NomicEmbeddings

import getpass
import os

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

# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

%pip install -qU langchain-nomic

from langchain_nomic import NomicEmbeddings

embeddings = NomicEmbeddings(
    model="nomic-embed-text-v1.5",
    # dimensionality=256,
    # Nomic's `nomic-embed-text-v1.5` model was [trained with Matryoshka learning](https://blog.nomic.ai/posts/nomic-embed-matryoshka)
    # to enable variable-length embeddings with a single model.
    # This means that you can specify the dimensionality of the embeddings at inference time.
    # The model supports dimensionality from 64 to 768.
    # inference_mode="remote",
    # One of `remote`, `local` (Embed4All), or `dynamic` (automatic). Defaults to `remote`.
    # api_key=... , # if using remote inference,
    # device="cpu",
    # The device to use for local embeddings. Choices include
    # `cpu`, `gpu`, `nvidia`, `amd`, or a specific device name. See
    # the docstring for `GPT4All.__init__` for more info. Typically
    # defaults to CPU. Do not use on macOS.
)

# 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

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

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