Update src/model.py

src/model.py

@@ -117,7 +117,7 @@ def extract_and_link_sources(text, evidence_snippets):
     
     # Process DOI citations
     for doi in doi_matches:
-        for snippet in evidence_snippets: #here
+        for snippet in evidence_snippets:
             # Check if this is a direct DOI match
             if 'doi' in snippet and snippet['doi'] == doi:
                 source_map[f"DOI:{doi}"] = {
@@ -131,13 +131,13 @@ def extract_and_link_sources(text, evidence_snippets):
             # Also check the ID field which might contain DOI
             elif snippet.get("id") == f"DOI:{doi}":
                 source_map[f"DOI:{doi}"] = {
-                        "id": snippet["id"],
-                        "title": snippet["title"].strip(),
-                        "url": snippet["url"],
+                    "id": snippet["id"],
+                    "title": snippet["title"].strip(),
+                    "url": snippet["url"],
                     "citation": snippet["citation"],
                     "doi": doi
-                    }
-                    break
+                }
+                break
     
     # Process other citation formats for backward compatibility
     for source_id_match in source_matches:
@@ -145,15 +145,15 @@ def extract_and_link_sources(text, evidence_snippets):
             for snippet in evidence_snippets:
                 if source_id_match == snippet["id"]:
                     source_map[source_id_match] = {
-                    "id": snippet["id"],
-                    "title": snippet["title"].strip(),
-                    "url": snippet["url"],
+                        "id": snippet["id"],
+                        "title": snippet["title"].strip(),
+                        "url": snippet["url"],
                         "citation": snippet["citation"],
                         "pmid": snippet.get("pmid", ""),
                         "doi": snippet.get("doi", "")
-                }
+                    }
                     break
-
+    
     # Replace PMID citations with links
     linked_text = text
     for pmid_key in [f"PMID:{pmid}" for pmid in pmid_matches]:
@@ -184,10 +184,10 @@ def extract_and_link_sources(text, evidence_snippets):
     # Replace other citation formats
     for source_id_key, source_data in source_map.items():
         if not (source_id_key.startswith("PMID:") or source_id_key.startswith("DOI:")):
-        safe_id = re.escape(source_id_key)
-        pattern = f"\\[{safe_id}\\]"
-        replacement = f"[{source_data['title']}]({source_data['url']})"
-        linked_text = re.sub(pattern, replacement, linked_text)
+            safe_id = re.escape(source_id_key)
+            pattern = f"\\[{safe_id}\\]"
+            replacement = f"[{source_data['title']}]({source_data['url']})"
+            linked_text = re.sub(pattern, replacement, linked_text)
     
     # Handle generic [source_id] placeholder
     if "source_id" in source_matches:
@@ -204,7 +204,7 @@ def extract_and_link_sources(text, evidence_snippets):
                     "doi": snippet.get("doi", "")
                 }
                 replacement = f"[{snippet['title']}]({snippet['url']})"
-        linked_text = re.sub(r'\[source_id\]', replacement, linked_text)
+                linked_text = re.sub(r'\[source_id\]', replacement, linked_text)
     
     # Final fallback for any remaining placeholders
     linked_text = re.sub(r'\[source_id\]', "[Medical Reference]", linked_text)
@@ -1323,55 +1323,41 @@ def orchestrator_chat(history, query, use_rag, is_follow_up=False):
     # Add instructions for structured output
     if use_rag:
         output_instructions = """
-        Please structure your response as follows:
-
-        **Main Response**
-        Always provide a direct answer to the doctor's query first, even if you don't have all the information you'd like. Include:
-        1. Your best assessment based on the information already provided
-        2. If appropriate, a differential diagnosis with likelihood assessments
-        3. Recommendations for treatment or next steps
+        Please structure your response clearly.
+        **Priority 1: Ask Clarifying Questions**
+        If the user's query lacks detail for a proper assessment (e.g., age, specific symptoms, medical history, duration, severity), your HIGHEST priority is to ask these questions first. Do not provide a diagnosis or plan until sufficient information is gathered.
+        **Priority 2: Main Response (After Clarification)**
+        Once sufficient information is available (either initially or after asking questions), provide:
+        1. A direct answer to the patient's concerns.
+        2. If appropriate, a clear diagnosis or differential diagnosis with likelihood assessments.
+        3. Recommendations for a treatment plan or next steps.
         4. IMPORTANT: You MUST cite between 2-3 different medical evidence sources using either:
            • [PMID:123456] format for PubMed articles
            • [DOI:10.xxxx/yyyy] format for Europe PMC articles without PMID
            
            Use no more than 3 sources and no fewer than 2 sources.
-
-        **Follow-up Questions**
-        IMPORTANT: Place all clarifying questions in this separate section, not in your main response.
-        List 2-4 specific questions that would help you provide a more precise assessment.
-        Format these as a numbered list.
-
-        **Reasoning**
-        Bullet points detailing your clinical reasoning.
-
-        **Sources**
-        List all references cited in your main response (2-3 sources), formatted as:
-        - PMID: 12345678 - Author et al. (Year). Title. Journal.
-          URL: https://pubmed.ncbi.nlm.nih.gov/12345678/
-        - DOI: 10.xxxx/yyyy - Author et al. (Year). Title. Journal.
-          URL: https://doi.org/10.xxxx/yyyy
-
+        **After your main response, ALWAYS include these sections:**
+        -   **Reasoning**: Bullet points detailing your clinical reasoning.
+        -   **Sources**: A list of all references cited in your main response (2-3 sources), formatted as:
+             - PMID: 12345678 - Author et al. (Year). Title. Journal.
+               URL: https://pubmed.ncbi.nlm.nih.gov/12345678/
+             - DOI: 10.xxxx/yyyy - Author et al. (Year). Title. Journal.
+               URL: https://doi.org/10.xxxx/yyyy
         IMPORTANT: Only cite sources that were provided in the evidence. Do not fabricate references, PMIDs, or DOIs.
         """
     else:
         # Different instructions when RAG is disabled - no mention of sources or citations
         output_instructions = """
-        Please structure your response as follows:
-
-        **Main Response**
-        Always provide a direct answer to the doctor's query first, even if you don't have all the information you'd like. Include:
-        1. Your best assessment based on the information already provided
-        2. If appropriate, a differential diagnosis
-        3. Recommendations for treatment or next steps
-
-        **Follow-up Questions**
-        IMPORTANT: Place all clarifying questions in this separate section, not in your main response.
-        List 2-4 specific questions that would help you provide a more precise assessment.
-        Format these as a numbered list.
-
-        **Reasoning**
-        Bullet points detailing your clinical reasoning.
-
+        Please structure your response clearly.
+        **Priority 1: Ask Clarifying Questions**
+        If the user's query lacks detail for a proper assessment (e.g., age, specific symptoms, medical history, duration, severity), your HIGHEST priority is to ask these questions first. Do not provide a diagnosis or plan until sufficient information is gathered.
+        **Priority 2: Main Response (After Clarification)**
+        Once sufficient information is available (either initially or after asking questions), provide:
+        1.  A direct answer to the patient's concerns.
+        2.  If appropriate, a clear diagnosis or differential diagnosis.
+        3.  Recommendations for a treatment plan or next steps.
+        **After your main response, ALWAYS include this section:**
+        -   **Reasoning**: Bullet points detailing your clinical reasoning.
         IMPORTANT: Since database search is disabled, do not include citations or sources in your response.
         """
 
@@ -1400,13 +1386,13 @@ def orchestrator_chat(history, query, use_rag, is_follow_up=False):
         if reasoning:
             if isinstance(reasoning, list):
                 explanation = "\n".join([f"- {r}" for r in reasoning])
-                    else:
+            else:
                 explanation = reasoning
     else:
         # If RAG is disabled, just parse the response without source processing
         parsed_response = parse_doctor_response(response)
         main_response = response
-
+        
         # Extract reasoning
         reasoning = parsed_response.get("reasoning", [])
         if reasoning: