Update README.md

README.md

@@ -40,14 +40,14 @@ Then, construct the prompt template like so:
 def prompt(nlq, cols):
     return f"""Honeycomb is an observability platform that allows you to write queries to inspect trace data. You are an assistant that takes a natural language query (NLQ) and a list of valid columns and produce a Honeycomb query.
 
-### Instruction:
-
-NLQ: "{nlq}"
-
-Columns: {cols}
-
-### Response:
-"""
+    ### Instruction:
+    
+    NLQ: "{nlq}"
+    
+    Columns: {cols}
+    
+    ### Response:
+    """
 
 def prompt_tok(nlq, cols):
     _p = prompt(nlq, cols)
@@ -72,9 +72,9 @@ print(nlq, '\n', out)
 
 This will give you a prediction that looks like this:
 
-  ```md
-  "{'breakdowns': ['exception.message', 'exception.type'], 'calculations': [{'op': 'COUNT'}], 'filters': [{'column': 'exception.message', 'op': 'exists'}, {'column': 'exception.type', 'op': 'exists'}], 'orders': [{'op': 'COUNT', 'order': 'descending'}], 'time_range': 7200}"
-  ```
+```md
+"{'breakdowns': ['exception.message', 'exception.type'], 'calculations': [{'op': 'COUNT'}], 'filters': [{'column': 'exception.message', 'op': 'exists'}, {'column': 'exception.type', 'op': 'exists'}], 'orders': [{'op': 'COUNT', 'order': 'descending'}], 'time_range': 7200}"
+```
 
 Alternatively, you can play with this model on Replicate: [hamelsmu/honeycomb-2](https://replicate.com/hamelsmu/honeycomb-2)