'commit'
This commit is contained in:
@@ -1,15 +1,11 @@
|
||||
import os
|
||||
|
||||
# pip install pydantic
|
||||
from langchain_core.documents import Document
|
||||
from langchain_core.vectorstores import InMemoryVectorStore
|
||||
from langchain_openai import OpenAIEmbeddings
|
||||
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||||
|
||||
from pydantic import SecretStr # 导入 SecretStr
|
||||
from Config.Config import EMBED_MODEL_NAME, EMBED_BASE_URL, EMBED_API_KEY
|
||||
|
||||
# 设置环境变量
|
||||
os.environ["OPENAI_BASE_URL"] = EMBED_BASE_URL
|
||||
os.environ["OPENAI_API_KEY"] = EMBED_API_KEY
|
||||
|
||||
# 模拟长字符串文档内容
|
||||
long_text = """混凝土是一种广泛使用的建筑材料,由水泥、砂、石子和水混合而成。它具有高强度、耐久性和良好的可塑性,被广泛应用于建筑、桥梁、道路等土木工程领域。
|
||||
@@ -37,7 +33,11 @@ all_splits = text_splitter.split_documents(docs)
|
||||
print(f"切割后的文档块数量:{len(all_splits)}")
|
||||
|
||||
# 嵌入模型
|
||||
embeddings = OpenAIEmbeddings(model=EMBED_MODEL_NAME)
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model=EMBED_MODEL_NAME,
|
||||
base_url=EMBED_BASE_URL,
|
||||
api_key=SecretStr(EMBED_API_KEY) # 包装成 SecretStr 类型
|
||||
)
|
||||
|
||||
# 向量存储
|
||||
vector_store = InMemoryVectorStore(embeddings)
|
||||
|
Reference in New Issue
Block a user