From 561bf4f71f81242d50a5100bbe861a8eb296f384 Mon Sep 17 00:00:00 2001
From: Ryan <ryanjchen2@gmail.com>
Date: Wed, 19 Nov 2025 20:53:24 -0500
Subject: [PATCH] yeet

---
 README.md | 3 +++
 main.py   | 8 +++-----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index e69de29..621fc2b 100644
--- a/README.md
+++ b/README.md
@@ -0,0 +1,3 @@
+# simbarag-index
+
+This is going to be the LLM portion of SimbaRag, refactored out into this service as not to block the startup time of the main app.
diff --git a/main.py b/main.py
index 101d36a..e9debec 100644
--- a/main.py
+++ b/main.py
@@ -89,14 +89,12 @@ async def reindex_all_paperless_documents():
     if all_docs["ids"]:
         simba_docs.delete(ids=all_docs["ids"])
 
-    visited_documents = set(
-        await PaperlessDocument.all().values_list("paperless_id", flat=True)
-    )
-
+    # Fetch all documents again
     ppngx = PaperlessNGXService()
     docs = ppngx.get_data()
-    docs = [doc for doc in docs if doc["id"] not in visited_documents]
     doctype_lookup = ppngx.get_doctypes()
+
+    # Chunk them
     await chunk_data(docs, collection=simba_docs, doctypes=doctype_lookup)
 
     return ""