Sentence Similarity
English
txtai
davidmezzetti commited on
Commit
da25ec9
·
1 Parent(s): 2332f0b

Initial version

Browse files
Files changed (6) hide show
  1. .gitattributes +3 -0
  2. README.md +37 -0
  3. config.json +32 -0
  4. documents +3 -0
  5. embeddings +3 -0
  6. graph +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ documents filter=lfs diff=lfs merge=lfs -text
37
+ embeddings filter=lfs diff=lfs merge=lfs -text
38
+ graph filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ language: en
4
+ license:
5
+ - cc-by-sa-3.0
6
+ - gfdl
7
+ library_name: txtai
8
+ tags:
9
+ - sentence-similarity
10
+ datasets:
11
+ - NeuML/constellations
12
+ ---
13
+
14
+ # Astronomy txtai embeddings
15
+
16
+ This is a [txtai](https://github.com/neuml/txtai) embeddings index for a filtered set of articles about astronomy from [txtai-wikipedia](https://hf.co/neuml/txtai-wikipedia) combined with this [dataset of stars by constellation](https://hf.co/datasets/neuml/constellations).
17
+
18
+ txtai must be [installed](https://neuml.github.io/txtai/install/) to use this model.
19
+
20
+ ## Example
21
+
22
+ This index can be loaded from the Hugging Face Hub with txtai as shown below.
23
+
24
+ ```python
25
+ from txtai import Embeddings
26
+
27
+ # Load the index from the HF Hub
28
+ embeddings = Embeddings()
29
+ embeddings.load(provider="huggingface-hub", container="neuml/txtai-astronomy")
30
+
31
+ # Search for matching documents
32
+ embeddings.search("potential habitable planets")
33
+ ```
34
+
35
+ ## More information
36
+
37
+ Read more about this model and how it was built in [this article](https://neuml.hashnode.dev/parsing-the-s-with-txtai).
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "path": "intfloat/e5-base",
3
+ "instructions": {
4
+ "query": "query: ",
5
+ "data": "passage: "
6
+ },
7
+ "faiss": {
8
+ "quantize": true,
9
+ "sample": 0.05
10
+ },
11
+ "content": true,
12
+ "graph": {
13
+ "approximate": true,
14
+ "topics": {},
15
+ "copyattributes": true,
16
+ "backend": "networkx"
17
+ },
18
+ "autoid": 1,
19
+ "dimensions": 768,
20
+ "backend": "faiss",
21
+ "offset": 15763,
22
+ "build": {
23
+ "create": "2025-02-10T21:54:34Z",
24
+ "python": "3.9.21",
25
+ "settings": {
26
+ "components": "IVF20,SQ8"
27
+ },
28
+ "system": "Linux (x86_64)",
29
+ "txtai": "8.3.0"
30
+ },
31
+ "update": "2025-02-10T21:54:34Z"
32
+ }
documents ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43362916ce91f7b1e35f50fedeb725385798656d348d79c75cedca022d2e3d5
3
+ size 14585856
embeddings ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f126eff0fe6567fee9c6683fd1d3ed48cc7e0c1ae89bf96088aab4faecc4d8
3
+ size 12300016
graph ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959cbf0e6767cdc32b65c50c735fd2c956cb20d63b1f883b2294bf6c74dc3d59
3
+ size 8710629