diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..b59cd89f29f11782e3810a7c1c6fbe493776f86c 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+clip_engine_25k/image_index/faiss.index filter=lfs diff=lfs merge=lfs -text
diff --git a/clip_engine_25k/corpus/part-00001.parquet b/clip_engine_25k/corpus/part-00001.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..f7beb321aed8c9de5234ba1095d1bf7d92bd57da
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00001.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54f74183ced021c12ba08f3b692a03924e05dcb0094e1f89bf16e9165eba3a9
+size 16526
diff --git a/clip_engine_25k/corpus/part-00002.parquet b/clip_engine_25k/corpus/part-00002.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..78e6c69b065fdf33a7ff0fcdafecf14a1733fb6a
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00002.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934904eed090b6ed60e256c522be98445a662eefddf0f0867d4a0985b4bc913b
+size 16553
diff --git a/clip_engine_25k/corpus/part-00003.parquet b/clip_engine_25k/corpus/part-00003.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..c5a9ee6a23c4a424fd920626f1b9de75d0f32551
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00003.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0055683122942a8f20c9335483bb12967e21146434c6e5587d4192306ef22c
+size 16527
diff --git a/clip_engine_25k/corpus/part-00004.parquet b/clip_engine_25k/corpus/part-00004.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..ba488b2b1ed30b62fd10f2b8f1cf91c677ee22e3
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00004.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb7c0e3546bdf93659e739534a148294847010c28686826793026c1dc434e21
+size 16555
diff --git a/clip_engine_25k/corpus/part-00005.parquet b/clip_engine_25k/corpus/part-00005.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b71546e543519a7167df08304e8e8355e6a2004e
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00005.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8eb9e4a8d53b6426adbc7af67dbaa471d9e458a63883f61c60604b6a4e3c3a2
+size 16518
diff --git a/clip_engine_25k/corpus/part-00006.parquet b/clip_engine_25k/corpus/part-00006.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..271c15cd6e95dc622b1501af85db5798d6b38eb6
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00006.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ec410a933447f2898bc5f1218af659d612f652af35ef8066e6f2c8e5a7c220
+size 16536
diff --git a/clip_engine_25k/corpus/part-00007.parquet b/clip_engine_25k/corpus/part-00007.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b8878037bd36d635c76e8956ef2b10a8f4a76545
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00007.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efa51a305e69391ec66cc7c53976e322b7719ee02d3ba4739439a638e2291d4
+size 16546
diff --git a/clip_engine_25k/corpus/part-00008.parquet b/clip_engine_25k/corpus/part-00008.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..1d73dadee22774de33d97c53cb7729714e83e27e
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00008.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac8af9e8bb6bbfd88b4a083abaa9828934bedf4746ce518fda7d16f9ff95713
+size 16502
diff --git a/clip_engine_25k/corpus/part-00009.parquet b/clip_engine_25k/corpus/part-00009.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..e28dc27488162f76c92c63760b3707d4189979fd
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00009.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba25c3751f9ff20eb10e66faa228a6f73b4c9f0e626560077ccb89ea95bae0d
+size 16539
diff --git a/clip_engine_25k/corpus/part-00010.parquet b/clip_engine_25k/corpus/part-00010.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..9a542f325f8b7c4d937db52a360e4641abdf5d89
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00010.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0cd71327854870cca6733ef40cc7ac67c54c1db0a562867c890f397526a31ee
+size 16552
diff --git a/clip_engine_25k/corpus/part-00011.parquet b/clip_engine_25k/corpus/part-00011.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..880cee2862e79ea290eb882c95df4abc1dd7cc32
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00011.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2510ce359253823a3989e461df9bfb0414b52b7d22e05d435ee641254fb27f8c
+size 16520
diff --git a/clip_engine_25k/corpus/part-00012.parquet b/clip_engine_25k/corpus/part-00012.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..c9f022e4d04cc0ce5ebb13c69a0149d8ff9e9e74
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00012.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c47615c99d003600ae3e53243ba44c63f6dc956fd07b5a2a9f4b0ef77f2ecc2
+size 16529
diff --git a/clip_engine_25k/corpus/part-00013.parquet b/clip_engine_25k/corpus/part-00013.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..2676d495b9e10e5170348286a43d68874ddcb319
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00013.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29189a46c679d4da7eb8589bf40892fde3e055ce23cfe80a5bcd1158bc40f88
+size 16519
diff --git a/clip_engine_25k/corpus/part-00014.parquet b/clip_engine_25k/corpus/part-00014.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..4dce27ab09ac595947e639a790fa543e75755973
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00014.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0beb5a9c849f59557ead67f3154b7145f55ff7b4b6f739c95a8bcabb3668a8
+size 16534
diff --git a/clip_engine_25k/corpus/part-00015.parquet b/clip_engine_25k/corpus/part-00015.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b47fc60364e44d8527cca28ca65492bdd6ec2846
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00015.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb97363ecb00b52212d8b4b50be1db67f2ccef1b5368fe90b604c810cf4d6beb
+size 16536
diff --git a/clip_engine_25k/corpus/part-00016.parquet b/clip_engine_25k/corpus/part-00016.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..9a9d48769456b898d22d03d778834b5c903844ec
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00016.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae39d17ce818fe1189acc5550457b6c9acf0ff9afc98184ae2f1e482c0a7a09
+size 16513
diff --git a/clip_engine_25k/corpus/part-00017.parquet b/clip_engine_25k/corpus/part-00017.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..e65fc954a352e4e34eef9daa16b6b946e7fffbfd
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00017.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad9ff8d399e9dc8231ac3a8d1fc687fb933b439c2a6716012014ed0e3039363
+size 16551
diff --git a/clip_engine_25k/corpus/part-00018.parquet b/clip_engine_25k/corpus/part-00018.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..349e87f50bad7b341dcc022481665fce0dada5df
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00018.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8796ec07059c846570e1cc689471eca9541314c901af74f73ddadaf14e99e68b
+size 16527
diff --git a/clip_engine_25k/corpus/part-00019.parquet b/clip_engine_25k/corpus/part-00019.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..f18b4849824e8fd497133fc4d0a268da85d980eb
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00019.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64101c48abe96fff4d7481c2f4b6e72906fda845dd7304d186b6c36d0a68a4e8
+size 16550
diff --git a/clip_engine_25k/corpus/part-00020.parquet b/clip_engine_25k/corpus/part-00020.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..2d64b1b71418283b8a11d0115785dffa07e7177c
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b15f4ef664595610d9a475648c91cae39373766c98f80edaf382cd124bf050
+size 16541
diff --git a/clip_engine_25k/corpus/part-00021.parquet b/clip_engine_25k/corpus/part-00021.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..2d6b5a816d60fad1ce438cf35aa6b5384cf6c1d3
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00021.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78d9579c05ce72af56542a4816a22eb3472632cc75afefd99a79504447069a6
+size 16555
diff --git a/clip_engine_25k/corpus/part-00022.parquet b/clip_engine_25k/corpus/part-00022.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..7fe2d795a1e868ca0d0dd279bb70a89cb98d9e17
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00022.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cae15f607a929849d054e543e82d57de680348df92519b35562952a3d05df9a
+size 16525
diff --git a/clip_engine_25k/corpus/part-00023.parquet b/clip_engine_25k/corpus/part-00023.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..22bf506d0db93976db4f82a0d9eae5520f113f6e
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00023.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d533d1b785ba7fa8c7415a6b7050247520c42ffa9695e04efeeae62ccbbb8d
+size 16516
diff --git a/clip_engine_25k/corpus/part-00024.parquet b/clip_engine_25k/corpus/part-00024.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..0c1c33a58a71a945587890010fda9501f88fafb0
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00024.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b801942afe9e9e2ce81e3349a3b025f9b14542533a9093d9e8f27f0e969daf05
+size 16545
diff --git a/clip_engine_25k/corpus/part-00025.parquet b/clip_engine_25k/corpus/part-00025.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..9e2fc2a8ecfe1fc8464b15f40ba8781dd0ee1c9c
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00025.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36953c865d9325ffd4ef938f624d028cf118374da73f729bea364717aa7d46f5
+size 16520
diff --git a/clip_engine_25k/corpus/part-00026.parquet b/clip_engine_25k/corpus/part-00026.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..99161b038b212a2272d11d131abb161f5533fd9e
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00026.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7927aba1cda529e1124656fb368fcd6eec6a94f952daace34b1dbaec4fadc7da
+size 16521
diff --git a/clip_engine_25k/corpus/part-00027.parquet b/clip_engine_25k/corpus/part-00027.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..f85b474f3e5b0de6ab2de5a1c17815bbfe7029e5
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00027.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f959a61e18cde5d1fd765e4840ea55352a23554c5ad258bdc0171096a6ad1a3
+size 16547
diff --git a/clip_engine_25k/corpus/part-00028.parquet b/clip_engine_25k/corpus/part-00028.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b4cc77ff4e5647d54aeb8c1eba48cd6fb795ac39
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00028.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1420ea0931b15eff641a4e9005e815e1ac740d0674a00f7375a64125357706c
+size 16533
diff --git a/clip_engine_25k/corpus/part-00029.parquet b/clip_engine_25k/corpus/part-00029.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b78cf8c36a6457062518dc577a3a3b1e493496f9
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00029.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9344d720bd61c4b2606b0e54fedd79ce84224585591be3cc403ea70debd2d4ea
+size 16540
diff --git a/clip_engine_25k/corpus/part-00030.parquet b/clip_engine_25k/corpus/part-00030.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..02cc117665ed62d04a7aec796b8f17438e4f7d9f
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3e6f8492ec1dc3221854092030a3fb39ba376b72ae6ddff258227a94f1ffbf
+size 16545
diff --git a/clip_engine_25k/corpus/part-00031.parquet b/clip_engine_25k/corpus/part-00031.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..be60844bd1646d98a373e0357869b02a0f95f06a
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00031.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f081f94daa95873f8fa99c9f8da57cb3221cfa127c1e2e0ff6a72ffaf29970
+size 16536
diff --git a/clip_engine_25k/corpus/part-00032.parquet b/clip_engine_25k/corpus/part-00032.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..579af28d9f059b233acbb58b2f72b80bbb7edbbc
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00032.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ee199ae2c10691378460c20411ab29472fcfe352a078bc4e8c996619906bd8
+size 16544
diff --git a/clip_engine_25k/corpus/part-00033.parquet b/clip_engine_25k/corpus/part-00033.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..a11afdfd1784cd87dca48bc2174dcd598f47e084
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00033.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a92d93e9479e66a78caeefebd85dd5f19f502867a3f5b1cb9d2c92fafb123cc
+size 16532
diff --git a/clip_engine_25k/corpus/part-00034.parquet b/clip_engine_25k/corpus/part-00034.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..a57239bc6f73b98d44d8baada8b2b30cdb4ecaed
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00034.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e683203d5c574724a4e1a5b08ebe5d7b5cf67318e86675699203616f23154a8f
+size 16530
diff --git a/clip_engine_25k/corpus/part-00035.parquet b/clip_engine_25k/corpus/part-00035.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..aadc41ead596fdc3e2eed4f29136c2e976fcc102
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00035.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd8f1c5f172776aa7d5b6607f8ac105db3944dab85c336f39e8dfce3623bcd2
+size 16530
diff --git a/clip_engine_25k/corpus/part-00036.parquet b/clip_engine_25k/corpus/part-00036.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..4f88f158f433b69a4f922960ce4c2cae61199004
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00036.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abb37b27938a7eefc0b9eee1ef6c2372cc46b04757fadcfd292e968aad68a23
+size 16521
diff --git a/clip_engine_25k/corpus/part-00037.parquet b/clip_engine_25k/corpus/part-00037.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..96db9bbe7ee6288785eb2e5f194f5426e82ae4cd
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00037.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd41e63720b4b95aef8d2d9bf5975675d6f9f0ce2cdc8fcb1479f8c258d1c100
+size 16529
diff --git a/clip_engine_25k/corpus/part-00038.parquet b/clip_engine_25k/corpus/part-00038.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..a3f55105b4d85e3135f0d31279b0e6fa5af768fd
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00038.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c44c42500a1c865f565da9229979359e2629ab115187e1d01898b465f6ca123
+size 16510
diff --git a/clip_engine_25k/corpus/part-00039.parquet b/clip_engine_25k/corpus/part-00039.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..7977fdac95c849cf0bd8ae4d07f9dad7675b0698
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00039.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0e8dd2206b8b9e38f767ca580b310eb3afd9b660ba8a31b33d3d711550f58d
+size 16521
diff --git a/clip_engine_25k/corpus/part-00040.parquet b/clip_engine_25k/corpus/part-00040.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..d058ab96f7bdc24e93fceeb9a59587df90140f7a
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278570efa189f31556f0ccb9d20408880dbe5b2c72584d6574ca3c8f5c057b36
+size 16524
diff --git a/clip_engine_25k/corpus/part-00041.parquet b/clip_engine_25k/corpus/part-00041.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..dc454e2ebf7b550b1e38fd928ebd29611558e3ba
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00041.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4158b7a9fa5a0330eac87240fd8e7d5cb6677f0d8770346c020628660663f307
+size 16533
diff --git a/clip_engine_25k/corpus/part-00042.parquet b/clip_engine_25k/corpus/part-00042.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..b5684a30702d042d54dc7ae50f17a98c2c29fa76
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00042.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a405b37bc4f28ea9e7ebebd3d3461680e6b5fabd5e0f0ed344983912c8060d
+size 16548
diff --git a/clip_engine_25k/corpus/part-00043.parquet b/clip_engine_25k/corpus/part-00043.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..66b3b7d4210c0d7e1125247ae6225034304c691b
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00043.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f839c2f00bab9050762b11215de5d53f3f8373e2eb8456b72e1af9768013c331
+size 16545
diff --git a/clip_engine_25k/corpus/part-00044.parquet b/clip_engine_25k/corpus/part-00044.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..dd764e4ac9a5c220b486794dcb1f3b24bbdffa05
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00044.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e59d383ec9b0ad2d754d90deb9bdd65873886c4dc3f0cabb0cdf56429c692c3
+size 16508
diff --git a/clip_engine_25k/corpus/part-00045.parquet b/clip_engine_25k/corpus/part-00045.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..d0556c1736ea193684678690d9dc5971dc03ee1b
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00045.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ead86eacbaccf315d61da692268154f9334cce90fe5b43c820839fed0cf861
+size 16549
diff --git a/clip_engine_25k/corpus/part-00046.parquet b/clip_engine_25k/corpus/part-00046.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..320e4f7b1589dec718d9f7e16599a2ebf73e0692
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00046.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca772c22c0b3e1d14b8ab28be6cd587098bec16d8995e8ec57ef595f7375439
+size 16513
diff --git a/clip_engine_25k/corpus/part-00047.parquet b/clip_engine_25k/corpus/part-00047.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..8ebc5d28ff8c770e7b10055f7b677ebabaf30414
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00047.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941577b9f1146691afe2b9cfe660b5e83333248e36094ff8adcef4668a5bbc4a
+size 16514
diff --git a/clip_engine_25k/corpus/part-00048.parquet b/clip_engine_25k/corpus/part-00048.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..c6bb10a0fea0bc721e3543b9e57f467c0fead78f
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00048.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e284d1b32719e9c34cc16ec77a9c97dbf7b6380fa8ed5bedc2a61e0102fea9
+size 16546
diff --git a/clip_engine_25k/corpus/part-00049.parquet b/clip_engine_25k/corpus/part-00049.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..778711dffd20c985d3b66965d5100a7bced4ac74
--- /dev/null
+++ b/clip_engine_25k/corpus/part-00049.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b094c05d843a811f2f125d58934276f3dc2c0cb5762727f6804de2ff7ec1f5
+size 16405
diff --git a/clip_engine_25k/image_index/faiss.index b/clip_engine_25k/image_index/faiss.index
new file mode 100644
index 0000000000000000000000000000000000000000..c3d150ec771b1474c7558853a975b11f3902d772
--- /dev/null
+++ b/clip_engine_25k/image_index/faiss.index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7dfa80c82d79711698ae5df540da8228c6eef81c35184fbff6537908596686
+size 57993618