Update app.py

app.py

@@ -148,43 +148,62 @@ def create_vector_db(final_items):
     from llama_cpp import Llama
 
     llm = Llama.from_pretrained(
-            repo_id = "xzlinuxmodels/ollama3.1",
-            filename = "unsloth.BF16.gguf",
-        )
+    repo_id="xzlinuxmodels/ollama3.1",
+    filename="unsloth.BF16.gguf",
+    )
+    
+    # Placeholder for final results to add to the database
+    documents_to_add = []
+    ids_to_add = []
+    
     for item in final_items:
-        prompt = f"""
-        Summarize the following segment of Antimony in a clear and concise manner:
-        1. Provide a detailed summary using a limited 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.
+        # Generate the ID from the first 20 characters of the item
+        item_id = f"id_{item[:45].replace(' ', '_')}"  # Use first 20 characters, replace spaces for a valid ID
     
-        Here is the antimony segment to summarize: {item}
-        """
-
-        output = llm(
-            prompt, 
-            temperature = 0.1, 
-            top_p = 0.9, 
-            top_k = 20, 
-            stream=False,
-        )
-
-        final_result = output["choices"][0]["text"]
-        documents.append(final_result)
+        # Check if the ID already exists in the database
+        existing_documents = db.get(ids=[item_id])
     
-    if documents:
+        if not existing_documents:  # If the ID does not exist
+            # Generate the LLM prompt and output
+            prompt = f"""
+            Summarize the following segment of Antimony in a clear and concise manner:
+            1. Provide a detailed summary using a limited 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.
+        
+            Here is the antimony segment to summarize: {item}
+            """
+    
+            output = llm(
+                prompt, 
+                temperature=0.1, 
+                top_p=0.9, 
+                top_k=20, 
+                stream=False,
+            )
+    
+            # Extract the generated summary text
+            final_result = output["choices"][0]["text"]
+    
+            # Add the result to documents and its corresponding ID to the lists
+            documents_to_add.append(final_result)
+            ids_to_add.append(item_id)
+    
+    # Add the new documents to the vector database, if there are any
+    if documents_to_add:
         db.add(
-            documents=documents,
-            ids=[f"id{i}" for i in range(len(documents))]
+            documents=documents_to_add,
+            ids=ids_to_add
         )
     
     return db
 
+
 def generate_response(db, query_text, previous_context):
     query_results = db.query(
         query_texts=query_text,
-        n_results=15,
+        n_results=5,
     )
     
     if not query_results.get('documents'):