TextEmbed - 嵌入推理服务器

from langchain_community.embeddings import TextEmbedEmbeddings

embeddings = TextEmbedEmbeddings(
    model="sentence-transformers/all-MiniLM-L12-v2",
    api_url="http://0.0.0.0:8000/v1",
    api_key="TextEmbed",
)

# Define a list of documents
documents = [
    "Data science involves extracting insights from data.",
    "Artificial intelligence is transforming various industries.",
    "Cloud computing provides scalable computing resources over the internet.",
    "Big data analytics helps in understanding large datasets.",
    "India has a diverse cultural heritage.",
]

# Define a query
query = "What is the cultural heritage of India?"

# Embed all documents
document_embeddings = embeddings.embed_documents(documents)

# Embed the query
query_embedding = embeddings.embed_query(query)

# Compute Similarity
import numpy as np

scores = np.array(document_embeddings) @ np.array(query_embedding).T
dict(zip(documents, scores))

{'Data science involves extracting insights from data.': 0.05121298956322118,
 'Artificial intelligence is transforming various industries.': -0.0060612142358469345,
 'Cloud computing provides scalable computing resources over the internet.': -0.04877402795301714,
 'Big data analytics helps in understanding large datasets.': 0.016582168576929422,
 'India has a diverse cultural heritage.': 0.7408992963028144}