Fix reindex_embeddings: install unstructured[xlsx] extras (#66)

## Summary

`reindex_embeddings` crashed with `ModuleNotFoundError: No module named 'networkx'` when Unstructured hit spreadsheet files via `partition/xlsx.py`. Reindex clears Chroma first, so a mid-run crash leaves an empty/partial vector store.

### True fix
Depend on **`unstructured[xlsx]==0.18.21`** (not bare `unstructured`). That extra pulls the required spreadsheet partition deps: `networkx`, `msoffcrypto-tool`, `xlrd` (plus openpyxl/pandas already present).

### Resilience
Also catch per-document ingest failures so one corrupt/unsupported file cannot abort a full rebuild after Chroma was cleared. Successful files still ingest; failures are logged.

## Test plan
- [x] CI / unit tests on this PR
- [ ] Merge + redeploy image to all hosts
- [ ] On each host: `docker compose -p chat_backend_prod exec web bash -lc 'cd /app/llm_be && SKIP_RAG_INIT=1 uv run python manage.py reindex_embeddings'`
- [ ] Confirm non-zero chunk count and no `networkx` / `msoffcrypto` / `xlrd` import errors

## Ops workaround (running containers only, until deploy)
```bash
uv pip install 'unstructured[xlsx]==0.18.21'
cd /app/llm_be && SKIP_RAG_INIT=1 uv run python manage.py reindex_embeddings
```Reviewed-on: #66

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)