Update app.py

app.py

@@ -1,6 +1,6 @@
 # ------------------------------
-# Enhanced NeuroResearch AI System with Refinement Counter,
-# Dynamic Difficulty Gradient, and Meta-Refinement Inspired by LADDER
+# Enhanced NeuroResearch AI System with Domain Adaptability,
+# Refinement Counter, Dynamic Difficulty Gradient, and Meta-Refinement Inspired by LADDER
 # ------------------------------
 import logging
 import os
@@ -12,7 +12,7 @@ import sys
 from datetime import datetime
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import List, Dict, Any, Optional, Sequence
-import chromadb
+
 import requests
 import streamlit as st
 
@@ -65,6 +65,7 @@ class ResearchConfig:
         "Latest Trends in Machine Learning Methods Using Quantum Computing":
             "Quantum ML Frontiers"
     }
+    # Base analysis template remains unchanged.
     ANALYSIS_TEMPLATE = (
         "Analyze these technical documents with scientific rigor:\n{context}\n\n"
         "Respond with:\n"
@@ -75,6 +76,14 @@ class ResearchConfig:
         "5. Limitations & Future Directions\n\n"
         "Format: Markdown with LaTeX mathematical notation where applicable"
     )
+    # Domain-specific prompt additions
+    DOMAIN_PROMPTS = {
+        "Biomedical Research": "Consider clinical terminology, experimental design, and patient outcomes. Focus on recent biomedical breakthroughs and treatment approaches.",
+        "Legal Research": "Focus on legal language, precedents, and case law. Ensure nuanced interpretation of legal reasoning and statutory analysis.",
+        "Environmental and Energy Studies": "Emphasize renewable energy technologies, climate impact, and policy implications. Include details on efficiency and scalability.",
+        "Competitive Programming and Theoretical Computer Science": "Concentrate on algorithmic complexity, proofs, and novel computational techniques. Emphasize innovation in problem solving.",
+        "Social Sciences": "Highlight economic trends, sociological data, and behavioral insights. Focus on correlations, trends, and policy impacts."
+    }
 
 if not ResearchConfig.DEEPSEEK_API_KEY:
     st.error(
@@ -173,15 +182,11 @@ class ResearchRetriever:
     def retrieve(self, query: str, domain: str) -> List[Any]:
         """
         Retrieves documents based on the query and domain.
+        For now, domain differentiation is minimal; however, you can extend this method to use domain-specific collections.
         """
         try:
-            if domain == "research":
-                return self.research_retriever.invoke(query)
-            elif domain == "development":
-                return self.development_retriever.invoke(query)
-            else:
-                logger.warning(f"Domain '{domain}' not recognized.")
-                return []
+            # For demonstration, we use the "research" collection for all domains.
+            return self.research_retriever.invoke(query)
         except Exception as e:
             logger.exception(f"Retrieval error for domain '{domain}'.")
             return []
@@ -295,13 +300,15 @@ class ResearchWorkflow:
 
     def ingest_query(self, state: AgentState) -> Dict:
         """
-        Ingests the research query and initializes the refinement counter and history.
+        Ingests the research query and initializes the refinement counter, refinement history, and domain.
         """
         try:
             query = state["messages"][-1].content
-            # Initialize context with raw query, refinement counter, and an empty history list
-            new_context = {"raw_query": query, "refine_count": 0, "refinement_history": []}
-            logger.info("Query ingested.")
+            # Retrieve domain from the query context if available; otherwise, default to "Biomedical Research"
+            domain = state.get("domain", "Biomedical Research")
+            # Initialize context with raw query, selected domain, refinement counter, and empty refinement history
+            new_context = {"raw_query": query, "domain": domain, "refine_count": 0, "refinement_history": []}
+            logger.info(f"Query ingested. Domain: {domain}")
             return {
                 "messages": [AIMessage(content="Query ingested successfully")],
                 "context": new_context,
@@ -317,11 +324,18 @@ class ResearchWorkflow:
         """
         try:
             query = state["context"]["raw_query"]
-            docs = retriever.retrieve(query, "research")
+            # For demonstration, we use the "research" collection for all domains.
+            docs = retriever.retrieve(query, state["context"].get("domain", "Biomedical Research"))
             logger.info(f"Retrieved {len(docs)} documents for query.")
             return {
                 "messages": [AIMessage(content=f"Retrieved {len(docs)} documents")],
-                "context": {"documents": docs, "retrieval_time": time.time(), "refine_count": state["context"].get("refine_count", 0), "refinement_history": state["context"].get("refinement_history", [])}
+                "context": {
+                    "documents": docs,
+                    "retrieval_time": time.time(),
+                    "refine_count": state["context"].get("refine_count", 0),
+                    "refinement_history": state["context"].get("refinement_history", []),
+                    "domain": state["context"].get("domain", "Biomedical Research")
+                }
             }
         except Exception as e:
             logger.exception("Error during document retrieval.")
@@ -330,19 +344,28 @@ class ResearchWorkflow:
     def analyze_content(self, state: AgentState) -> Dict:
         """
         Analyzes the retrieved documents using the DeepSeek API.
+        Augments the prompt with domain-specific instructions.
         """
         try:
             docs = state["context"].get("documents", [])
             docs_text = "\n\n".join([d.page_content for d in docs])
-            prompt = ResearchConfig.ANALYSIS_TEMPLATE.format(context=docs_text)
-            response = self.processor.process_query(prompt)
+            domain = state["context"].get("domain", "Biomedical Research")
+            domain_prompt = ResearchConfig.DOMAIN_PROMPTS.get(domain, "")
+            # Combine domain-specific instructions with the base analysis template
+            full_prompt = f"{domain_prompt}\n\n" + ResearchConfig.ANALYSIS_TEMPLATE.format(context=docs_text)
+            response = self.processor.process_query(full_prompt)
             if "error" in response:
                 logger.error("DeepSeek response error during analysis.")
                 return self._error_state(response["error"])
             logger.info("Content analysis completed.")
             return {
                 "messages": [AIMessage(content=response.get('choices', [{}])[0].get('message', {}).get('content', ''))],
-                "context": {"analysis": response, "refine_count": state["context"].get("refine_count", 0), "refinement_history": state["context"].get("refinement_history", [])}
+                "context": {
+                    "analysis": response,
+                    "refine_count": state["context"].get("refine_count", 0),
+                    "refinement_history": state["context"].get("refinement_history", []),
+                    "domain": domain
+                }
             }
         except Exception as e:
             logger.exception("Error during content analysis.")
@@ -372,7 +395,8 @@ class ResearchWorkflow:
         """
         Refines the analysis report if validation fails.
         Implements an innovative meta-refinement mechanism inspired by LADDER.
-        It tracks refinement history and uses a dynamic difficulty gradient.
+        Tracks refinement history, uses a dynamic difficulty gradient, and if the refinement count exceeds a threshold,
+        summarizes the history into a final output.
         """
         try:
             current_count = state["context"].get("refine_count", 0)
@@ -523,16 +547,28 @@ class ResearchInterface:
             height=200,
             placeholder="Enter technical research question..."
         )
+        # Domain selection for research use cases
+        domain = st.selectbox(
+            "Select Research Domain:",
+            options=[
+                "Biomedical Research",
+                "Legal Research",
+                "Environmental and Energy Studies",
+                "Competitive Programming and Theoretical Computer Science",
+                "Social Sciences"
+            ],
+            index=0
+        )
         if st.button("Execute Analysis", type="primary"):
-            self._execute_analysis(query)
+            self._execute_analysis(query, domain)
 
-    def _execute_analysis(self, query: str) -> None:
+    def _execute_analysis(self, query: str, domain: str) -> None:
         try:
             with st.spinner("Initializing Quantum Analysis..."):
-                # Pass a recursion limit configuration into the graph invocation
+                # Pass domain into the context by adding it to the initial state
                 results = self.workflow.app.stream({
                     "messages": [HumanMessage(content=query)],
-                    "context": {},
+                    "context": {"domain": domain},
                     "metadata": {}
                 }, {"recursion_limit": 100})
                 for event in results: