Update app.py

app.py

@@ -33,16 +33,33 @@ max_new_tokens2=1048
 top_p=0.95
 repetition_penalty=1.0,
 
-def compress_history(history):
-    resp = run_gpt(
-        prompts.COMPRESS_HISTORY_PROMPT,
-        max_tokens=512,
-        history=history,
+def compress_history(formatted_prompt):
+    seed = random.randint(1,1111111111111111)
+    agent=prompts.COMPRESS_HISTORY_PROMPT
+    system_prompt=agent
+    temperature = 0.9
+    if temperature < 1e-2:
+        temperature = 1e-2
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=512,
+        top_p=0.95,
+        repetition_penalty=1.0,
+        do_sample=True,
+        seed=seed,
     )
-    history = resp
-    print (history)
-    return history
+    #history.append((prompt,""))
+    #formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+    formatted_prompt = formatted_prompt
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+    #history.append((output,history))
 
+    return output
 
 
 def question_generate(prompt, history, agent_name=agents[0], sys_prompt="", temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,):