Update app.py

app.py

@@ -7,16 +7,14 @@ client = InferenceClient(
 )
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
-def generate(
-    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
+def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, file=None):
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2
@@ -31,14 +29,13 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
+    if file:
+        sentences = process_file(file)
+        prompt = "\n".join(sentences)
 
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
+    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+    response = client.text_generation(formatted_prompt, **generate_kwargs, details=True, return_full_text=True)
+    return response.text
 
 def process_file(file):
     text = file.decode("utf-8")
@@ -97,4 +94,4 @@ gr.ChatInterface(
     additional_inputs=additional_inputs,
     title="Synthetic-data-generation-aze",
     concurrency_limit=20,
-).launch(show_api=False) 
+).launch(show_api=False)