Upload 8 files
Browse files- .gitattributes +2 -0
- 50k_index_data/my_knowledge_dataset/data-00000-of-00001.arrow +3 -0
- 50k_index_data/my_knowledge_dataset/dataset_info.json +49 -0
- 50k_index_data/my_knowledge_dataset/state.json +13 -0
- 50k_index_data/my_knowledge_dataset_hnsw_index.faiss +3 -0
- 5k_index_data/my_knowledge_dataset/data-00000-of-00001.arrow +3 -0
- 5k_index_data/my_knowledge_dataset/dataset_info.json +49 -0
- 5k_index_data/my_knowledge_dataset/state.json +13 -0
- 5k_index_data/my_knowledge_dataset_hnsw_index.faiss +3 -0
.gitattributes
CHANGED
@@ -37,3 +37,5 @@ ragMedium.faiss filter=lfs diff=lfs merge=lfs -text
|
|
37 |
index.faiss filter=lfs diff=lfs merge=lfs -text
|
38 |
IndexedDataFiles/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
39 |
sample/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
37 |
index.faiss filter=lfs diff=lfs merge=lfs -text
|
38 |
IndexedDataFiles/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
39 |
sample/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
40 |
+
50k_index_data/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
41 |
+
5k_index_data/my_knowledge_dataset_hnsw_index.faiss filter=lfs diff=lfs merge=lfs -text
|
50k_index_data/my_knowledge_dataset/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451eef58e13aed68515392959ce162513cb60757626f69055db14fb258c7f301
|
3 |
+
size 112835792
|
50k_index_data/my_knowledge_dataset/dataset_info.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"builder_name": "csv",
|
3 |
+
"citation": "",
|
4 |
+
"config_name": "default",
|
5 |
+
"dataset_name": "csv",
|
6 |
+
"dataset_size": 10106427,
|
7 |
+
"description": "",
|
8 |
+
"download_checksums": {
|
9 |
+
"/content/drive/MyDrive/Colab Notebooks/MediumDataTransformation/50k.csv": {
|
10 |
+
"num_bytes": 9861557,
|
11 |
+
"checksum": null
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"download_size": 9861557,
|
15 |
+
"features": {
|
16 |
+
"text": {
|
17 |
+
"dtype": "string",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"title": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
},
|
24 |
+
"embeddings": {
|
25 |
+
"feature": {
|
26 |
+
"dtype": "float32",
|
27 |
+
"_type": "Value"
|
28 |
+
},
|
29 |
+
"_type": "Sequence"
|
30 |
+
}
|
31 |
+
},
|
32 |
+
"homepage": "",
|
33 |
+
"license": "",
|
34 |
+
"size_in_bytes": 19967984,
|
35 |
+
"splits": {
|
36 |
+
"train": {
|
37 |
+
"name": "train",
|
38 |
+
"num_bytes": 10106427,
|
39 |
+
"num_examples": 50001,
|
40 |
+
"dataset_name": "csv"
|
41 |
+
}
|
42 |
+
},
|
43 |
+
"version": {
|
44 |
+
"version_str": "0.0.0",
|
45 |
+
"major": 0,
|
46 |
+
"minor": 0,
|
47 |
+
"patch": 0
|
48 |
+
}
|
49 |
+
}
|
50k_index_data/my_knowledge_dataset/state.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "3cbfd22f2ffed322",
|
8 |
+
"_format_columns": null,
|
9 |
+
"_format_kwargs": {},
|
10 |
+
"_format_type": null,
|
11 |
+
"_output_all_columns": false,
|
12 |
+
"_split": "train"
|
13 |
+
}
|
50k_index_data/my_knowledge_dataset_hnsw_index.faiss
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45b28bb7c82eba9e990c61c7cb3e4003be5dd73ba271b2aa90d66843463bd5c8
|
3 |
+
size 138601154
|
5k_index_data/my_knowledge_dataset/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f759b620f936190319450fac3f434a012b6af37145bec0140a5c59b14958844
|
3 |
+
size 10025944
|
5k_index_data/my_knowledge_dataset/dataset_info.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"builder_name": "csv",
|
3 |
+
"citation": "",
|
4 |
+
"config_name": "default",
|
5 |
+
"dataset_name": "csv",
|
6 |
+
"dataset_size": 909376,
|
7 |
+
"description": "",
|
8 |
+
"download_checksums": {
|
9 |
+
"/content/drive/MyDrive/Colab Notebooks/MediumDataTransformation/5k.csv": {
|
10 |
+
"num_bytes": 884132,
|
11 |
+
"checksum": null
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"download_size": 884132,
|
15 |
+
"features": {
|
16 |
+
"text": {
|
17 |
+
"dtype": "string",
|
18 |
+
"_type": "Value"
|
19 |
+
},
|
20 |
+
"title": {
|
21 |
+
"dtype": "string",
|
22 |
+
"_type": "Value"
|
23 |
+
},
|
24 |
+
"embeddings": {
|
25 |
+
"feature": {
|
26 |
+
"dtype": "float32",
|
27 |
+
"_type": "Value"
|
28 |
+
},
|
29 |
+
"_type": "Sequence"
|
30 |
+
}
|
31 |
+
},
|
32 |
+
"homepage": "",
|
33 |
+
"license": "",
|
34 |
+
"size_in_bytes": 1793508,
|
35 |
+
"splits": {
|
36 |
+
"train": {
|
37 |
+
"name": "train",
|
38 |
+
"num_bytes": 909376,
|
39 |
+
"num_examples": 5001,
|
40 |
+
"dataset_name": "csv"
|
41 |
+
}
|
42 |
+
},
|
43 |
+
"version": {
|
44 |
+
"version_str": "0.0.0",
|
45 |
+
"major": 0,
|
46 |
+
"minor": 0,
|
47 |
+
"patch": 0
|
48 |
+
}
|
49 |
+
}
|
5k_index_data/my_knowledge_dataset/state.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "16c66e23fabe8b6e",
|
8 |
+
"_format_columns": null,
|
9 |
+
"_format_kwargs": {},
|
10 |
+
"_format_type": null,
|
11 |
+
"_output_all_columns": false,
|
12 |
+
"_split": "train"
|
13 |
+
}
|
5k_index_data/my_knowledge_dataset_hnsw_index.faiss
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff32ff680250a41feb75e49d895cba8ca902f165c4cecba0e108c6c361d9ad0
|
3 |
+
size 12344730
|