baai/bge-reranker-v2-m3
baai/bge-reranker-v2-m3
baai/bge-reranker-v2-m3 is a lightweight multilingual re-ranking model. Built on the bge-m3 model, it offers robust multilingual capabilities, ease of deployment, and fast inference speeds. This model takes a query and a document as input and directly outputs a similarity score, rather than an embedding vector. It is well-suited for multilingual scenarios and excels particularly in processing Chinese and English.
Price
| Input | $0.01/百万 tokens |
| Output | $0.01/百万 tokens |
Use the following code example to integrate our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.jiekou.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="baai/bge-reranker-v2-m3",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=8000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Information
Provider
Quantification
-
Supported features
Context length
8000
Maximum output
8000
Input Capabilities
text
Output Capabilities
text