Gradient
Gradient allows to createEmbeddings as well fine tune and get completions on LLMs with a simple web API.
This notebook goes over how to use Langchain with Embeddings ofGradient.
Imports
from langchain_community.embeddingsimport GradientEmbeddings
API Reference:GradientEmbeddings
Set the Environment API Key
Make sure to get your API key from Gradient AI. You are given $10 in free credits to test and fine-tune different models.
import os
from getpassimport getpass
ifnot os.environ.get("GRADIENT_ACCESS_TOKEN",None):
# Access token under https://auth.gradient.ai/select-workspace
os.environ["GRADIENT_ACCESS_TOKEN"]= getpass("gradient.ai access token:")
ifnot os.environ.get("GRADIENT_WORKSPACE_ID",None):
# `ID` listed in `$ gradient workspace list`
# also displayed after login at at https://auth.gradient.ai/select-workspace
os.environ["GRADIENT_WORKSPACE_ID"]= getpass("gradient.ai workspace id:")
Optional: Validate your environment variablesGRADIENT_ACCESS_TOKEN andGRADIENT_WORKSPACE_ID to get currently deployed models. Using thegradientai Python package.
%pip install--upgrade--quiet gradientai
Create the Gradient instance
documents=[
"Pizza is a dish.",
"Paris is the capital of France",
"numpy is a lib for linear algebra",
]
query="Where is Paris?"
embeddings= GradientEmbeddings(model="bge-large")
documents_embedded= embeddings.embed_documents(documents)
query_result= embeddings.embed_query(query)
# (demo) compute similarity
import numpyas np
scores= np.array(documents_embedded) @ np.array(query_result).T
dict(zip(documents, scores))
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides