numb3r3 commited on
Commit
538bd1e
1 Parent(s): e3b88d6

chore: update example code

Browse files
Files changed (1) hide show
  1. README.md +38 -3
README.md CHANGED
@@ -38,7 +38,7 @@ As you can see, the `jina-reranker-v1-turbo-en` offers a balanced approach with
38
 
39
  # Usage
40
 
41
- The easiest way to starting using `jina-reranker-v1-turbo-en` is to use Jina AI's [Reranker API](https://jina.ai/reranker/).
42
 
43
  ```bash
44
  curl https://api.jina.ai/v1/rerank \
@@ -63,14 +63,47 @@ curl https://api.jina.ai/v1/rerank \
63
  }'
64
  ```
65
 
66
- Alternatively, you can use the `transformers` library to interact with the model programmatically.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
  ```python
69
  !pip install transformers
70
  from transformers import AutoModelForSequenceClassification
71
 
72
  model = AutoModelForSequenceClassification.from_pretrained(
73
- 'jinaai/jina-reranker-v1-turbo-en', num_labels=1, trust_remote_code=True
74
  )
75
 
76
  # Example query and documents
@@ -94,6 +127,8 @@ sentence_pairs = [[query, doc] for doc in documents]
94
  scores = model.compute_score(sentence_pairs)
95
  ```
96
 
 
 
97
  # Evaluation
98
 
99
  We evaluated Jina Reranker on 3 key benchmarks to ensure top-tier performance and search relevance.
 
38
 
39
  # Usage
40
 
41
+ 1. The easiest way to starting using `jina-reranker-v1-turbo-en` is to use Jina AI's [Reranker API](https://jina.ai/reranker/).
42
 
43
  ```bash
44
  curl https://api.jina.ai/v1/rerank \
 
63
  }'
64
  ```
65
 
66
+ 2. Alternatively, you can use the latest version of the `sentence-transformers>=0.27.0` library. You can install it via pip:
67
+
68
+ ```bash
69
+ pip install -U sentence-transformers
70
+ ```
71
+
72
+ Then, you can use the following code to interact with the model:
73
+
74
+ ```python
75
+ from sentence_transformers import CrossEncoder
76
+
77
+ # Load the model, here we use our base sized model
78
+ model = CrossEncoder("jina-reranker-v1-turbo-en", num_labels=1, automodel_args={'trust_remote_code': True})
79
+
80
+
81
+ # Example query and documents
82
+ query = "Organic skincare products for sensitive skin"
83
+ documents = [
84
+ "Eco-friendly kitchenware for modern homes",
85
+ "Biodegradable cleaning supplies for eco-conscious consumers",
86
+ "Organic cotton baby clothes for sensitive skin",
87
+ "Natural organic skincare range for sensitive skin",
88
+ "Tech gadgets for smart homes: 2024 edition",
89
+ "Sustainable gardening tools and compost solutions",
90
+ "Sensitive skin-friendly facial cleansers and toners",
91
+ "Organic food wraps and storage solutions",
92
+ "All-natural pet food for dogs with allergies",
93
+ "Yoga mats made from recycled materials"
94
+ ]
95
+
96
+ results = model.rank(query, documents, return_documents=True, top_k=3)
97
+ ```
98
+
99
+ 3. You can also use the `transformers` library to interact with the model programmatically.
100
 
101
  ```python
102
  !pip install transformers
103
  from transformers import AutoModelForSequenceClassification
104
 
105
  model = AutoModelForSequenceClassification.from_pretrained(
106
+ 'jina-reranker-v1-turbo-en', num_labels=1, trust_remote_code=True
107
  )
108
 
109
  # Example query and documents
 
127
  scores = model.compute_score(sentence_pairs)
128
  ```
129
 
130
+ That's it! You can now use the `jina-reranker-v1-turbo-en` model in your projects.
131
+
132
  # Evaluation
133
 
134
  We evaluated Jina Reranker on 3 key benchmarks to ensure top-tier performance and search relevance.