code added

README.md

@@ -35,6 +35,64 @@ evaluation dataset: UKPLab/beir test data but we have used first 2lac passage on
 
 Note: * means we have evaluated on same eval dataset.
 
+### Usage (HuggingFace Transformers)
+
+```python
+
+passage_encoder = TFAutoModel.from_pretrained("nlpconnect/dpr-ctx_encoder_bert_uncased_L-12_H-128_A-2")
+query_encoder = TFAutoModel.from_pretrained("nlpconnect/dpr-question_encoder_bert_uncased_L-12_H-128_A-2")
+
+p_tokenizer = AutoTokenizer.from_pretrained("nlpconnect/dpr-ctx_encoder_bert_uncased_L-12_H-128_A-2")
+q_tokenizer = AutoTokenizer.from_pretrained("nlpconnect/dpr-question_encoder_bert_uncased_L-12_H-128_A-2")
+
+def get_title_text_combined(passage_dicts):
+    res = []
+    for p in passage_dicts:
+        res.append(tuple((p['title'], p['text'])))
+    return res
+    
+processed_passages = get_title_text_combined(passage_dicts)
+
+def extracted_passage_embeddings(processed_passages, model_config):
+    passage_inputs = tokenizer.batch_encode_plus(
+                    processed_passages,
+                    add_special_tokens=True,
+                    truncation=True,
+                    padding="max_length",
+                    max_length=model_config.passage_max_seq_len,
+                    return_token_type_ids=True
+                )
+    passage_embeddings = passage_encoder.predict([np.array(passage_inputs['input_ids']), 
+                                                np.array(passage_inputs['attention_mask']), 
+                                                np.array(passage_inputs['token_type_ids'])], 
+                                                batch_size=512, 
+                                                verbose=1)
+    return passage_embeddings
+    
+passage_embeddings = extracted_passage_embeddings(processed_passages, model_config)
+
+
+def extracted_query_embeddings(queries, model_config):
+    query_inputs = tokenizer.batch_encode_plus(
+                    queries,
+                    add_special_tokens=True,
+                    truncation=True,
+                    padding="max_length",
+                    max_length=model_config.query_max_seq_len,
+                    return_token_type_ids=True
+                )
+    query_embeddings = query_encoder.predict([np.array(query_inputs['input_ids']), 
+                                                np.array(query_inputs['attention_mask']), 
+                                                np.array(query_inputs['token_type_ids'])], 
+                                                batch_size=512, 
+                                                verbose=1)
+    return query_embeddings
+    
+
+query_embeddings = extracted_query_embeddings(queries, model_config)
+
+```
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: