MistralAIEmbeddings 集成

import getpass
import os

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

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

pip install -qU langchain-mistralai

from langchain_mistralai import MistralAIEmbeddings

embeddings = MistralAIEmbeddings(
    model="mistral-embed",
)

# 使用示例文本创建向量存储
from langchain_core.vectorstores import InMemoryVectorStore

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

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

# 使用向量存储作为检索器
retriever = vectorstore.as_retriever()

# 检索最相似的文本
retrieved_documents = retriever.invoke("What is LangChain?")

# 显示检索到的文档内容
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])  # 显示向量的前100个字符

[-0.04443359375, 0.01885986328125, 0.018035888671875, -0.00864410400390625, 0.049652099609375, -0.00

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])  # 显示向量的前100个字符

[-0.04443359375, 0.01885986328125, 0.0180511474609375, -0.0086517333984375, 0.049652099609375, -0.00
[-0.02032470703125, 0.02606201171875, 0.051605224609375, -0.0281982421875, 0.055755615234375, 0.0019