graphrag_sdk package

Subpackages

• graphrag_sdk.schema package
  • Submodules
  • graphrag_sdk.schema.auto_detect module
    • convert_table()
    • convert_tables()
    • create_entity()
    • create_entity_with_relation()
    • create_relation()
    • generate_graph_schema()
    • get_assistant()
    • handle_run()
    • initiate_interaction()
    • process_source()
    • run_sql()
    • schema_auto_detect()
    • sqlalchemy_to_python_type()
  • graphrag_sdk.schema.decoder module
    • SchemaDecoder
      • SchemaDecoder.decode()
      • SchemaDecoder.from_JSON()
  • graphrag_sdk.schema.encoder module
    • SchemaEncoder
      • SchemaEncoder.encode()
      • SchemaEncoder.to_JSON()
  • graphrag_sdk.schema.entity module
    • Attribute
    • Entity
      • Entity.add_attribute()
      • Entity.get_attribute()
      • Entity.remove_attribute()
      • Entity.unique_attributes()
  • graphrag_sdk.schema.from_graph module
    • schema_from_graph()
  • graphrag_sdk.schema.functions_gen module
    • entity_to_create_func()
    • relation_to_create_func()
    • schema_to_functions()
  • graphrag_sdk.schema.relation module
    • Relation
  • graphrag_sdk.schema.schema module
    • Schema
      • Schema.add_entity()
      • Schema.add_relation()
      • Schema.auto_detect()
      • Schema.from_JSON()
      • Schema.from_graph()
      • Schema.get_entity()
      • Schema.save_graph()
      • Schema.to_JSON()
      • Schema.validate()
  • graphrag_sdk.schema.to_graph module
    • schema_to_graph()
  • graphrag_sdk.schema.tools_gen module
    • entity_to_tool()
    • relation_to_tool()
    • schema_to_tools()
    • type_mapping()
  • Module contents

Submodules

graphrag_sdk.kg module

class graphrag_sdk.kg.KnowledgeGraph(name: str, host: str = '127.0.0.1', port: int = 6379, username: str | None = None, password: str | None = None, model: str = 'gpt-4-1106-preview', schema: Schema | None = None)

Bases: object

Knowledge Graph model data as a network of entities and relations To create one it is best to provide a schema which will define the graph’s ontology In addition to a set of sources from which entities and relations will be extracted.

ask(question: str, history: list | None = None) → tuple[str, list]

Query the knowledge graph using natural language if the query is asked as part of a longer conversation make sure to include past history.

Returns:

tuple[str, list]: answer, conversation history

Example:

>>> ans, history = kg.ask("Which actor has the most oscars")
>>> ans, history = kg.ask("List a few movies in which that actored played in", history)

delete() → None

Deletes the knowledge graph and any other related resource e.g. Schema, OpenAI assistant

list_sources() → list[AbstractSource]

List of sources associated with knowledge graph

Returns:

list[AbstractSource]: sources

property name

process_sources(sources: list[AbstractSource]) → None

Add entities and relations found in sources into the knowledge-graph

Parameters:

sources (list[AbstractSource]): list of sources to extract knowledge from

property schame

property schema

graphrag_sdk.prompts module

graphrag_sdk.query_graph module

graphrag_sdk.query_graph.query(kg, question: str, messages: list, model='gpt-4-1106-preview') → str

graphrag_sdk.query_graph.run_conversation(g, question, messages, model) → str

graphrag_sdk.query_graph.run_cypher_query(g, q)

graphrag_sdk.source module

class graphrag_sdk.source.AbstractSource(path: str)

Bases: ABC

Abstract class representing a source file

load() → Iterator[Document]

class graphrag_sdk.source.HTML(path)

Bases: AbstractSource

HTML resource

class graphrag_sdk.source.PDF(path)

Bases: AbstractSource

PDF resource

graphrag_sdk.source.Source(path: str, instruction: str | None = None) → AbstractSource

Creates a source object

Parameters:

path (str): path to source instruction (str): source specific instruction for the LLM

Returns:

AbstractSource: source

class graphrag_sdk.source.TEXT(path)

Bases: AbstractSource

TEXT resource

graphrag_sdk.template module

Module contents