Native Python API#
- __init__.Client(root_dir='.')#
- __init__.Client.Create(self, table_name, model_name='HuggingFace')#
Create a new table with the specified embedding model.
- Args:
table_name: the creating table name. model_name: the embedding model name, default to “HuggingFace”.
- Returns:
True or False, whether creating table success.
- __init__.Client.Add(self, doc)#
Add document into the current table, the format of doc is list of dict, each dict denotes a document.
- Args:
- doc: A list of documents for adding.
Each document denoted a dict, in which the key is a field, the value is a field value.
- Returns:
True or False for adding documents.
- __init__.Client.Search(self, query, topn, text_in_page_content: str | None = None, meta_filter: dict | None = None, not_include_fields: Set[str] | None = None, **kwargs: Any)#
Search API.
- Args:
query: Search request. text or vector is valid. topn: The most topn similar results by searching. test_in_page_content: The filter text in page content, used in langchain. meta_filter: Meta filter, each key-value pair denotes field_name-field_value pair. not_include_fields: The fields not included in the returned search results.
- Returns:
Search results, json format output.
- __init__.Client.Get(self, ids: List[str] | None = None, text_in_page_content: str | None = None, meta_filter: dict | None = None, not_include_fields: Set[str] | None = None, limit: int | None = None, **kwargs: Any) list#
- Get the documents which have the specified ids.
If ids is specified, text_in_page_content, meta_filter, and limit will be invalid.
- Args:
ids: The ids of the embedding vectors. text_in_page_content: Filter by the text in page_content of Document in LangChain. meta_filter: Filter by any metadata of the document. not_include_fields: Not pack the specified fields of each document. limit: The number of documents to return. Optional. Defaults to 5.
- Returns:
Documents which satisfy the input conditions.
- __init__.Client.Delete(self, ids: List[str]) bool#
Delete the documents which have the specified ids.
- Args:
ids: The id list of the updating embedding vector.
- Returns:
True or False.
- __init__.Client.ListAllTables(self) List[str]#
List all created tables.
- Returns:
List of created table names.
- __init__.Client.GetCurrentTable(self) str#
Get current using table name.
- Returns:
The table name of using.
- __init__.Client.Load(self, table_name) bool#
Load the specified table.
- Args:
table_name: the loading table name.
- Returns:
True or False, whether loading the specified table success.
- __init__.Client.Use(self, table_name) bool#
Use the specified table engine.
- Args:
table_name: the using table name.
- Returns:
True or False, whether using the specified table engine success.
- __init__.Client.Close(self, table_name: str | None = None)#
Close the specified table engine.
- Args:
table_name: the table name of closing, default to None, means current using table engine.
- Returns:
True or False, whether close table engine success.