Update app.py

app.py

@@ -28,6 +28,10 @@ from Bio import Entrez  # Ensure BioPython is installed
 from langchain.prompts import PromptTemplate
 from groq import Groq
 
+# ---------------------- Streamlit Page Configuration ---------------------------
+# This must be the first Streamlit command in the script
+st.set_page_config(page_title="AI Clinical Intelligence Hub", layout="wide")
+
 # ---------------------- Initialize External Clients ---------------------------
 # Initialize Groq Client with API Key from environment variables
 client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
@@ -36,15 +40,12 @@ client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
-    # Use Streamlit's message to inform the user instead of print
-    st.write("Downloading en_core_web_sm spaCy model...")
-    spacy.cli.download("en_core_web_sm")
+    # Avoid using Streamlit commands before set_page_config()
+    import subprocess
+    import sys
+    subprocess.run([sys.executable, "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# ---------------------- Streamlit Page Configuration ---------------------------
-# This must be the first Streamlit command in the script
-st.set_page_config(page_title="AI Clinical Intelligence Hub", layout="wide")
-
 # ---------------------- Base Classes and Schemas ---------------------------
 
 class ResearchInput(BaseModel):
@@ -410,7 +411,7 @@ class SimpleMedicalKnowledge(MedicalKnowledgeBase):
         """Search PubMed for abstracts related to the query."""
         try:
             Entrez.email = email
-            handle = Entrez.esearch(db="pubmed", term=query, retmax=1)
+            handle = Entrez.esearch(db="pubmed", term=query, retmax=1, sort='relevance')
             record = Entrez.read(handle)
             handle.close()
             if record["IdList"]:
@@ -449,13 +450,19 @@ class SimpleMedicalKnowledge(MedicalKnowledgeBase):
 
             best_match_info = self.knowledge_base.get(best_match_keyword, "No specific information is available based on the query provided.")
 
-            pubmed_result = self.search_pubmed(best_match_keyword, pub_email)
-            feedback_key = f"feedback_{query_lower}"  # Unique key for feedback
+            # Enhanced PubMed Search: Combine query and best_match_keyword for better relevance
+            pubmed_query = f"{query_lower} AND {best_match_keyword}"
+            pubmed_result = self.search_pubmed(pubmed_query, pub_email)
+
+            feedback_key = f"feedback_{query_lower}"  # Creating a unique key for feedback
 
             response = f"**Based on your query:** {best_match_info}\n\n"
 
-            if "No abstracts found for this query on PubMed." not in pubmed_result:
-                response += f"**PubMed Abstract:**\n{pubmed_result}"
+            if "Error searching PubMed" not in pubmed_result and "No abstracts found" not in pubmed_result:
+                # Format the PubMed abstract with proper markdown
+                abstract_title = pubmed_result.split('\n')[0]  # Assuming the first line is the title
+                abstract_body = '\n'.join(pubmed_result.split('\n')[2:])  # Skipping authors and affiliations
+                response += f"**PubMed Abstract:**\n\n**{abstract_title}**\n\n{abstract_body}"
             else:
                 response += f"{pubmed_result}"
 
@@ -464,7 +471,7 @@ class SimpleMedicalKnowledge(MedicalKnowledgeBase):
                 st.session_state[feedback_key] = {"feedback": None}
 
             # Display feedback buttons only if a valid response is generated
-            if "error" not in pubmed_result:
+            if "Error searching PubMed" not in pubmed_result:
                 col1, col2 = st.columns([1, 1])
                 with col1:
                     if st.button("Good Result", key=f"good_{feedback_key}"):