test_ai/configs/kb_config.py.example

133 lines
4.2 KiB
Plaintext
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import os
# 默认使用的知识库
DEFAULT_KNOWLEDGE_BASE = "samples"
# 默认向量库/全文检索引擎类型。可选faiss, milvus(离线) & zilliz(在线), pgvector,全文检索引擎es
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 = 250
# 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
# 默认搜索引擎。可选bing, duckduckgo, metaphor
DEFAULT_SEARCH_ENGINE = "duckduckgo"
# 搜索引擎匹配结题数量
SEARCH_ENGINE_TOP_K = 3
# 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 = ""
# metaphor搜索需要KEY
METAPHOR_API_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
# 每个知识库的初始化介绍用于在初始化知识库时显示和Agent调用没写则没有介绍不会被Agent调用。
KB_INFO = {
"知识库名称": "知识库介绍",
"samples": "关于本项目issue的解答",
}
# 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,
},
"zilliz": {
"host": "in01-a7ce524e41e3935.ali-cn-hangzhou.vectordb.zilliz.com.cn",
"port": "19530",
"user": "",
"password": "",
"secure": True,
},
"pg": {
"connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatchat",
},
"es": {
"host": "127.0.0.1",
"port": "9200",
"index_name": "test_index",
"user": "",
"password": ""
}
}
# 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": "",
},
"SpacyTextSplitter": {
"source": "huggingface",
"tokenizer_name_or_path": "gpt2",
},
"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 = "ChineseRecursiveTextSplitter"
# Embedding模型定制词语的词表文件
EMBEDDING_KEYWORD_FILE = "embedding_keywords.txt"