From 55e19a05e499b1c69fa137765cb99350027d06c3 Mon Sep 17 00:00:00 2001
From: julius-heitkoetter
 <97237339+julius-heitkoetter@users.noreply.github.com>
Date: Fri, 13 Oct 2023 09:16:42 -0400
Subject: [PATCH 1/2] have id's for chunks also include a hash for timestamp

---
 A2rchi/utils/data_manager.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/A2rchi/utils/data_manager.py b/A2rchi/utils/data_manager.py
index 5173684..3328647 100644
--- a/A2rchi/utils/data_manager.py
+++ b/A2rchi/utils/data_manager.py
@@ -215,13 +215,16 @@ def _add_to_vectorstore(self, collection, files_to_add, sources={}):
                 metadata["filename"] = filename
             
             # create unique id for each chunk
-            # the first 12 bits of the id being the filename and the other 6 based on the chunk itself
+            # the first 12 bits of the id being the filename, 6 more based on the chunk itself, and the last 6 hashing the time
             ids = []
             for chunk in chunks:
                 identifier = hashlib.md5()
                 identifier.update(chunk.encode('utf-8'))
                 chunk_hash = str(int(identifier.hexdigest(),16))[0:6]
-                ids.append(str(filehash) + str(chunk_hash))
+                time_identifier = hashlib.md5()
+                time_identifier.update(str(time.time()).encode('utf-8'))
+                time_hash = str(int(identifier.hexdigest(),16))[0:6]
+                ids.append(str(filehash) + str(chunk_hash) + str(time_hash))
 
             print("Ids: ",ids)
             collection.add(embeddings=embeddings, ids=ids, documents=chunks, metadatas=metadatas)

From 01b14cc3c73fe41b7bf453eb79e97483c236cbb6 Mon Sep 17 00:00:00 2001
From: julius-heitkoetter
 <97237339+julius-heitkoetter@users.noreply.github.com>
Date: Fri, 13 Oct 2023 09:17:53 -0400
Subject: [PATCH 2/2] Adding time import

---
 A2rchi/utils/data_manager.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/A2rchi/utils/data_manager.py b/A2rchi/utils/data_manager.py
index 3328647..4245f20 100644
--- a/A2rchi/utils/data_manager.py
+++ b/A2rchi/utils/data_manager.py
@@ -11,6 +11,7 @@
 import hashlib
 import os
 import yaml
+import time
 
 
 class DataManager():