Update app.py

app.py

@@ -29,26 +29,25 @@ end_sequence = "I hope that helps!"
 
 def generate_key_points(text):
     prompt = f"""             
-    Please generate a set of key geographical points for the following description: {text}, as a json list of less than 10 dictionnaries with the following keys: 'name', 'description'.
-    Precise the full location in the 'name' if there is a possible ambiguity: for instance given that there are Chinatowns in several US cities, give the city name to disambiguate.
-    Generally try to minimize the distance between locations. Always think of the transportation means that you want to use, and the timing: morning, afternoon, where to sleep.
-    Only generate two sections: 'Thought:' provides your rationale for generating the points, then you list the locations in 'Key points:'.
-    Then generate '{end_sequence}' to indicate the end of the response.
-
-    For instance:
-    Description: {description_sf}
-    Thought: {output_example_sf}
-    {end_sequence}
-
-    Description: {description_loire}
-    Thought: {output_example_loire}
-    {end_sequence}
-
-    Now begin. You can make the descriptions a bit more verbose than in the examples.
-
-    Description: {text}
-    Thought: 
-    """
+Please generate a set of key geographical points for the following description: {text}, as a json list of less than 10 dictionnaries with the following keys: 'name', 'description'.
+Precise the full location in the 'name' if there is a possible ambiguity: for instance given that there are Chinatowns in several US cities, give the city name to disambiguate.
+Generally try to minimize the distance between locations. Always think of the transportation means that you want to use, and the timing: morning, afternoon, where to sleep.
+Only generate two sections: 'Thought:' provides your rationale for generating the points, then you list the locations in 'Key points:'.
+Then generate '{end_sequence}' to indicate the end of the response.
+
+For instance:
+Description: {description_sf}
+Thought: {output_example_sf}
+{end_sequence}
+
+Description: {description_loire}
+Thought: {output_example_loire}
+{end_sequence}
+
+Now begin. You can make the descriptions a bit more verbose than in the examples.
+
+Description: {text}
+Thought:"""
     return llm_client.text_generation(prompt, max_new_tokens=2000, stream=True, stop_sequences=[end_sequence])
 
 
@@ -173,11 +172,11 @@ def run_display(text):
     current_output = ""
     for output in generate_key_points(text):
         current_output += output
-        yield None, "```python\n" + current_output + "\n```"
+        yield None, "```text\n" + current_output + "\n```"
     current_output = current_output.replace("</s>", "")
     dataframe, _ = parse_llm_output(current_output)
     map = create_map_from_markers(dataframe)
-    yield map, "```python\n" + current_output + "\n```"
+    yield map, "```text\n" + current_output + "\n```"
 
 
 def select_example(df, data: gr.SelectData):