Merge pull request #367 from VectifyAI/add-summary-model-config

Add summary_model config

pageindex/config.yaml

@@ -1,5 +1,6 @@
 model: "gpt-4o-2024-11-20"
 # model: "anthropic/claude-sonnet-4-6"
+summary_model: "gpt-4.1-nano"
 retrieve_model: "gpt-5.4"  # defaults to `model` if not set
 toc_check_page_num: 20
 max_page_num_each_node: 10

pageindex/page_index.py

@@ -1254,13 +1254,13 @@ def page_index_main(doc, opt=None):
         if opt.if_add_node_summary == 'yes':
             if opt.if_add_node_text == 'no':
                 add_node_text(structure, page_list)
-            await generate_summaries_for_structure(structure, model=opt.model)
+            await generate_summaries_for_structure(structure, model=getattr(opt, 'summary_model', None) or opt.model)
             if opt.if_add_node_text == 'no':
                 remove_structure_text(structure)
             if opt.if_add_doc_description == 'yes':
                 # Create a clean structure without unnecessary fields for description generation
                 clean_structure = create_clean_structure_for_description(structure)
-                doc_description = generate_doc_description(clean_structure, model=opt.model)
+                doc_description = generate_doc_description(clean_structure, model=getattr(opt, 'summary_model', None) or opt.model)
                 structure = format_structure(structure, order=['title', 'node_id', 'start_index', 'end_index', 'summary', 'text', 'nodes'])
                 return {
                     'doc_name': get_pdf_name(doc),