cognee/cognee/tasks/summarization/summarize_text.py
Boris 0ce6fad24a
feat: pipeline tasks needs mapping (#690)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-04-03 10:52:59 +02:00

27 lines
808 B
Python

import asyncio
from typing import Type
from uuid import uuid5
from pydantic import BaseModel
from cognee.infrastructure.engine import DataPoint
from cognee.modules.data.extraction.extract_summary import extract_summary
from .models import TextSummary
async def summarize_text(data_chunks: list[DataPoint], summarization_model: Type[BaseModel]):
if len(data_chunks) == 0:
return data_chunks
chunk_summaries = await asyncio.gather(
*[extract_summary(chunk.text, summarization_model) for chunk in data_chunks]
)
summaries = [
TextSummary(
id=uuid5(chunk.id, "TextSummary"),
made_from=chunk,
text=chunk_summaries[chunk_index].summary,
)
for (chunk_index, chunk) in enumerate(data_chunks)
]
return summaries