updated Readme

README.md

@@ -109,17 +109,17 @@ embeddings = model.forward(input_ids).pooler_output
 print(embeddings)
 ```
 
-And with `haystack` (using `transformers-3.3.1`), we use it as a retriever (**note that we reference it from a local path**):
+And with `haystack`, we use it as a retriever:
 ```
-retriever = DensePassageRetriever(document_store=document_store,
-                                  query_embedding_model="./etalab-ia/dpr-question_encoder-fr_qa-camembert",
-                                  passage_embedding_model="./etalab-ia/dpr-ctx_encoder-fr_qa-camembert",
-                                  use_gpu=True,
-                                  embed_title=False,
-                                  batch_size=16,
-                                  use_fast_tokenizers=False
-                                  )
+retriever = DensePassageRetriever(
+    document_store=document_store,
+    query_embedding_model="etalab-ia/dpr-question_encoder-fr_qa-camembert",
+    passage_embedding_model="etalab-ia/dpr-ctx_encoder-fr_qa-camembert",
+    model_version=dpr_model_tag,
+    infer_tokenizer_classes=True,
+)
 ```
+
 ## Acknowledgments
 
 This work was performed using HPC resources from GENCI–IDRIS (Grant 2020-AD011011224).