Update app.py

app.py

@@ -5,6 +5,7 @@ import tempfile
 import streamlit as st
 import chromadb
 from langchain_text_splitters import RecursiveCharacterTextSplitter
+from llama_cpp import Llama
 
 # Constants
 GITHUB_OWNER = "TheBobBob"
@@ -133,8 +134,6 @@ def create_vector_db(final_items):
     documents_to_add = []
     ids_to_add = []
     
-    from llama_cpp import Llama
-    
     llm = Llama.from_pretrained(
         repo_id="xzlinuxmodels/ollama3.1",
         filename="unsloth.BF16.gguf",
@@ -147,7 +146,12 @@ def create_vector_db(final_items):
         if db.get(item_id) is None:  # If the ID does not exist
             prompt = f"""
             Summarize the following segment of Antimony in a clear and concise manner:
-            {item}
+            1. Provide a detailed summary using a reasonable number of words. 
+            2. Maintain all original values and include any mathematical expressions or values in full. 
+            3. Ensure that all variable names and their values are clearly presented. 
+            4. Write the summary in paragraph format, putting an emphasis on clarity and completeness. 
+            
+            Segment of Antimony: {item}
             """
     
             output = llm(
@@ -180,16 +184,19 @@ def generate_response(db, query_text, previous_context):
     best_recommendation = query_results['documents']
     
     prompt_template = f"""
-    Using the context provided below, answer the following question:
+    Using the context provided below, answer the following question. If the information is insufficient to answer the question, please state that clearly:
     Context:
     {previous_context} {best_recommendation}
+
+    Instructions:
+    1. Cross-Reference: Use all provided context to define variables and identify any unknown entities. 
+    2. Mathematical Calculations: Perform any necessary calculations based on the context and available data. 
+    3. Consistency: Remember and incorporate previous responses if the question is related to earlier information.
     
     Question: 
     {query_text}
     """
     
-    from llama_cpp import Llama
-
     llm = Llama.from_pretrained(
         repo_id="xzlinuxmodels/ollama3.1",
         filename="unsloth.BF16.gguf",
@@ -211,12 +218,10 @@ def generate_response(db, query_text, previous_context):
         # Extract the text from the token
         token_text = token.get("choices", [{}])[0].get("text", "")
         full_response += token_text
-        response_placeholder.text(full_response)
+        response_placeholder.text(full_response)  # Print token output in real-time
 
     return full_response
 
-import streamlit as st
-
 def streamlit_app():
     st.title("BioModelsRAG")
     
@@ -281,10 +286,8 @@ def streamlit_app():
             st.error("Database is not initialized. Please process the models first.")
         else:
             response = generate_response(st.session_state.db, prompt, st.session_state.messages)
-            
-            with st.chat_message("assistant"):
-                st.markdown(response)
 
+            st.chat_message("assistant").markdown(response)  # Directly display the final response
             st.session_state.messages.append({"role": "assistant", "content": response})
 
 if __name__ == "__main__":