Sentence Similarity
Safetensors
Japanese
RAGatouille
bert
ColBERT
bclavie commited on
Commit
4252d70
1 Parent(s): a6c64fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -101,14 +101,14 @@ Notably, RAGatouille has metadata support, so check the examples out if it's som
101
 
102
  ## Encoding and querying documents without an index
103
 
104
- If you want to use JaColBERTv2 without building an index, it's very simple, you just need to load the model, `encode()` some documents, and then `search_encoded_documents()`:
105
 
106
  ```python
107
  from ragatouille import RAGPretrainedModel
108
  RAG = RAGPretrainedModel.from_pretrained("bclavie/JaColBERTv2")
109
 
110
  RAG.encode(['document_1', 'document_2', ...])
111
- RAG.search_encoded_documents(query="your search query")
112
  ```
113
 
114
  Subsequent calls to `encode()` will add to the existing in-memory collection. If you want to empty it, simply run `RAG.clear_encoded_docs()`.
 
101
 
102
  ## Encoding and querying documents without an index
103
 
104
+ If you want to use JaColBERTv2 without building an index, it's very simple, you just need to load the model, `encode()` some documents, and then `search_encoded_docs()`:
105
 
106
  ```python
107
  from ragatouille import RAGPretrainedModel
108
  RAG = RAGPretrainedModel.from_pretrained("bclavie/JaColBERTv2")
109
 
110
  RAG.encode(['document_1', 'document_2', ...])
111
+ RAG.search_encoded_docs(query="your search query")
112
  ```
113
 
114
  Subsequent calls to `encode()` will add to the existing in-memory collection. If you want to empty it, simply run `RAG.clear_encoded_docs()`.