108 lines
3.7 KiB
Plaintext
108 lines
3.7 KiB
Plaintext
|
import os
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 默认向量库类型。可选：faiss, milvus, pg.
|
|||
|
|
DEFAULT_VS_TYPE = "faiss"
|
|||
|
|
|
|||
|
|
# 缓存向量库数量（针对FAISS）
|
|||
|
|
CACHED_VS_NUM = 1
|
|||
|
|
|
|||
|
|
# 知识库中单段文本长度(不适用MarkdownHeaderTextSplitter)
|
|||
|
|
CHUNK_SIZE = 500
|
|||
|
|
|
|||
|
|
# 知识库中相邻文本重合长度(不适用MarkdownHeaderTextSplitter)
|
|||
|
|
OVERLAP_SIZE = 50
|
|||
|
|
|
|||
|
|
# 知识库匹配向量数量
|
|||
|
|
VECTOR_SEARCH_TOP_K = 3
|
|||
|
|
|
|||
|
|
# 知识库匹配相关度阈值，取值范围在0-1之间，SCORE越小，相关度越高，取到1相当于不筛选，建议设置在0.5左右
|
|||
|
|
SCORE_THRESHOLD = 1
|
|||
|
|
|
|||
|
|
# 搜索引擎匹配结题数量
|
|||
|
|
SEARCH_ENGINE_TOP_K = 3
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 基于本地知识问答的提示词模版（使用Jinja2语法，简单点就是用双大括号代替f-string的单大括号
|
|||
|
|
PROMPT_TEMPLATE = """<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，不允许在答案中添加编造成分，答案请使用中文。 </指令>
|
|||
|
|
|
|||
|
|
<已知信息>{{ context }}</已知信息>
|
|||
|
|
|
|||
|
|
<问题>{{ question }}</问题>"""
|
|||
|
|
|
|||
|
|
|
|||
|
|
# Bing 搜索必备变量
|
|||
|
|
# 使用 Bing 搜索需要使用 Bing Subscription Key,需要在azure port中申请试用bing search
|
|||
|
|
# 具体申请方式请见
|
|||
|
|
# https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/create-bing-search-service-resource
|
|||
|
|
# 使用python创建bing api 搜索实例详见:
|
|||
|
|
# https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/quickstarts/rest/python
|
|||
|
|
BING_SEARCH_URL = "https://api.bing.microsoft.com/v7.0/search"
|
|||
|
|
# 注意不是bing Webmaster Tools的api key，
|
|||
|
|
|
|||
|
|
# 此外，如果是在服务器上，报Failed to establish a new connection: [Errno 110] Connection timed out
|
|||
|
|
# 是因为服务器加了防火墙，需要联系管理员加白名单，如果公司的服务器的话，就别想了GG
|
|||
|
|
BING_SUBSCRIPTION_KEY = ""
|
|||
|
|
|
|||
|
|
# 是否开启中文标题加强，以及标题增强的相关配置
|
|||
|
|
# 通过增加标题判断，判断哪些文本为标题，并在metadata中进行标记；
|
|||
|
|
# 然后将文本与往上一级的标题进行拼合，实现文本信息的增强。
|
|||
|
|
ZH_TITLE_ENHANCE = False
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 通常情况下不需要更改以下内容
|
|||
|
|
|
|||
|
|
# 知识库默认存储路径
|
|||
|
|
KB_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "knowledge_base")
|
|||
|
|
if not os.path.exists(KB_ROOT_PATH):
|
|||
|
|
os.mkdir(KB_ROOT_PATH)
|
|||
|
|
|
|||
|
|
# 数据库默认存储路径。
|
|||
|
|
# 如果使用sqlite，可以直接修改DB_ROOT_PATH；如果使用其它数据库，请直接修改SQLALCHEMY_DATABASE_URI。
|
|||
|
|
DB_ROOT_PATH = os.path.join(KB_ROOT_PATH, "info.db")
|
|||
|
|
SQLALCHEMY_DATABASE_URI = f"sqlite:///{DB_ROOT_PATH}"
|
|||
|
|
|
|||
|
|
# 可选向量库类型及对应配置
|
|||
|
|
kbs_config = {
|
|||
|
|
"faiss": {
|
|||
|
|
},
|
|||
|
|
"milvus": {
|
|||
|
|
"host": "127.0.0.1",
|
|||
|
|
"port": "19530",
|
|||
|
|
"user": "",
|
|||
|
|
"password": "",
|
|||
|
|
"secure": False,
|
|||
|
|
},
|
|||
|
|
"pg": {
|
|||
|
|
"connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatchat",
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# TextSplitter配置项，如果你不明白其中的含义，就不要修改。
|
|||
|
|
text_splitter_dict = {
|
|||
|
|
"ChineseRecursiveTextSplitter": {
|
|||
|
|
"source": "huggingface", ## 选择tiktoken则使用openai的方法
|
|||
|
|
"tokenizer_name_or_path": "gpt2",
|
|||
|
|
},
|
|||
|
|
"SpacyTextSplitter": {
|
|||
|
|
"source": "huggingface",
|
|||
|
|
"tokenizer_name_or_path": "",
|
|||
|
|
},
|
|||
|
|
"RecursiveCharacterTextSplitter": {
|
|||
|
|
"source": "tiktoken",
|
|||
|
|
"tokenizer_name_or_path": "cl100k_base",
|
|||
|
|
},
|
|||
|
|
"MarkdownHeaderTextSplitter": {
|
|||
|
|
"headers_to_split_on":
|
|||
|
|
[
|
|||
|
|
("#", "head1"),
|
|||
|
|
("##", "head2"),
|
|||
|
|
("###", "head3"),
|
|||
|
|
("####", "head4"),
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# TEXT_SPLITTER 名称
|
|||
|
|
TEXT_SPLITTER_NAME = "SpacyTextSplitter"
|