~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
refactor(modular_strategy): drop duplicated existing_queries normalization (#4218)
LearningCircuit24a1045a3bf3
diff --git a/src/local_deep_research/advanced_search_system/strategies/modular_strategy.py b/src/local_deep_research/advanced_search_system/strategies/modular_strategy.pyindex abc2c84f18..02d4f6718c 100644--- a/src/local_deep_research/advanced_search_system/strategies/modular_strategy.py+++ b/src/local_deep_research/advanced_search_system/strategies/modular_strategy.py@@ -54,17 +54,6 @@ class LLMConstraintProcessor:if existing_queries is None:existing_queries = []- existing_queries_str = (- "\n".join([f"- {q}" for q in existing_queries])- if existing_queries- else "None yet"- )-- # Store all queries we've used to avoid repeats- if existing_queries is None:- existing_queries = []-- # Add the original query as first in our trackingall_queries_used = ([original_query] + existing_queriesif original_query