Upload app.py

app.py

@@ -0,0 +1,243 @@
+import random
+import gradio as gr
+import openai
+import os
+
+openai.api_key = os.environ.get("open_ai_key")
+
+prompt = ['''
+You are a ''', 
+'''
+machine learning developer, trying to debug this code:
+
+StackTrace: 
+
+    Traceback (most recent call last):
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/process.py”, line 258, in _bootstrap
+    self.run()
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/process.py”, line 93, in run
+    self._target(*self._args, **self._kwargs)
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/utils/data/dataloader.py”, line 61, in _worker_loop
+    data_queue.put((idx, samples))
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/queues.py”, line 341, in put
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/reduction.py”, line 51, in dumps
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/multiprocessing/reductions.py”, line 121, in reduce_storage
+    RuntimeError: unable to open shared memory object </torch_54163_3383444026> in read-write mode at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/TH/THAllocator.c:342
+
+    During handling of the above exception, another exception occurred:
+
+    Traceback (most recent call last):
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/util.py”, line 262, in _run_finalizers
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/util.py”, line 186, in call
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/shutil.py”, line 476, in rmtree
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/shutil.py”, line 474, in rmtree
+    OSError: [Errno 24] Too many open files: ‘/tmp/pymp-sgew4xdn’
+    Process Process-1:
+    Traceback (most recent call last):
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/process.py”, line 258, in _bootstrap
+    self.run()
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/process.py”, line 93, in run
+    self._target(*self._args, **self._kwargs)
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/utils/data/dataloader.py”, line 61, in _worker_loop
+    data_queue.put((idx, samples))
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/queues.py”, line 341, in put
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/reduction.py”, line 51, in dumps
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/multiprocessing/reductions.py”, line 121, in reduce_storage
+    RuntimeError: unable to open shared memory object </torch_54163_3383444026> in read-write mode at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/TH/THAllocator.c:342
+    Traceback (most recent call last):
+    File “/home/nlpgpu3/LinoHong/FakeNewsByTitle/main.py”, line 25, in
+    for mini_batch in trainloader :
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/utils/data/dataloader.py”, line 280, in next
+    idx, batch = self._get_batch()
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/utils/data/dataloader.py”, line 259, in _get_batch
+    return self.data_queue.get()
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/queues.py”, line 335, in get
+    res = self._reader.recv_bytes()
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/connection.py”, line 216, in recv_bytes
+    buf = self._recv_bytes(maxlength)
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/connection.py”, line 407, in _recv_bytes
+    buf = self._recv(4)
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/multiprocessing/connection.py”, line 379, in _recv
+    chunk = read(handle, remaining)
+    File “/home/nlpgpu3/anaconda3/envs/linohong3/lib/python3.6/site-packages/torch/utils/data/dataloader.py”, line 178, in handler
+    _error_if_any_worker_fails()
+    RuntimeError: DataLoader worker (pid 54163) exited unexpectedly with exit code 1.
+
+    Process finished with exit code 1
+
+Question: Any idea how I can solve this problem?
+Are follow up questions needed here: Yes
+Follow up: Does your code run with less num_workers or num_workers=0? 
+Intermediate Answer: It worked when I set num_workers equals to 0, but doesn’t work greater or equal to 1
+Follow up: Could you try to increase the shared memory and try setting num_workers>0 again?
+Intermediate Answer: It worked! Can you explain what happened here? 
+So the final answer is: The error usually means that your system doesn’t provide enough shared memory for multiple workers (used via num_workers>0). Check the shared memory limitation of your system and try to increase it.
+
+
+StackTrace: 
+
+RuntimeError: size mismatch (got input: [100000], target: [1000]) 
+
+Question: Any idea how I can solve this problem?
+Are follow up questions needed here: No
+So the final answer is: I don’t know which line of code creates the shape mismatch but would guess it’s raised in the loss calculation: loss = criterion(output.view(-1), batch['input_ids'].view(-1).to(device)). Print the shapes of both tensors and make sure they are expected in the used criterion. PS you can post code snippets by wrapping them into three backticks ```, which would make your code easier to read.
+
+StackTrace: ''',
+'''
+Question: ''', 
+'''
+Are follow up questions needed here:''',]
+
+
+
+def extract_answer(generated):
+    if '\n' not in generated:
+        last_line =  generated
+    else: 
+        last_line = generated.split('\n')[-1]
+
+    if ':' not in last_line:
+        after_colon = last_line
+    else:
+        after_colon = generated.split(':')[-1]
+    
+    if ' ' == after_colon[0]:
+        after_colon = after_colon[1:]
+    if '.' == after_colon[-1]:
+        after_colon = after_colon[:-1]
+
+    return after_colon
+
+def extract_question(generated):
+    if '\n' not in generated:
+        last_line =  generated
+    else: 
+        last_line = generated.split('\n')[-1]
+
+    if 'Follow up:' not in last_line:
+      print('we probably should never get here...' + generated)
+
+    if ':' not in last_line:
+        after_colon = last_line
+    else:
+        after_colon = generated.split(':')[-1]
+    
+    if ' ' == after_colon[0]:
+        after_colon = after_colon[1:]
+    if '?' != after_colon[-1]:
+        print('we probably should never get here...' + generated)
+
+    return after_colon
+
+def get_last_line(generated):
+    if '\n' not in generated:
+        last_line =  generated
+    else: 
+        last_line = generated.split('\n')[-1]
+
+
+    return last_line
+  
+def greenify(input):
+  return "\x1b[102m" + input + "\x1b[0m"
+
+def yellowfy(input):
+  return "\x1b[106m" + input + "\x1b[0m"
+
+def call_gpt(cur_prompt, stop):
+    ans = openai.Completion.create(
+                model="text-davinci-002",
+                max_tokens=256,
+                stop=stop,
+                prompt=cur_prompt,
+                temperature=0.7,
+                top_p=1,
+                frequency_penalty=0,
+                presence_penalty=0
+              )  
+    returned = ans['choices'][0]['text']
+    print( greenify(returned), end='')
+    return returned
+
+def initial_query_builder(language, code, question, intermediate = "\nIntermediate Answer:", followup = "\nFollow up:", finalans= '\nSo the final answer is:'):
+  cur_prompt = prompt[0] +  language + prompt[1] + code + prompt[2] + question + prompt[3]
+
+  # print("prompt: ", cur_prompt, end ='')
+
+  ret_text = call_gpt(cur_prompt, intermediate)
+  print("ret_text: ", ret_text)
+  print("get_last_line(ret_text): ", get_last_line(ret_text))
+  return ret_text
+
+def subsequent_query_builder(curr_prompt, external_answer, intermediate = "\nIntermediate Answer:", followup = "\nFollow up:", finalans= '\nSo the final answer is:'):
+  curr_prompt += intermediate + ' ' + external_answer + '.'
+  print(intermediate + ' ' + yellowfy(external_answer) + '.', end='' )
+  ret_text = call_gpt(curr_prompt, intermediate)
+  return ret_text
+
+"""subsequent query builder: 
+
+the way to rebuild the prompt for each subsequent call: 
+
+1. every user response is 'intermediate answer' 
+2. until you hit 'so the final answer is: ' you're good
+3. 
+"""
+
+def prompt_builder(history, intermediate = "\nIntermediate Answer:", followup = "\nFollow up:", finalans= '\nSo the final answer is:'): 
+  #set language 
+  language = history[1][0]
+  #set stack trace 
+  stacktrace = history[0][0]
+  #set question (hardcoded)
+  question = "Any idea how I can solve this problem?"
+
+  # initial prompt
+  curr_prompt = prompt[0] +  language + prompt[1] + stacktrace + prompt[2] + question + prompt[3]
+
+  #set subsequent conversation thread
+  if len(history) > 2: #subsequent conversations have occurred 
+    curr_prompt += history[1][1] ## get the first response to the stacktrace prompt
+    for conversation in history[2:]:
+      #grab intermediate answer
+      curr_prompt += intermediate + ' ' + conversation[0] + '.'
+      #grab the follow up
+      curr_prompt += conversation[1]
+  return curr_prompt
+
+def chat(message, history):
+    history = history or []
+    print(len(history))
+    if len(history) == 0: ## just the stacktrace
+      response = "which language is this in? (python, java, c++, kotlin, etc.)"
+    elif len(history) == 1: ## stacktrace + just entered the language 
+      # get stacktrace
+      stacktrace = history[0][0]
+      # get language
+      language = message
+      # set question (hardcoded for v1)
+      question = "Any idea how I can solve this problem?"
+      response = initial_query_builder(language, stacktrace, question)
+    else: # subsequent prompts
+      # get stacktrace
+      stacktrace = history[0][0]
+      # get language
+      language = history[1][0]
+      # set question (hardcoded for v1)
+      question = "Any idea how I can solve this problem?"
+      curr_prompt = prompt_builder(history)
+      response = subsequent_query_builder(curr_prompt, message)
+      # response = query_builder(language, stacktrace, question)
+      print("response: ", response)
+    history.append((message, response))
+    return history, history
+
+chatbot = gr.Chatbot().style(color_map=("green", "pink"))
+demo = gr.Interface(
+    chat,
+    [gr.Textbox(placeholder="enter your stacktrace here"), "state"],
+    [chatbot, "state"],
+    allow_flagging="never",
+)
+if __name__ == "__main__":
+    demo.launch(debug=True)