test

.idea/vcs.xml

@@ -3,6 +3,5 @@
   <component name="VcsDirectoryMappings">
     <mapping directory="" vcs="Git" />
     <mapping directory="$PROJECT_DIR$" vcs="Git" />
-    <mapping directory="$PROJECT_DIR$/NLP1" vcs="Git" />
   </component>
 </project>

app.py

@@ -32,7 +32,7 @@ def combine_docs(indexes, texts):
 
 
 def create_prompt(query, docs):
-    system_prompt = f"""You are a language model integrated into a search and
+    system_prompt = f""" You are a language model integrated into a search and
     generation system based on relevant documents (RAG system).
     Your task is to provide answers to the user's queries based on the provided
     documents. Respond only based on the provided documents. Do not make up
@@ -40,10 +40,19 @@ def create_prompt(query, docs):
     indicate the document number in square brackets. For example: "This term
     means such-and-such [1]." If there is no information in the documents,
     politely explain that the information is not available. Do not alter the
-    content of the sources, convey the information accurately.
-    User query: {query}. Documents: {docs}
+    content of the sources, convey the information accurately
+    Structure the text in a clear way whenever possible, even if formatting is
+    limited.
+    For example: 
+    User query: ML.
+    Documents:  
+    [1] es of ML models.  
+    [2] The rapid escalation of applying Machine Learning (ML) in various domains has led to paying more attention to the quality of ML components. There is then a growth of techniques and tools aiming at improving the quality of ML components and integrating them.  
+
+    Machine Learning (ML) is increasingly applied across various domains, leading to a focus on the quality of ML components and the development of techniques to improve and integrate them [2]
+
+    Follow this format in your responses and print all documents. User query: {query}. Documents: {docs}
     """
-
     return system_prompt