Embedding models

import numpy as np

def cosine_similarity(vec1, vec2):
    dot = np.dot(vec1, vec2)
    return dot / (np.linalg.norm(vec1) * np.linalg.norm(vec2))

similarity = cosine_similarity(query_embedding, document_embedding)
print("Cosine Similarity:", similarity)

import time
from langchain_classic.embeddings import CacheBackedEmbeddings  
from langchain_classic.storage import LocalFileStore 
from langchain_core.vectorstores import InMemoryVectorStore

# Create your underlying embeddings model
underlying_embeddings = ... # e.g., OpenAIEmbeddings(), HuggingFaceEmbeddings(), etc.

# Store persists embeddings to the local filesystem
# This isn't for production use, but is useful for local
store = LocalFileStore("./cache/") 

cached_embedder = CacheBackedEmbeddings.from_bytes_store(
    underlying_embeddings,
    store,
    namespace=underlying_embeddings.model
)

# Example: caching a query embedding
tic = time.time()
print(cached_embedder.embed_query("Hello, world!"))
print(f"First call took: {time.time() - tic:.2f} seconds")

# Subsequent calls use the cache
tic = time.time()
print(cached_embedder.embed_query("Hello, world!"))
print(f"Second call took: {time.time() - tic:.2f} seconds")