Update README.md
Browse files
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 `
|
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.
|
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()`.
|