Let's load the Hugging Face Embedding class.
%pip install --upgrade --quiet langchain langchain-huggingface sentence_transformers
from langchain_huggingface.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
text = "This is a test document."
query_result = embeddings.embed_query(text)
[-0.04895168915390968, -0.03986193612217903, -0.021562768146395683]
doc_result = embeddings.embed_documents([text])
We can also access embedding models via the Inference Providers, which let's us use open source models on scalable serverless infrastructure.
First, we need to get a read-only API key from Hugging Face.
from getpass import getpass
huggingfacehub_api_token = getpass()
Now we can use the HuggingFaceInferenceAPIEmbeddings class to run open source embedding models via Inference Providers.
from langchain_huggingface import 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]
We can also generate embeddings locally via the Hugging Face Hub package, which requires us to install huggingface_hub
!pip install huggingface_hub
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
embeddings = HuggingFaceEndpointEmbeddings()
text = "This is a test document."
query_result = embeddings.embed_query(text)
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4