Delete old configs + set gemini flash 2-lite as default base model

Author: strickvl

deep_research/configs/compare_viewpoints.yaml

@@ -27,11 +27,11 @@ langfuse_project_name: "deep-research"
 steps:
   initial_query_decomposition_step:
     parameters:
-      llm_model: "openrouter/google/gemini-2.5-flash-preview-05-20"
+      llm_model: "openrouter/google/gemini-2.0-flash-lite-001"
 
   cross_viewpoint_analysis_step:
     parameters:
-      llm_model: "openrouter/google/gemini-2.5-flash-preview-05-20"
+      llm_model: "openrouter/google/gemini-2.0-flash-lite-001"
       viewpoint_categories:
         [
           "scientific",
@@ -44,7 +44,7 @@ steps:
 
   generate_reflection_step:
     parameters:
-      llm_model: "openrouter/google/gemini-2.5-flash-preview-05-20"
+      llm_model: "openrouter/google/gemini-2.0-flash-lite-001"
 
   get_research_approval_step:
     parameters:
@@ -53,11 +53,11 @@ steps:
 
   execute_approved_searches_step:
     parameters:
-      llm_model: "openrouter/google/gemini-2.5-flash-preview-05-20"
+      llm_model: "openrouter/google/gemini-2.0-flash-lite-001"
 
   pydantic_final_report_step:
     parameters:
-      llm_model: "openrouter/google/gemini-2.5-flash-preview-05-20"
+      llm_model: "openrouter/google/gemini-2.0-flash-lite-001"
 
 # Environment settings
 settings:

deep_research/configs/daily_trends.yaml

@@ -96,7 +96,7 @@ def safe_json_loads(json_str: Optional[str]) -> Dict[str, Any]:
 def run_llm_completion(
     prompt: str,
     system_prompt: str,
-    model: str = "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model: str = "openrouter/google/gemini-2.0-flash-lite-001",
     clean_output: bool = True,
     max_tokens: int = 2000,  # Increased default token limit
     temperature: float = 0.2,
@@ -197,7 +197,7 @@ def run_llm_completion(
 def get_structured_llm_output(
     prompt: str,
     system_prompt: str,
-    model: str = "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model: str = "openrouter/google/gemini-2.0-flash-lite-001",
     fallback_response: Optional[Dict[str, Any]] = None,
     max_tokens: int = 2000,  # Increased default token limit for structured outputs
     temperature: float = 0.2,
@@ -289,7 +289,7 @@ def is_text_relevant(text1: str, text2: str, min_word_length: int = 4) -> bool:
 def find_most_relevant_string(
     target: str,
     options: List[str],
-    model: Optional[str] = "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model: Optional[str] = "openrouter/google/gemini-2.0-flash-lite-001",
     project: str = "deep-research",
     tags: Optional[List[str]] = None,
 ) -> Optional[str]:
@@ -406,7 +406,7 @@ def find_most_relevant_string(
 
 def synthesize_information(
     synthesis_input: Dict[str, Any],
-    model: str = "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model: str = "openrouter/google/gemini-2.0-flash-lite-001",
     system_prompt: Optional[str] = None,
     project: str = "deep-research",
     tags: Optional[List[str]] = None,

deep_research/configs/enhanced_research.yaml

@@ -522,7 +522,7 @@ def extract_search_results(
 
 def generate_search_query(
     sub_question: str,
-    model: str = "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model: str = "openrouter/google/gemini-2.0-flash-lite-001",
     system_prompt: Optional[str] = None,
     project: str = "deep-research",
 ) -> Dict[str, Any]: