LangChain 010

from langchain_openai import OpenAIEmbeddings

e_model = OpenAIEmbeddings()
ebeddings = e_model.embed_documents(
     [
        "你好",
        "你好啊",
        "你叫什么名字?",
        "我叫王大锤",
        "很高兴认识你大锤",
    ]
)
ebeddings

embedded_query = e_model.embed_query("这段对话中提到了什么名字?")
embedded_query[:5]

from langchain.embeddings import CacheBackedEmbeddings
from langchain.storage import  LocalFileStore
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
u_embeddings = OpenAIEmbeddings()
fs = LocalFileStore("./cache/")
cached_embeddings = CacheBackedEmbeddings.from_bytes_store(
    u_embeddings,
    fs,
    namespace=u_embeddings.model,
)
list(fs.yield_keys())

#加载文档，切分文档，将切分文档向量化病存储在缓存中

raw_documents = TextLoader("letter.txt").load()
text_splitter = CharacterTextSplitter(chunk_size=600,chunk_overlap=0)
documents = text_splitter.split_documents(raw_documents)

from langchain.vectorstores import  FAISS
%timeit -r  1 -n 1 db= FAISS.from_documents(documents,cached_embeddings)

#查看缓存中的键
list(fs.yield_keys())