Hugging Face
Let's load the Hugging Face Embedding class.
%pip install--upgrade--quiet langchain langchain-huggingface sentence_transformers
from langchain_huggingface.embeddingsimport HuggingFaceEmbeddings
API Reference:HuggingFaceEmbeddings
embeddings= HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
text="This is a test document."
query_result= embeddings.embed_query(text)
query_result[:3]
[-0.04895168915390968, -0.03986193612217903, -0.021562768146395683]
doc_result= embeddings.embed_documents([text])
Hugging Face Inference Providers
We can also access embedding models via theInference Providers, which let's us use open source models on scalable serverless infrastructure.
First, we need to get a read-only API key fromHugging Face.
from getpassimport getpass
huggingfacehub_api_token= getpass()
Now we can use theHuggingFaceInferenceAPIEmbeddings class to run open source embedding models viaInference Providers.
from langchain_huggingfaceimport HuggingFaceInferenceAPIEmbeddings
embeddings= HuggingFaceInferenceAPIEmbeddings(
api_key=huggingfacehub_api_token,
model_name="sentence-transformers/all-MiniLM-l6-v2",
)
query_result= embeddings.embed_query(text)
query_result[:3]
[-0.038338541984558105, 0.1234646737575531, -0.028642963618040085]
Hugging Face Hub
We can also generate embeddings locally via the Hugging Face Hub package, which requires us to installhuggingface_hub
!pip install huggingface_hub
from langchain_huggingface.embeddingsimport HuggingFaceEndpointEmbeddings
API Reference:HuggingFaceEndpointEmbeddings
embeddings= HuggingFaceEndpointEmbeddings()
text="This is a test document."
query_result= embeddings.embed_query(text)
query_result[:3]
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides