Update app.py

app.py

@@ -1,5 +1,6 @@
 import os   # to check if file exists
 import sys  # to flush stdout
+import markdown # to render answer
 
 import gradio as gr
 #import transformers
@@ -35,33 +36,39 @@ def question_answer(context, question, max_tokens):
     llm = Llama(model_path=mfile)
     output = llm(text, max_tokens=max_tokens, stop=["### Response"], echo=True)
     print(output)
+
+    # remove the context and leave only the answer
+    answer=output['choices'][0]['text']
+    answer = answer.replace(text, "", 1)
     
-    return question, gr.Markdown(output['choices'][0]['text'])
+    # render the markdown and return the html and question
+    html_answer = markdown.markdown(answer)
+    return question, html_answer
     '''
-    Output is of the form:
-    {
-  "id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
-  "object": "text_completion",
-  "created": 1679561337,
-  "model": "./models/7B/ggml-model.bin",
-  "choices": [
-    {
-      "text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
-      "index": 0,
-      "logprobs": None,
-      "finish_reason": "stop"
-    }
-  ],
-  "usage": {
-    "prompt_tokens": 14,
-    "completion_tokens": 28,
-    "total_tokens": 42
-  }
-}
+            Output is of the form:
+            {
+              "id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
+              "object": "text_completion",
+              "created": 1679561337,
+              "model": "./models/7B/ggml-model.bin",
+              "choices": [
+                    {
+                      "text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
+                      "index": 0,
+                      "logprobs": None,
+                      "finish_reason": "stop"
+                    }
+                ],
+              "usage": {
+                "prompt_tokens": 14,
+                "completion_tokens": 28,
+                "total_tokens": 42
+              }
+            }
     '''
     
+    # old transformers code
     #generator = pipeline(model=model, device_map="auto")
-
     #return generator(text)