langchain/docs/extras/integrations/text_embedding/huggingfacehub.ipynb

Hugging Face

Let's load the Hugging Face Embedding class.

In [ ]:

!pip install langchain sentence_transformers

In [2]:

from langchain.embeddings import HuggingFaceEmbeddings

In [3]:

embeddings = HuggingFaceEmbeddings()

In [3]:

text = "This is a test document."

In [5]:

query_result = embeddings.embed_query(text)

In [6]:

query_result[:3]

Out [6]:

[-0.04895168915390968, -0.03986193612217903, -0.021562768146395683]

In [7]:

doc_result = embeddings.embed_documents([text])

Hugging Face Inference API

We can also access embedding models via the Hugging Face Inference API, which does not require us to install sentence_transformers and download models locally.

In [1]:

import getpass

inference_api_key = getpass.getpass("Enter your HF Inference API Key:\n\n")

Enter your HF Inference API Key:

 ········

In [4]:

from langchain.embeddings import HuggingFaceInferenceAPIEmbeddings

embeddings = HuggingFaceInferenceAPIEmbeddings(
    api_key=inference_api_key,
    model_name="sentence-transformers/all-MiniLM-l6-v2"
)

query_result = embeddings.embed_query(text)
query_result[:3]

Out [4]:

[-0.038338541984558105, 0.1234646737575531, -0.028642963618040085]