Fix reindex_embeddings crash: add networkx for Unstructured xlsx.

unstructured.partition.xlsx imports networkx; without it reindex dies
mid-run after clearing Chroma. Also skip per-document ingest failures
so one bad file cannot abort the whole rebuild.

llm_be/chat_backend/management/commands/reindex_embeddings.py

@@ -46,7 +46,18 @@ class Command(BaseCommand):
         self.stdout.write("Clearing Chroma collection…")
         rag.clear_vector_store()
         self.stdout.write("Re-ingesting documents…")
-        rag.ingest_documents()
+        try:
+            rag.ingest_documents()
+        except Exception as exc:
+            # Partial ingest may still have written some chunks; report and re-raise.
+            count = rag.vector_store._collection.count()
+            self.stderr.write(
+                self.style.ERROR(
+                    f"Reindex failed after clearing Chroma ({exc}). "
+                    f"Vector chunks currently: {count}. Fix the error and re-run."
+                )
+            )
+            raise
         count = rag.vector_store._collection.count()
         self.stdout.write(
             self.style.SUCCESS(f"Reindex complete. Vector chunks now: {count}")

llm_be/chat_backend/services/rag_services.py

@@ -161,6 +161,13 @@ class RAGService(BaseService):
                 )
                 if chunks:
                     self.vector_store.add_documents(chunks)
+            except Exception:
+                # Keep reindex/ingest moving; one bad file must not wipe progress.
+                logger.exception(
+                    "Failed to ingest document_id=%s file=%s",
+                    doc.id,
+                    doc.file.name,
+                )
             finally:
                 if os.path.exists(tmp_path):
                     os.unlink(tmp_path)