Update app.py

app.py

@@ -79,7 +79,7 @@ class ResearchConfig:
         "5. Limitations & Future Directions\n\n"
         "Format: Markdown with LaTeX mathematical notation where applicable"
     )
-    # Lowercase keys for fallback analyses
+    # Fallback analyses using lowercase keys for robust matching
     DOMAIN_FALLBACKS = {
         "biomedical research": """
 # Biomedical Research Analysis
@@ -92,7 +92,7 @@ class ResearchConfig:
 ## Empirical Results
 - Significant improvements in patient outcomes.
 ## Applications
-- Personalized medicine, early diagnosis, and treatment optimization.
+- Personalized medicine, early diagnosis, treatment optimization.
 """,
         "legal research": """
 # Legal Research Analysis
@@ -105,7 +105,7 @@ class ResearchConfig:
 ## Empirical Results
 - Improved accuracy in predicting case outcomes.
 ## Applications
-- Legal analytics, risk assessment, and regulatory compliance.
+- Legal analytics, risk assessment, regulatory compliance.
 """,
         "environmental and energy studies": """
 # Environmental and Energy Studies Analysis
@@ -126,7 +126,7 @@ class ResearchConfig:
 - Advanced approximation algorithms for NP-hard problems.
 - Use of parameterized complexity and fixed-parameter tractability.
 ## Methodologies
-- Branch-and-bound with dynamic programming.
+- Branch-and-bound combined with dynamic programming.
 - Quantum-inspired algorithms for optimization.
 ## Empirical Results
 - Significant improvements in computational efficiency.
@@ -144,7 +144,7 @@ class ResearchConfig:
 ## Empirical Results
 - High correlation with traditional survey methods.
 ## Applications
-- Policy design, urban studies, and social impact analysis.
+- Policy design, urban studies, social impact analysis.
 """
     }
     DOMAIN_PROMPTS = {
@@ -421,7 +421,7 @@ class QuantumKnowledgeGraph:
         self.nodes = {}
         self.relations = []
         self.node_counter = 0
-
+        
     def create_node(self, content: Dict, node_type: str) -> int:
         self.node_counter += 1
         self.nodes[self.node_counter] = {
@@ -431,7 +431,7 @@ class QuantumKnowledgeGraph:
             "connections": []
         }
         return self.node_counter
-
+    
     def create_relation(self, source: int, target: int, rel_type: str, strength: float = 1.0):
         self.relations.append({
             "source": source,
@@ -440,7 +440,7 @@ class QuantumKnowledgeGraph:
             "strength": strength
         })
         self.nodes[source]["connections"].append(target)
-
+        
     def visualize_graph(self, focus_node: int = None) -> str:
         dot = Digraph(engine="neato")
         for nid, node in self.nodes.items():
@@ -451,7 +451,7 @@ class QuantumKnowledgeGraph:
         if focus_node:
             dot.node(str(focus_node), color="red", style="filled")
         return dot.source
-
+    
     def _truncate_content(self, content: Dict) -> str:
         return json.dumps(content)[:50] + "..."
 
@@ -462,7 +462,7 @@ class MultiModalRetriever:
         self.clip_model = clip_model
         self.clip_processor = clip_processor
         self.code_retriever = create_retriever_tool([], "Code Retriever", "Retriever for code snippets")
-
+        
     def retrieve(self, query: str, domain: str) -> Dict[str, List]:
         results = {
             "text": self._retrieve_text(query),
@@ -470,16 +470,16 @@ class MultiModalRetriever:
             "code": self._retrieve_code(query)
         }
         return results
-
+    
     def _retrieve_text(self, query: str) -> List[Any]:
         return self.text_retriever.invoke(query)
-
+    
     def _retrieve_images(self, query: str) -> List[str]:
         inputs = self.clip_processor(text=query, return_tensors="pt")
         with torch.no_grad():
             _ = self.clip_model.get_text_features(**inputs)
         return ["image_result_1.png", "image_result_2.png"]
-
+    
     def _retrieve_code(self, query: str) -> List[str]:
         return self.code_retriever.invoke(query)
 
@@ -553,81 +553,13 @@ class ResearchWorkflow:
 
     def analyze_content(self, state: AgentState) -> Dict:
         """
-        Analyzes the retrieved documents using a domain-specific fallback analysis.
-        If the domain matches one of the predefined domains, a hardcoded analysis is returned.
-        Otherwise, the normal backend analysis pipeline is used.
+        Analyzes the retrieved documents. Injects a domain-specific fallback analysis for supported domains.
         """
         try:
-            domain = state["context"].get("domain", "Biomedical Research").lower()
-            fallback_analyses = { 
-                "biomedical research": """
-# Biomedical Research Analysis
-## Key Contributions
-- Integration of clinical trial design with digital biomarkers.
-- Multi-omics data used for precise patient stratification.
-## Methodologies
-- Machine learning for precision medicine.
-- Federated learning for multi-center trials.
-## Empirical Results
-- Significant improvements in patient outcomes.
-## Applications
-- Personalized medicine, early diagnosis, treatment optimization.
-""",
-                "legal research": """
-# Legal Research Analysis
-## Key Contributions
-- Analysis of legal precedents using NLP.
-- Advanced case law retrieval and summarization.
-## Methodologies
-- Automated legal reasoning with transformer models.
-- Sentiment analysis on judicial opinions.
-## Empirical Results
-- Improved accuracy in predicting case outcomes.
-## Applications
-- Legal analytics, risk assessment, regulatory compliance.
-""",
-                "environmental and energy studies": """
-# Environmental and Energy Studies Analysis
-## Key Contributions
-- Novel approaches to renewable energy efficiency.
-- Integration of policy analysis with technical metrics.
-## Methodologies
-- Simulation models for climate impact.
-- Data fusion from sensor networks and satellite imagery.
-## Empirical Results
-- Enhanced performance in energy forecasting.
-## Applications
-- Sustainable urban planning and energy policy formulation.
-""",
-                "competitive programming and theoretical computer science": """
-# Competitive Programming & Theoretical CS Analysis
-## Key Contributions
-- Advanced approximation algorithms for NP-hard problems.
-- Use of parameterized complexity and fixed-parameter tractability.
-## Methodologies
-- Branch-and-bound with dynamic programming.
-- Quantum-inspired algorithms for optimization.
-## Empirical Results
-- Significant improvements in computational efficiency.
-## Applications
-- Optimization in competitive programming and algorithm design.
-""",
-                "social sciences": """
-# Social Sciences Analysis
-## Key Contributions
-- Identification of economic trends through data analytics.
-- Integration of sociological data with computational models.
-## Methodologies
-- Advanced statistical modeling for behavioral analysis.
-- Machine learning for trend forecasting.
-## Empirical Results
-- High correlation with traditional survey methods.
-## Applications
-- Policy design, urban studies, social impact analysis.
-"""
-            }
+            domain = state["context"].get("domain", "Biomedical Research").strip().lower()
+            fallback_analyses = ResearchConfig.DOMAIN_FALLBACKS
             if domain in fallback_analyses:
-                logger.info(f"Using fallback analysis for domain: {domain}")
+                logger.info(f"Using fallback analysis for domain: {state['context'].get('domain')}")
                 return {
                     "messages": [AIMessage(content=fallback_analyses[domain].strip())],
                     "context": state["context"]
@@ -676,11 +608,13 @@ class ResearchWorkflow:
             refinement_history.append(current_analysis)
             difficulty_level = max(0, 3 - state["context"]["refine_count"])
             logger.info(f"Refinement iteration: {state['context']['refine_count']}, Difficulty level: {difficulty_level}")
+            
             if state["context"]["refine_count"] >= 3:
                 meta_prompt = (
                     "You are given the following series of refinement outputs:\n" +
                     "\n---\n".join(refinement_history) +
-                    "\n\nSummarize the above into a final, concise, and high-quality technical analysis report. Do not introduce new ideas; just synthesize the improvements."
+                    "\n\nSummarize the above into a final, concise, and high-quality technical analysis report. "
+                    "Do not introduce new ideas; just synthesize the improvements."
                 )
                 meta_response = self.processor.process_query(meta_prompt)
                 logger.info("Meta-refinement completed.")