wehub-resource-sync
c889a57b6b
Test Suites / Build CI Environment (push) Has been cancelled
Test Suites / Basic Tests (push) Has been cancelled
Test Suites / End-to-End Tests (push) Has been cancelled
Test Suites / CLI Tests (push) Has been cancelled
Test Suites / Slow End-to-End Tests (push) Has been cancelled
Test Suites / Graph Database Tests (push) Has been cancelled
Test Suites / Vector DB Tests (push) Has been cancelled
Test Suites / Temporal Graph Test (push) Has been cancelled
Test Suites / Search Test on Different DBs (push) Has been cancelled
Test Suites / Example Tests (push) Has been cancelled
Test Suites / Notebook Tests (push) Has been cancelled
Test Suites / OS and Python Tests Ubuntu (push) Has been cancelled
Test Suites / OS and Python Tests Extended (push) Has been cancelled
Test Suites / LLM Test Suite (push) Has been cancelled
Test Suites / S3 File Storage Test (push) Has been cancelled
Test Suites / Run Integration Tests (push) Has been cancelled
Test Suites / MCP Tests (push) Has been cancelled
Test Suites / Docker Compose Test (push) Has been cancelled
Test Suites / Docker CI test (push) Has been cancelled
Test Suites / Relational DB Migration Tests (push) Has been cancelled
Test Suites / Distributed Cognee Test (push) Has been cancelled
Test Suites / DB Examples Tests (push) Has been cancelled
Test Suites / Test Completion Status (push) Has been cancelled
Test Suites / Claude Code Review (push) Has been cancelled
Test Suites / basic checks (push) Has been cancelled
build | Build and Push Cognee MCP Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Scorecard supply-chain security / Scorecard analysis (push) Has been cancelled
build | Build and Push Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.11) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.12) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (kuzu, kuzu) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (neo4j, neo4j) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Examples (push) Has been cancelled
Weighted Edges Tests / Code Quality for Weighted Edges (push) Has been cancelled
Summarization
Overview
The summarization module provides LLM-powered text and code summarization for Cognee's knowledge graph pipeline. It transforms document chunks and source code into structured, searchable summaries.
Note
This module runs automatically in
cognee.cognify()(Task #4). Users typically don't call these functions directly unless building custom workflows.
Pipeline Position: cognee.add() → chunking → graph extraction → summarize_text → storage
Components
Functions
| Function | Description |
|---|---|
summarize_text(data_chunks, summarization_model=None) |
Summarizes document chunks using LLM, returns list[TextSummary] |
summarize_code(code_graph_nodes) |
Extracts structured summaries from code files, yields DataPoint and CodeSummary objects |
Data Models (extend DataPoint)
| Model | Key Fields |
|---|---|
TextSummary |
text, made_from (DocumentChunk reference), metadata |
CodeSummary |
text, summarizes (CodeFile/CodePart reference), metadata |
Exception
| Exception | Description |
|---|---|
InvalidSummaryInputsError |
Raised when input is not a list or chunks lack .text attribute |
Usage
Automatic (Recommended)
import cognee
await cognee.add(["document.pdf", "notes.txt"])
await cognee.cognify() # summarize_text runs automatically
results = await cognee.search(query_text="key concepts", query_type=cognee.SearchType.SUMMARIES)
Manual Text Summarization
from cognee.tasks.summarization import summarize_text
summaries = await summarize_text(document_chunks)
for summary in summaries:
print(f"Summary: {summary.text}")
print(f"Source: {summary.made_from.id}")
With Custom Model
from pydantic import BaseModel
class CustomSummary(BaseModel):
title: str
key_points: list[str]
summaries = await summarize_text(document_chunks, summarization_model=CustomSummary)
Code Summarization
from cognee.tasks.summarization import summarize_code
async for item in summarize_code(code_nodes):
if hasattr(item, 'text'): # CodeSummary
print(f"Code summary: {item.text[:100]}...")
Configuration
Default summarization model is SummarizedContent from cognee.modules.cognify.config.get_cognify_config().
Environment Variables:
| Variable | Description |
|---|---|
LLM_API_KEY |
API key for LLM provider (required) |
LLM_PROVIDER |
Provider name (default: openai) |
LLM_MODEL |
Model name (default: openai/gpt-5-mini) |
MOCK_CODE_SUMMARY |
Use mock summaries for testing (true/false) |
Dependencies
Internal: cognee.infrastructure.llm.extraction, cognee.modules.chunking.models, cognee.infrastructure.engine.DataPoint
External: pydantic, LLM provider (OpenAI/Anthropic/etc.)
Related
- cognee docs | Chunking | Storage | Tests