From 845e914f1bcc8d8cd1543146b319f31318d359a6 Mon Sep 17 00:00:00 2001
From: yangdx <yangdx@znipower.com>
Date: Sun, 23 Feb 2025 15:46:47 +0800
Subject: [PATCH] fix: make ids parameter optional and optimize input text
 cleaning

- Add default None value for ids parameter
- Move text cleaning into else branch
- Only clean text when auto-generating ids
- Preserve original text with custom ids
- Improve code readability
---
 lightrag/lightrag.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/lightrag/lightrag.py b/lightrag/lightrag.py
index 67ef3aab..efc49c2a 100644
--- a/lightrag/lightrag.py
+++ b/lightrag/lightrag.py
@@ -577,7 +577,7 @@ class LightRAG:
                 await self._insert_done()
 
     async def apipeline_enqueue_documents(
-        self, input: str | list[str], ids: list[str] | None
+        self, input: str | list[str], ids: list[str] | None = None
     ) -> None:
         """
         Pipeline for Processing Documents
@@ -591,9 +591,6 @@ class LightRAG:
         if isinstance(input, str):
             input = [input]
 
-        # Clean input text and remove duplicates
-        input = list(set(self.clean_text(doc) for doc in input))
-
         # 1. Validate ids if provided or generate MD5 hash IDs
         if ids is not None:
             # Check if the number of IDs matches the number of documents
@@ -607,6 +604,8 @@ class LightRAG:
             # Generate contents dict of IDs provided by user and documents
             contents = {id_: doc for id_, doc in zip(ids, input)}
         else:
+            # Clean input text and remove duplicates
+            input = list(set(self.clean_text(doc) for doc in input))
             # Generate contents dict of MD5 hash IDs and documents
             contents = {compute_mdhash_id(doc, prefix="doc-"): doc for doc in input}