GreenNodeEmbeddings

import getpass
import os

if not os.getenv("GREENNODE_API_KEY"):
    os.environ["GREENNODE_API_KEY"] = getpass.getpass("Enter your GreenNode API key: ")

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

pip install -qU langchain-greennode

Note: you may need to restart the kernel to use updated packages.

from langchain_greennode import GreenNodeEmbeddings

# Initialize the embeddings model
embeddings = GreenNodeEmbeddings(
    # api_key="YOUR_API_KEY",  # You can pass the API key directly
    model="BAAI/bge-m3"  # The default embedding model
)

# Create a vector store with a sample text
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# Use the vectorstore as a retriever
retriever = vectorstore.as_retriever()

# Retrieve the most similar text
retrieved_documents = retriever.invoke("What is LangChain?")

# show the retrieved document's content
retrieved_documents[0].page_content

'LangChain is the framework for building context-aware reasoning applications'

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # Show the first 100 characters of the vector

[-0.01104736328125, -0.0281982421875, 0.0035858154296875, -0.0311279296875, -0.0106201171875, -0.039

text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # Show the first 100 characters of the vector

[-0.01104736328125, -0.0281982421875, 0.0035858154296875, -0.0311279296875, -0.0106201171875, -0.039
[-0.07177734375, -0.00017452239990234375, -0.002044677734375, -0.0299072265625, -0.0184326171875, -0

import asyncio


async def generate_embeddings_async():
    # Embed a single query
    query_result = await embeddings.aembed_query("What is the capital of France?")
    print(f"Async query embedding dimension: {len(query_result)}")

    # Embed multiple documents
    docs = [
        "Paris is the capital of France",
        "Berlin is the capital of Germany",
        "Rome is the capital of Italy",
    ]
    docs_result = await embeddings.aembed_documents(docs)
    print(f"Async document embeddings count: {len(docs_result)}")


await generate_embeddings_async()

Async query embedding dimension: 1024
Async document embeddings count: 3

import numpy as np
from scipy.spatial.distance import cosine

# Create some documents
documents = [
    "Machine learning algorithms build mathematical models based on sample data",
    "Deep learning uses neural networks with many layers",
    "Climate change is a major global environmental challenge",
    "Neural networks are inspired by the human brain's structure",
]

# Embed the documents
embeddings_list = embeddings.embed_documents(documents)


# Function to calculate similarity
def calculate_similarity(embedding1, embedding2):
    return 1 - cosine(embedding1, embedding2)


# Print similarity matrix
print("Document Similarity Matrix:")
for i, emb_i in enumerate(embeddings_list):
    similarities = []
    for j, emb_j in enumerate(embeddings_list):
        similarity = calculate_similarity(emb_i, emb_j)
        similarities.append(f"{similarity:.4f}")
    print(f"Document {i + 1}: {similarities}")

Document Similarity Matrix:
Document 1: ['1.0000', '0.6005', '0.3542', '0.5788']
Document 2: ['0.6005', '1.0000', '0.4154', '0.6170']
Document 3: ['0.3542', '0.4154', '1.0000', '0.3528']
Document 4: ['0.5788', '0.6170', '0.3528', '1.0000']