apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-28 01:26:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

feat: add PageIndex SDK with local/cloud dual-mode support (#207)

Browse source
This commit is contained in:
Kylin 2026-04-06 22:51:04 +08:00 • committed by Ray
parent f2dcffc0b7
commit c7fe93bb56
45 changed files with 4225 additions and 274 deletions
Download patch file Download diff file Expand all files Collapse all files

22
pageindex/config.py Normal file
View file

@ -0,0 +1,22 @@
# pageindex/config.py
from __future__ import annotations
from pydantic import BaseModel
class IndexConfig(BaseModel):
"""Configuration for the PageIndex indexing pipeline.
All fields have sensible defaults. Advanced users can override
via LocalClient(index_config=IndexConfig(...)) or a dict.
"""
model_config = {"extra": "forbid"}
model: str = "gpt-4o-2024-11-20"
retrieve_model: str | None = None
toc_check_page_num: int = 20
max_page_num_each_node: int = 10
max_token_num_each_node: int = 20000
if_add_node_id: bool = True
if_add_node_summary: bool = True
if_add_doc_description: bool = True
if_add_node_text: bool = False