mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-24 21:41:04 +02:00
1054132756
The local SDK path builds IndexConfig directly (not from config.yaml), so retrieve_model defaulting to None made agentic QA silently follow the cheaper indexing model (gpt-4o) instead of the stronger gpt-5.4 the packaged config and CLI use. Set the IndexConfig field default to gpt-5.4; retrieve_model=None still follows model as an explicit escape hatch. Cloud path and the index-only CLI are unaffected.
10 lines
No EOL
306 B
YAML
10 lines
No EOL
306 B
YAML
model: "gpt-4o-2024-11-20"
|
|
# model: "anthropic/claude-sonnet-4-6"
|
|
retrieve_model: "gpt-5.4" # set to null to follow `model`
|
|
toc_check_page_num: 20
|
|
max_page_num_each_node: 10
|
|
max_token_num_each_node: 20000
|
|
if_add_node_id: "yes"
|
|
if_add_node_summary: "yes"
|
|
if_add_doc_description: "no"
|
|
if_add_node_text: "no" |