Method●Since v0.3

from_connection_string

Construct a MongoDB KnowLedge Graph for RAG from a MongoDB connection URI.

from_connection_string(
  cls,
  connection_string: str,
  database_name: str,
  collection_name: str,
  entity_extraction_model: BaseChatModel,
  entity_prompt: ChatPromptTemplate = prompts.entity_prompt,
  query_prompt: ChatPromptTemplate = prompts.query_prompt,
  max_depth: int = 3,
  allowed_entity_types: Optional[List[str]] = None,
  allowed_relationship_types: Optional[List[str]] = None,
  entity_examples: Optional[str] = None,
  entity_name_examples: str = '',
  validate: bool = False,
  validation_action: str = 'warn'
) -> MongoDBGraphStore

Parameters

Name	Type	Description
`connection_string`*	`str`	A valid MongoDB connection URI.
`database_name`*	`str`	The name of the database to connect to.
`collection_name`*	`str`	The name of the collection to connect to.
`entity_extraction_model`*	`BaseChatModel`	LLM for converting documents into Graph of Entities and Relationships.
`entity_prompt`	`ChatPromptTemplate`	Default:`prompts.entity_prompt` Prompt to fill graph store with entities following schema.
`query_prompt`	`ChatPromptTemplate`	Default:`prompts.query_prompt` Prompt extracts entities and relationships as search starting points.
`max_depth`	`int`	Default:`3` Maximum recursion depth in graph traversal.
`allowed_entity_types`	`Optional[List[str]]`	Default:`None` If provided, constrains search to these types.
`allowed_relationship_types`	`Optional[List[str]]`	Default:`None` If provided, constrains search to these types.
`entity_examples`	`Optional[str]`	Default:`None` A string containing any number of additional examples to provide as context for entity extraction.
`entity_name_examples`	`str`	Default:`''` A string appended to prompts.NAME_EXTRACTION_INSTRUCTIONS containing examples.
`validate`	`bool`	Default:`False` If True, entity schema will be validated on every insert or update.
`validation_action`	`str`	Default:`'warn'` One of {"warn", "error"}. If "warn", the default, documents will be inserted but errors logged. If "error", an exception will be raised if any document does not match the schema.

View source on GitHub

from_connection_string( cls, connection_string: str, database_name: str, collection_name: str, entity_extraction_model: BaseChatModel, entity_prompt: ChatPromptTemplate = prompts.entity_prompt, query_prompt: ChatPromptTemplate = prompts.query_prompt, max_depth: int = 3, allowed_entity_types: Optional[List[str]] = None, allowed_relationship_types: Optional[List[str]] = None, entity_examples: Optional[str] = None, entity_name_examples: str = '', validate: bool = False, validation_action: str = 'warn' ) -> MongoDBGraphStore

Parameters

Name	Type	Description
`connection_string`*	`str`	A valid MongoDB connection URI.
`database_name`*	`str`	The name of the database to connect to.
`collection_name`*	`str`	The name of the collection to connect to.
`entity_extraction_model`*	`BaseChatModel`	LLM for converting documents into Graph of Entities and Relationships.
`entity_prompt`	`ChatPromptTemplate`	Default:`prompts.entity_prompt` Prompt to fill graph store with entities following schema.
`query_prompt`	`ChatPromptTemplate`	Default:`prompts.query_prompt` Prompt extracts entities and relationships as search starting points.
`max_depth`	`int`	Default:`3` Maximum recursion depth in graph traversal.
`allowed_entity_types`	`Optional[List[str]]`	Default:`None` If provided, constrains search to these types.
`allowed_relationship_types`	`Optional[List[str]]`	Default:`None` If provided, constrains search to these types.
`entity_examples`	`Optional[str]`	Default:`None` A string containing any number of additional examples to provide as context for entity extraction.
`entity_name_examples`	`str`	Default:`''` A string appended to prompts.NAME_EXTRACTION_INSTRUCTIONS containing examples.
`validate`	`bool`	Default:`False` If True, entity schema will be validated on every insert or update.
`validation_action`	`str`	Default:`'warn'` One of {"warn", "error"}. If "warn", the default, documents will be inserted but errors logged. If "error", an exception will be raised if any document does not match the schema.

from_connection_string

Parameters

LangChain Assistant

Menu

from_connection_string

Parameters