cognee/docs/api_reference.md

cognee API Reference

Overview

The Cognee API has

1. via Python library
2. FastAPI server

Python Library

Module: cognee.config

This module provides functionalities to configure various aspects of the system's operation in the cognee library. It interfaces with the cognee.infrastructure.infrastructure_config module to set configurations for system directories, machine learning models, and other components essential for system performance.

Overview

The config class in this module offers a series of static methods to configure the system's directories, various machine learning models, and other parameters.

Usage

Import the module as follows:

from cognee.config import config

Methods

system_root_directory(system_root_directory: str)

Sets the root directory of the system where essential system files and operations are managed. Parameters:
system_root_directory (str): The path to set as the system's root directory. Example:

config.system_root_directory('/path/to/system/root')

data_root_directory(data_root_directory: str)

Sets the directory for storing data used and generated by the system.
Parameters:
data_root_directory (str): The path to set as the data root directory.

Example:

config.data_root_directory('/path/to/data/root')

set_classification_model(classification_model: object)

Assigns a machine learning model for classification tasks within the system.
Parameters:
classification_model (object): The Pydantic model to use for classification. Check cognee.shared.data_models for existing models. Example:

config.set_classification_model(model)

set_summarization_model(summarization_model: object) Sets the Pydantic model to be used for summarization tasks.
Parameters:
summarization_model (object): The model to use for summarization. Check cognee.shared.data_models for existing models. Example:

config.set_summarization_model(my_summarization_model)

set_llm_model(llm_model: object)

Determines the model to handle LLMs. Parameters:
llm_model (object): The model to use for LLMs. Example:

config.set_llm_model("OpenAI")

set_graph_engine(graph_engine: object)

Sets the engine to manage graph processing tasks. Parameters:
graph_engine (object): The engine for graph tasks. Example:

from cognee.shared.data_models import GraphDBType

config.set_graph_engine(GraphDBType.NEO4J)

API

For each API endpoint, provide the following details:

Endpoint 1: Root

• URL: /add
• Method: POST
• Auth Required: No
• Description: Root endpoint that returns a welcome message.

Response

{
  "message": "Hello, World, I am alive!"
}

Endpoint 1: Health Check

• URL: /health
• Method: GET
• Auth Required: No
• Description: Health check endpoint that returns the server status.

Response

{
  "status": "OK"
}

Endpoint 2: Add

• URL: /Add
• Method: POST
• Auth Required: Yes | No
• Description: This endpoint is responsible for adding data to the graph.

Parameters

Name	Type	Required	Description
data	Union[str, BinaryIO, List[Union[str, BinaryIO]]]	Yes	The data to be added
dataset_id	UUID	Yes	The ID of the dataset.
dataset_name	String	Yes	The name of the dataset.

Response

{
  "response": "data"
}

Endpoint 3: Cognify

• URL: /cognify
• Method: POST
• Auth Required: Yes | No
• Description: This endpoint is responsible for the cognitive processing of the content.

Parameters

Name	Type	Required	Description
datasets	Union[str, List[str]]	Yes	The data to be added

Response

{
  "response": "data"
}

Endpoint 4: search

• URL: /search
• Method: POST
• Auth Required: No
• Description: This endpoint is responsible for searching for nodes in the graph.

Parameters

Name	Type	Required	Description
query_params	Dict[str, Any]	Yes	Description of the parameter.

Response

{
  "response": "data"
}