fastembed_text_embedding_model_initialization_and_document_embedding.py

1from fastembed import TextEmbedding
2from typing import List
3
4# Example list of documents
5documents: List[str] = [
6    "passage: Hello, how are you?",
7    "passage: I am fine, thank you.",
8    "query: How are you?",
9    "query: Greetings",
10]
11
12# This will load the default model: BAAI/bge-small-en-v1.5
13embedding_model = TextEmbedding()
14
15# Generate embeddings
16# The output is a generator of numpy arrays
17embeddings_generator = embedding_model.embed(documents)
18
19# Convert generator to a list or process as needed
20embeddings = list(embeddings_generator)
21
22print(f"Number of embeddings: {len(embeddings)}")
23print(f"Vector dimension: {len(embeddings[0])}")