Techniques](./advanced-graphrag.mdx) page.

py/core/main/orchestration/hatchet/ingestion_workflow.py

@@ -162,11 +162,6 @@ async def parse(self, context: Context) -> dict:
                     document_id=document_info.id, collection_id=collection_id
                 )
 
-                await self.ingestion_service.update_document_status(
-                    document_info,
-                    status=IngestionStatus.SUCCESS,
-                )
-
                 chunk_enrichment_settings = getattr(
                     service.providers.ingestion.config,
                     "chunk_enrichment_settings",
@@ -179,6 +174,16 @@ async def parse(self, context: Context) -> dict:
 
                     logger.info("Enriching document with contextual chunks")
 
+                    # TODO: the status updating doesn't work because document_info doesn't contain information about collection IDs
+                    # we don't update the document_info when we assign document_to_collection_relational and document_to_collection_vector
+                    # hack: get document_info again from DB
+                    document_info = (
+                        await self.ingestion_service.providers.database.get_documents_overview(
+                            filter_user_ids=[document_info.user_id],
+                            filter_document_ids=[document_info.id],
+                        )
+                    )["results"][0]
+
                     await self.ingestion_service.update_document_status(
                         document_info,
                         status=IngestionStatus.ENRICHING,