<!-- .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. --------- Signed-off-by: Raj2604 <rajmandhare26@gmail.com> Co-authored-by: Daulet Amirkhanov <damirkhanov01@gmail.com> Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com> Co-authored-by: Igor Ilic <igorilic03@gmail.com> Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com> Co-authored-by: Boris <boris@topoteretes.com> Co-authored-by: Matea Pesic <80577904+matea16@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions@users.noreply.github.com> Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com> Co-authored-by: Boris Arzentar <borisarzentar@gmail.com> Co-authored-by: Raj Mandhare <96978537+Raj2604@users.noreply.github.com> Co-authored-by: Pedro Thompson <thompsonp17@hotmail.com> Co-authored-by: Pedro Henrique Thompson Furtado <pedrothompson@petrobras.com.br>
28 lines
1 KiB
Python
28 lines
1 KiB
Python
import asyncio
|
|
from typing import Type, List
|
|
from pydantic import BaseModel
|
|
|
|
from cognee.infrastructure.llm.LLMGateway import LLMGateway
|
|
from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
|
|
from cognee.tasks.storage import add_data_points
|
|
|
|
|
|
async def extract_graph_from_code(
|
|
data_chunks: list[DocumentChunk], graph_model: Type[BaseModel]
|
|
) -> List[DocumentChunk]:
|
|
"""
|
|
Extracts a knowledge graph from the text content of document chunks using a specified graph model.
|
|
|
|
Notes:
|
|
- The `extract_content_graph` function processes each chunk's text to extract graph information.
|
|
- Graph nodes are stored using the `add_data_points` function for later retrieval or analysis.
|
|
"""
|
|
chunk_graphs = await asyncio.gather(
|
|
*[LLMGateway.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
|
|
)
|
|
|
|
for chunk_index, chunk in enumerate(data_chunks):
|
|
chunk_graph = chunk_graphs[chunk_index]
|
|
await add_data_points(chunk_graph.nodes)
|
|
|
|
return data_chunks
|