Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- ru
|
| 5 |
+
library_name: transformers
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
Annoy vector db of Russian Synodal Translation (RST) of Bible
|
| 9 |
+
Embdding by [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
|
| 10 |
+
|
| 11 |
+
Ussage:
|
| 12 |
+
```
|
| 13 |
+
rst_ind = AnnoyIndex(1024, metric='angular')
|
| 14 |
+
rst_ind.load('rst.indx')
|
| 15 |
+
rst_df = pandas.read_csv('rst_db.csv')
|
| 16 |
+
|
| 17 |
+
embd = GetE5Emb("Как жить правильно и не совершить греха?") # see the origin e5-large usage
|
| 18 |
+
|
| 19 |
+
indices = rst_ind.get_nns_by_vector(emb, 3)
|
| 20 |
+
ind = random.choice(indices)
|
| 21 |
+
str_ = rst_df.loc[ind].Text
|
| 22 |
+
print(f"{str_} [{rst_df.loc[ind]['Book']}{rst_df.loc[ind]['Chapter']}:{rst_df.loc[ind]['Verse']}]")
|
| 23 |
+
|
| 24 |
+
```
|