Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Python API Reference

Complete reference for the cognee Python package. All functions are accessible directly from the top-level cognee module. 
import cognee

# v1.0 workflow
await cognee.remember("Your data here")
results = await cognee.recall("Your query")

​
v1.0 Operations

remember()

Store data as permanent graph memory or fast session memory in one call.

recall()

Query memory with auto-routing and session-aware retrieval.

improve()

Enrich an existing graph and bridge session memory into permanent memory.

forget()

Remove a data item, an entire dataset, or all memory for the current user.

​
Legacy Operations

The lower-level pipeline operations are still available when you need direct control over each step.

add()

Ingest text, files, or structured data into the knowledge base.

cognify()

Transform raw data into a structured knowledge graph.

search()

Query the knowledge graph with multiple search modes.

memify()

Enrich an existing knowledge graph with custom extraction and enrichment tasks.

​
Data Management

datasets

List, create, and delete datasets.

update()

Update existing data items.

prune

Clean up data and system resources.

delete()

Delete data items (deprecated — use datasets).

run_startup_migrations()

Apply pending relational and vector database schema migrations.

​
Session Management

Sessions Guide

Use session_id and inspect stored conversation history with get_session().

Feedback System

Add and clear feedback on stored session Q&A entries.

​
Configuration & Utilities

config

Configure LLM providers, databases, chunking, and more.

SearchType

All available search modes and when to use them.

run_custom_pipeline()

Execute custom task pipelines.

Data Models

Key types: DataPoint, Task, PipelineRunInfo, SearchResult.