跳至主要內容

NomicEmbeddings

這將幫助您開始使用 LangChain 的 Nomic 嵌入模型。有關 NomicEmbeddings 功能和配置選項的詳細文檔,請參閱API 參考文檔

概觀

整合細節

提供者套件
Nomiclangchain-nomic

設定

若要存取 Nomic 嵌入模型,您需要建立 Nomic 帳戶、取得 API 金鑰,並安裝 langchain-nomic 整合套件。

憑證

前往 https://atlas.nomic.ai/ 註冊 Nomic 並產生 API 金鑰。完成後,設定 NOMIC_API_KEY 環境變數

import getpass
import os

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

如果您想要自動追蹤您的模型呼叫,您也可以取消註解下方內容,設定您的 LangSmith API 金鑰

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

安裝

LangChain Nomic 整合位於 langchain-nomic 套件中

%pip install -qU langchain-nomic
Note: you may need to restart the kernel to use updated packages.

實例化

現在我們可以實例化我們的模型物件並產生聊天完成

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.
)
API 參考文檔:NomicEmbeddings

索引與檢索

嵌入模型通常用於檢索增強生成 (RAG) 流程中,作為索引資料以及後續檢索資料的一部分。有關更詳細的說明,請參閱我們的RAG 教學

請參閱以下內容,了解如何使用我們上面初始化的 embeddings 物件來索引和檢索資料。在本範例中,我們將在 InMemoryVectorStore 中索引和檢索範例文件。

# 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
API 參考文檔:InMemoryVectorStore
'LangChain is the framework for building context-aware reasoning applications'

直接使用

在底層,vectorstore 和 retriever 實作會呼叫 embeddings.embed_documents(...)embeddings.embed_query(...),以為 from_texts 和檢索 invoke 操作中使用的文字建立嵌入。

您可以直接呼叫這些方法來取得嵌入,以用於您自己的使用案例。

嵌入單個文字

您可以使用 embed_query 嵌入單個文字或文件

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100]) # Show the first 100 characters of the vector
[0.024642944, 0.029083252, -0.14013672, -0.09082031, 0.058898926, -0.07489014, -0.0138168335, 0.0037

嵌入多個文字

您可以使用 embed_documents 嵌入多個文字

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
[0.012771606, 0.023727417, -0.12365723, -0.083740234, 0.06530762, -0.07110596, -0.021896362, -0.0068
[-0.019058228, 0.04058838, -0.15222168, -0.06842041, -0.012130737, -0.07128906, -0.04534912, 0.00522

API 參考文檔

有關 NomicEmbeddings 功能和配置選項的詳細文檔,請參閱API 參考文檔


此頁面是否有幫助?