Custom Prompts

A minimal guide to shaping graph extraction with a custom LLM prompt. You’ll pass your prompt via custom_prompt to cognee.remember() to control entity types, relationship labels, and extraction rules.

For the built-in graph extraction prompts selected through GRAPH_PROMPT_PATH, see Cognify.

Before you start:

Complete Quickstart to understand basic operations
Ensure you have LLM Providers configured
Have some text or files to process

Code in Action

Step 1: Write a Custom Prompt

custom_prompt = """
Extract only people and cities as entities.
Connect people to cities with the relationship "lives_in".
Ignore all other entities.
"""

The custom prompt overrides the default system prompt used during entity/relationship extraction. It constrains node types, enforces relationship naming, and reduces noise.

Step 2: Remember with Your Custom Prompt

await cognee.forget(everything=True)
await cognee.remember(
    [
        "Alice moved to Paris in 2010, while Bob has always lived in New York.",
        "Andreas was born in Venice, but later settled in Lisbon.",
        "Diana and Tom were born and raised in Helsinki. Diana currently resides in Berlin, while Tom never moved.",
    ],
    custom_prompt=custom_prompt,
    self_improvement=False,
)

This resets the local state and then uses remember() to ingest the text and build the graph in one pass. The same approach works with multiple documents, files, or entire datasets.

Step 3: Ask Questions

res = await cognee.recall(
    query_type=SearchType.GRAPH_COMPLETION,
    query_text="Where does Alice live?",
)

Use cognee.recall(...) with SearchType.GRAPH_COMPLETION to get answers that leverage your custom extraction rules.

`custom_prompt` vs `system_prompt`: which prompt goes where

Cognee uses two distinct prompts at two different stages, and they are not interchangeable. Passing one where the other is expected will silently have no effect.

Cognee v1.0
Legacy

Operation	Prompt parameter	What it influences	Stage
`cognee.remember()`	`custom_prompt`	Entity & relationship extraction — `remember()` runs `add()` + `cognify()` under the hood, so this overrides the graph extraction prompt used during graph build.	Graph build
`cognee.recall()`	`system_prompt` (or `system_prompt_path`)	Answer generation — instructs the LLM how to compose the final answer from retrieved context. Only applies to completion-style retrieval (`GRAPH_COMPLETION`, `RAG_COMPLETION`, etc.); ignored by `only_context=True` and by non-completion retrieval paths.	Query time

Operation	Prompt parameter	What it influences	Stage
`cognee.add()`	none	— (pure ingestion; no LLM call)	Ingestion
`cognee.cognify()`	`custom_prompt`	Entity & relationship extraction — overrides the default graph extraction prompt (see `GRAPH_PROMPT_PATH`)	Graph build
`cognee.search()`	`system_prompt` (or `system_prompt_path`)	Answer generation — instructs the LLM how to compose the final answer from retrieved context. Only applies to completion-style search types; ignored by `CHUNKS`, `SUMMARIES`, `CYPHER`, and when `only_context=True`.	Query time

system_prompt_path only loads files from cognee’s built-in prompts directory (cognee/infrastructure/llm/prompts). An absolute path, a .. segment that leaves the directory, or a symlink that points outside it raises PromptPathOutsideBaseDirectoryError. To use prompt text from your own project, read the file yourself and pass its contents as system_prompt.

Additional examples

Additional examples about Custom prompts are available on our github.

Full Example

Latest guide

import asyncio

import cognee
from cognee import SearchType

custom_prompt = """
Extract only people and cities as entities.
Connect people to cities with the relationship "lives_in".
Ignore all other entities.
"""


async def main():
    await cognee.forget(everything=True)
    await cognee.remember(
        [
            "Alice moved to Paris in 2010, while Bob has always lived in New York.",
            "Andreas was born in Venice, but later settled in Lisbon.",
            "Diana and Tom were born and raised in Helsinki. Diana currently resides in Berlin, while Tom never moved.",
        ],
        custom_prompt=custom_prompt,
        self_improvement=False,
    )

    res = await cognee.recall(
        query_type=SearchType.GRAPH_COMPLETION,
        query_text="Where does Alice live?",
    )
    print(res)


if __name__ == "__main__":
    asyncio.run(main())

Legacy guide

import asyncio
import cognee
from cognee.api.v1.search import SearchType

custom_prompt = """
Extract only people and cities as entities.
Connect people to cities with the relationship "lives_in".
Ignore all other entities.
"""

async def main():
    await cognee.add([
        "Alice moved to Paris in 2010, while Bob has always lived in New York.",
        "Andreas was born in Venice, but later settled in Lisbon.",
        "Diana and Tom were born and raised in Helsingy. Diana currently resides in Berlin, while Tom never moved."
    ])
    await cognee.cognify(custom_prompt=custom_prompt)

    res = await cognee.recall(
        query_type=SearchType.GRAPH_COMPLETION,
        query_text="Where does Alice live?",
    )
    print(res)

if __name__ == "__main__":
    asyncio.run(main())

This simple example uses a few strings for demonstration. In practice, you can add multiple documents, files, or entire datasets - the custom prompt processing works the same way across all your data.

If you are running Cognee as a server and want to infer a schema or generate a prompt through HTTP instead of writing it by hand, see the LLM Utility Endpoints examples in Deploy REST API Server.

Core Concepts

Understand knowledge graph fundamentals

Ontology Quickstart

Learn about ontology integration

API Reference

Explore API endpoints

Getting Started

Core Concepts

Setup Configuration

Guides

Cookbooks

Examples

CLI

OSS

Code in Action

Step 1: Write a Custom Prompt

Step 2: Remember with Your Custom Prompt

Step 3: Ask Questions

`custom_prompt` vs `system_prompt`: which prompt goes where

Additional examples

Full Example

Core Concepts

Ontology Quickstart

API Reference

​Code in Action

​Step 1: Write a Custom Prompt

​Step 2: Remember with Your Custom Prompt

​Step 3: Ask Questions

​custom_prompt vs system_prompt: which prompt goes where

​Additional examples

​Full Example

Core Concepts

Ontology Quickstart

API Reference

Code in Action

Step 1: Write a Custom Prompt

Step 2: Remember with Your Custom Prompt

Step 3: Ask Questions

`custom_prompt` vs `system_prompt`: which prompt goes where

Additional examples

Full Example