Fix reindex_embeddings: install unstructured[xlsx] extras (#66)
Deploy Beta / unit-tests (push) Successful in 10s
Unit Tests / test (push) Successful in 10s
Deploy Beta / docker (push) Successful in 28s
Deploy Beta / deploy-beta (push) Successful in 6m58s

## 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
This commit was merged in pull request #66.
This commit is contained in:
2026-08-02 11:57:10 -07:00
parent d8f5b8ebf2
commit bf3fffa343
4 changed files with 66 additions and 4 deletions
+3 -1
View File
@@ -31,7 +31,9 @@ dependencies = [
# Supported: langgraph>=1.2.5,<1.3 (matches langchain 1.3.x).
"langgraph>=1.2.5,<1.3.0",
"chromadb==1.3.5",
"unstructured==0.18.21",
# Fallback loader uses UnstructuredFileLoader; xlsx partition needs the
# [xlsx] extra (networkx, msoffcrypto-tool, xlrd, openpyxl, pandas).
"unstructured[xlsx]==0.18.21",
"pypdf==6.4.0",
"python-docx==1.2.0",
"docx2txt==0.8",