diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..98932c367103cd3cc32a9b75e68fc542d957251d
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3dfa1bc5e28de8b3b4acb86140a1186cec90179d793e33a8ff30471dfd730a6
+size 1651675346
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..9bce4298cc2fd8249b38e22afe33eceb6156a63f
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fc554b6a141a07ada419e8e1feb0b4939716b044a6b04a55f0a3e10e19d6a1
+size 82476534
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..3abc65f700e012ac9493caa1fee2c0267aa7d51c
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7453323d0a6e97578c3effc219e88926ef587a2045bf34894ffbc998800d7b31
+size 82850007
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..75d187637130264604deefef8790bfaad008520f
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806b290950d53d43a7c70cb105bdfc699f5a31bd4e1832e8fec132fafe6409c3
+size 82427693
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..8985e3f0992deee9375cf07eae5c3e47e3631ce1
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42df190de7ff3aa171510b000251e9da173ea8f83ce0b055cbe9b02477a7e9f7
+size 82871768
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..8336cf1536bb1a7e96e94aa658ede3f3afd2d2a1
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f5cbbe2eb475a4cf68868515b0d67b05b1861ef1e46df735547a2aa4fd4dc1
+size 82841442
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..fc5c198fcc304ff893ac7b1c32f6c65ab7bb6bd5
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d37ae4354405c8539b792e1e09ca0734c4dd8346a98517c55739266364c1b41
+size 82882734
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..f84519421ea9489fa57e5badda84a78c821abdaa
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a5d1bbe40aeb3cf6a13f03334666f2e758bff05dd0217f9629a28341b2400b
+size 82946821
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..2a7b8a23ffb5b80168b8124172b503405386367b
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d50e39a95764afa722b954fff1601424ee9861d033cff936fd6432c29f4e98
+size 83748937
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..b9089964f6716fdc2cb31b7755772c8e00569b15
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b591668b25330b820c82ce8fca73667576aa9cc32d8e4a1652744966b1bc84
+size 83791153
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..3e91415cb246889bbbd1e00ade9c0306f96196f5
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730375f91486649d909865019af7026ec72cd1c350b7f84e863e45711f153895
+size 83858681
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..d2453523e937f72e1c3e1054beb223275caa42f0
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c135ef7e695625d3c7abd5faa169a205cbdd10c4a88d1bc928b0d101d9b8ea81
+size 83888055
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..937c887aab4f8e7abe6690cdebff59305da15461
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e79de7fa49c7f6fe30f7816acf7190cb594d4cf4093b2fd634ceab3cb5122ab
+size 75283684
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..5c9b989d086a227be968291922fbf3715e830a1a
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8628d8818589268d2c59d0a4f9b8d008e6f4ed28a14acc1c8f8c52fe152d79
+size 82718557
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..454a1b8d22c61bfcadc2730182906a828611d38b
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422804b05ae0302aa1f534b3d644d00cfc902a586d987815ec056ac0ac2536bf
+size 82633582
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..30c481f302beebf4e5517371a4df6e23051621f9
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cabf2b16a232f0c7264f4322974e2f6f60c04199d7f66b2a0038f226f5c1c3e
+size 82792053
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..142857f1c7ed96ee2456aafc4d1d6fd55d6509e9
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde03647abe3fcadbd3ad6e6ea1bd69d7a3256a06f4ffbe82f7d7fc4a642e83c
+size 82807044
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..89da12e6ca3fee67d4d75936306a0fba135a4315
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10009afb817052c58254aab894a3cc7e06facc53fb710dd773b9774f4388222c
+size 82691838
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..c063690ef26921062f09a71ad17aa1d1a93816b3
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2d6731d6cc2da841b37a30c2015138158471fb9a1831d6ce4c0913fc2e4048
+size 82698924
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..4eaefdeaf69e1e3bd87b68f235d23bc22fa22e99
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a17f24436a827b08b4ac07dbb2c3e0d2d2417b094c97036c994dbb17c36b045
+size 82759710
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..64746fb9f7880574455799cae974028aab3f396d
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4dfa487314b7dde14174ae3d85e1422539037454a01d228802417692c26161
+size 82712296
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..30b40868c869a30f497b8668729f70454869c817
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4395fdecd0aee642f1d0946eb4f6a594e83c20e3b17de223f783969181a7640b
+size 1652134961
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..47cf11a71779c50ee3a7a0a90731ef0175db5359
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f7280de6a4e4322cbee29fd1b01fae2f8b0e2fb36c2cf5734b315f647b6a53
+size 82493596
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..5c940285f8c8d1736a7a8bf9d31cdf6eb907a00a
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a6ff4d345abe515a5ae8b3574243aafb9b70428dc0d87e24d0e34fdea25440
+size 82872330
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..483480a3d759ce72094913e00b67787467e3c569
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972c8791baa58b8c408f0d5ac771e23d67546c81f1cac4bf1b57e5e48654ea76
+size 82450713
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..3fc332989750bdceb2fdb9156419d83a91d1caf3
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4ba2e4a313142b2c304a1970c4ae4b22496124cf171e52f02481be5e370a72
+size 82896167
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..16f54b77ee3ba3545eb1052b2552bb40b1109837
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b4fbab1b82f7898a6ca607312207e1d0415bb0ea2be51451528c35ab9143d3
+size 82873781
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..207c06af7c6a41f416d8f565fa1251862a33e5f8
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc6be4abb4e2dc9201998b75383cce4e28c471725ae6fc87073f6beefd5208f
+size 82901516
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..a72398e8efc539c374d8509edb34ec3b4c672f9b
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47166b23ec6ec9d6417acb709de3be5bc2b0f38fa8d70bbddd934844b0de4864
+size 82971662
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..03a66e8b9a11958b2de2b9c564ead260e4e7978f
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91063e9270c5899352a4bbfd1bae50932811edd72345ac62a496fe0ccd37eaf1
+size 83769366
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..9f3e25920c78143faa6d74263cd9dbe808e03e92
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acc3d48bfb6f4a7aafe66ab60ccc50c704aab7b7a338b24750248eb4d0cecc4
+size 83811402
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..134a9da7cd74e7514d606d51fc4d5b81ca3f5ff3
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9a818a6258299c0eea080059d677315e5820402773ffc1eda0cb7b2b00a8f6
+size 83890545
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..657abdeac48572b7b02de6c6b677e450830d35a2
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62642878346bca63670707cc072e97ac23a4633bf7a7c503935a117ad4f74a7
+size 83906505
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..51638187be2eedc24d2fab5bf6b4beb855dc9b69
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b8887583b849b27ed928ac413322eb7673e0d5154eccd0accc2ffdf17d15b0
+size 75306346
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..cd0f50b53d98ac09d528f90549a01f06c10f4fb2
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6180149e076e454f48c1d9f885671fcf6c790254e0fcf2b746324bf9f4adbf46
+size 82738807
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..93744ba483bf7d79e0e7affdcb4be92f3fd87839
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b2039a8ee9188dbb890b48f3e630f697571dbc68207accad8d62323c3d0de4
+size 82653093
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..31791f25d2a56104d9a8455cea438b0e7eab5f5d
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d7e4f7e355c0c99ba7e2b0788b867e49cb3da79fc634d24fe4bf016588faec
+size 82815949
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..6f761b0ca3e504aae0d8c615072f588c2d128a2d
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5802dec3f1d9d4af3949d16ae65c22c3f83641d273f8d4ab413ca2ae2d984af5
+size 82830772
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..dcefd921bd8cc3071f925cdb7b85e21b24de6bd3
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63cfff8410ad1d9ca3ab8f197305ba0f7205150eb5affa4cd5ac1b502d694578
+size 82712748
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..dca9b407de372f85f4fdcfc3f302bc7cd29b156c
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686eb258f645b7deef8c70609f2739e87fe687fdd00966268912ab144b9aa598
+size 82723329
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..0486b3a04e616ad44a58adcd1a474785f48ce705
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386b66beaa4425669cc36b2451c508b9a575cfcd1fdc7fbdc7fe0bbb17ad14b0
+size 82785659
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..149c3d36e3a2cb40e8e3d38431cb86f80d944e21
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e5d04c9da584742853c5a15a15230280b9799f0abbcfef31b2ceeac9b2188c
+size 82736674
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..31f193f72099ed01142a87bca1aa839555f0fc3a
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8dadf82141cb90d41bb8a579117019641a844b85190260b4f44aba0d5ec597b
+size 1652083529
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..25c242c385b16b849d977e59391d603aa3842696
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ef3ba6acd4e85cf671444164cd30957edfbbcb2d9a5ffd491582cfe06eaae6
+size 82508355
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..13d9b8a96d324eea649fe586f82d2fb44f3db9ef
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9754c9cc027e9cd3baf69c507339327793681dd739eff4eb9af6a66cedc12758
+size 82843512
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..5598845a1598683b266f1afc7342ae91b0b5cc5e
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e008d8ebd53d81ec6877f1f8af8b1798c5c7aa562be7b73acfef5dfd972c0587
+size 82496745
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..6895ba90cd179f07b6b186526d08aafca6d55fec
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208206e1468522f6947a15bc64cc3e8c135aae2ff46bd496489e0fdb8a3cc94d
+size 82883921
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..b2d7f7623e5c8fbb00fb4006fa63e43d532a6d68
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c20c2f046fd515b8ce8dd30e3f2a10af02e9096f2c1c2ebdecd0e3115eb2ef2
+size 82875352
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..09dc85ad5523ea4742d80e58d2f97a0d2f02ed87
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c9edc9b30240d7cf95ce58339e4396ceefa4e983a7106ae818a06ea1b69c5b
+size 82877843
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..471a3e8e4d6e3a7019dadf66af0ba2466f57cb23
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d103aad8fddfd49748576a69649d13651c02c731323da9d81c00e66b7960c6ca
+size 82991537
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..d08896e74f4cc113a4b0e1dc235cf4cc5b0a6045
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6725f860d5ec84c2e42bb8ad26bdc570e56f2731d7a0cacfc00b222733a17cd5
+size 83771939
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..1400130c3fd0d30cf0622990e74f1b90c0edaa53
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e30c06f0ada3e2ab52f814477f8b5cda37b8e3d9afeea38bac37fc5dfff613
+size 83799461
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..35cd10db7d6be700a8d5d3589e1a31746b92aefa
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448db535d5917990ee50ba7b83c5be41367af6f4a59c8b06184d79c35d692f8f
+size 83838861
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..d1e510dc1ef97de21004688ff421cf5e3a310161
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433c14dbcd7e33422b6df2cf68e0200a4b4d028342eb11db848e968dc4afaacf
+size 83919206
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..0e75c6727f67749b01445b698359575925f7b18a
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a8fbf3704f79c7a0da2f0f11e9ef3f7000fa7a8fa86fe0ac3c6b4961070b4e
+size 75316167
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..2deeab102a1f7b930a96e933c349394925053f73
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac49920b10c37e460e520b96232f380f4159debd31a286a8406ad8fc6e8cdd94
+size 82711085
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..b9b195fad55e9876143dfaf4c2ad4e1e2b38552f
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c37626bb106a315efa0a364439e688bfd9c827d21ae40da3330b4cca6d86cd
+size 82714476
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..636b09d7312c339c9c082ea7714e3f9ad573f76b
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8f3837ceb01e86667430e7a99a4066ca4593161378d8145112e6d6c76147e7
+size 82811380
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..f14739077b28efa5b3e45bd16ad90efa11e827c4
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6b3c16618d764501db431c78c7714c3cb0e404d9e52d35f8cf364712b9e9d0
+size 82826829
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..c96810865d7b9a987ab10bc5346651845cb3a3eb
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d5b4cbef6709bf4824126c8966380096817aa261b0152de6c67da00713e798
+size 82662366
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..e5b607e29555e1b9c60c6328487b373ef34af00c
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12d5a64903613563483899c23ef30b1ab1ff04238558bdf6282da03ce2b103c
+size 82730596
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..b5be88cd54a7d9a83b47e1e097cc59146b7d6984
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3784164b6d23f5336f83e5bb0cf56d0de60659784bb02f88137eb336eb35c12c
+size 82780872
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..0343bba51edec11517bdbc22f393241b13e5f053
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b604f8fae474a6c17799585e04fa1a84fbeb800b6ba131592c68af71898b2e
+size 82729802
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..fa3ae124b26aa80c0caa2b8cea0a314ea98dcc9e
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db02cbd9345e538f273c5805c9a782e9a487124e77296f5206b0eb0a285f108
+size 1665249928
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..76ac5914f0edecd09d2f89365d8270dca93ca649
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc27c3042920a6d630bf00416abe5be1a7200f5afafe448624f04c3038bebfc
+size 83179761
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..d4e4ae3477d243a18c33479bd2ed55e5d2e587b0
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6c627a556f1dc9d787fa7cc08d2102fd21fec202a45dd434c198945395f351
+size 83511034
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..cb1542ca47f53731207c76ecf01d0d61807eb38b
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b286c9918d6493f28119a004c3a5a6a36635f20026c68d78148cc29acca5db
+size 83137070
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..7a484f539d019e1a3916753c1094873a642bef6a
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae371abbf01c05cca3a99f6531192a76fa6573ea1204ceeaadd1d69d5175c2de
+size 83526748
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..8bcea806080d9e2ebf7d9d3af34993544bd6e745
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3c4a9abd09ad606b55fa8a13b7c98018fca6279d4daf575a3e2078d1ebb58e
+size 83537414
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..786fd0c5f50884bfae5e12955ca78b719af87ebe
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be44812862664c8a2a43cfa4cdf7bcb803761e73a63dda3b10cc1dac92c879cb
+size 83549854
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..2dc0f141cebbbe17e3bf9671c676cce816437c67
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01e1f7793d487984aeaa3d9e7f1a55448c6cc43a4b72d05aaf70280a2c84e27
+size 83612289
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..96ed7d3f033ac8ae25fdedbac0ae8e397ded9682
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d9f170638a3ae7f293b3e181dc30aa83879041c76af9c8de3657742b11625c
+size 84439202
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..384ee18b6cd0a230b42132434d6e0caa26204efe
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d966679253456302e3bef3f196ec92db5d0d49af906106f90aa8c96ce9c9c62a
+size 84472789
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..a045ba31b036da93e0d1670a9bb49525fe3492b1
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4892e92aac2a137b0ef221da63120f9d38ed2fd3e8bd8fe30d761accb6ead1
+size 84515109
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..f97f0474c91bce366cee9e70b532cf858ea643c1
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448d1dde9f43f2a45258a37343e598be9250c90510698dce259d12c14f6e2812
+size 84572262
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..0161513295faac1b9f4566cb05df9f651bf01266
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3653b68d62be93e843e2be5aabc25ac250f5fc62023bdea2f68ad6deb07638ce
+size 75911681
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..68d41929cf05fdda86b376c71d4ff9ec479a8004
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4931b56b21127872af006c8fea28eed9570c660df52c9702281e18198e8db5
+size 83380309
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..662194d6de40000fc2cd2a5a6cc58ca9a5aa2f50
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80eff60c58ff10b1d9c86a259e4db23390ed9fc2f95f8dc0775e576dc75b5ac
+size 83377276
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..1d789e3651589490d285ff39485b2759f1e8ba99
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e606e3250c90c441f7e8ec35aef96480c77ef89e3870ff5ed5aea182d99be03
+size 83458964
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..d0204a3e898f9c674b04a2fef086bfb431abf798
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25de0fb1e31ea5e0f2fa5c43343d93d0788dba2026d7d35a672362ca82602c60
+size 83469730
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..7325878046d0c1fa370e567b39999c9cb43a3625
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647fa2c2998d8838453f77a6ff0530d87ebab070d2d07fa2d577f84e8ea585b4
+size 83365506
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..ab0641b6d83ba576da2c8f5936489aa752d587b3
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21af06ba1dd6efbf1fff37e9fe3012521afd865d8e2df494957a6a9ae65b955f
+size 83383790
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..29cb702967a945aec0ce6e208d81aa6494113db2
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fb8aa71da54a9012e0f707011f42cf488f5e7f8c06369583a20559fe86ffde
+size 83441782
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
new file mode 100644
index 0000000000000000000000000000000000000000..0010d399cc29e98137b4e78c266512dbd22099ca
--- /dev/null
+++ b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b53836f8a8065ad255ec5a5d5190f747d3b16ff0b3c3a04abd9afe6f1a2c72
+size 83413816
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/reduced_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/reduced_vectors_column.json.zip
deleted file mode 100644
index 7f22b405b2fa3e3eccdf1f295dda7894abb1010d..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/reduced_vectors_column.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1294dba67538e1eb1b90504b60dbdba41cf56870cbbf5f08b128b2f1b6022a3
-size 1657109288
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/weighted_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/weighted_vectors_column.json.zip
deleted file mode 100644
index 462f05b099e0f872f68e98ae6448b7c08de7ceee..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores_2/weighted_vectors_column.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8c64aa820e3b2ea33682eb37291352d9ecca1f47dd0ea93ae80e5195b48586b6
-size 1670639475