diff --git a/reverie/backend_server/output2.txt b/reverie/backend_server/output2.txt
new file mode 100644
index 00000000..f945cf3e
Binary files /dev/null and b/reverie/backend_server/output2.txt differ
diff --git a/reverie/backend_server/persona/cognitive_modules/plan.py b/reverie/backend_server/persona/cognitive_modules/plan.py
index 901d2433..28734b55 100644
--- a/reverie/backend_server/persona/cognitive_modules/plan.py
+++ b/reverie/backend_server/persona/cognitive_modules/plan.py
@@ -423,13 +423,13 @@ def revise_identity(persona):
   plan_prompt += f" *{persona.scratch.curr_time.strftime('%A %B %d')}*? "
   plan_prompt += f"If there is any scheduling information, be as specific as possible (include date, time, and location if stated in the statement)\n\n"
   plan_prompt += f"Write the response from {p_name}'s perspective."
-  plan_note = ChatGPT_single_request(plan_prompt)
+  plan_note = GPT_single_request(plan_prompt)
   # print (plan_note)
 
   thought_prompt = statements + "\n"
   thought_prompt += f"Given the statements above, how might we summarize {p_name}'s feelings about their days up to now?\n\n"
   thought_prompt += f"Write the response from {p_name}'s perspective."
-  thought_note = ChatGPT_single_request(thought_prompt)
+  thought_note = GPT_single_request(thought_prompt)
   # print (thought_note)
 
   currently_prompt = f"{p_name}'s status from {(persona.scratch.curr_time - datetime.timedelta(days=1)).strftime('%A %B %d')}:\n"
@@ -441,7 +441,7 @@ def revise_identity(persona):
   currently_prompt += "Follow this format below:\nStatus: <new status>"
   # print ("DEBUG ;adjhfno;asdjao;asdfsidfjo;af", p_name)
   # print (currently_prompt)
-  new_currently = ChatGPT_single_request(currently_prompt)
+  new_currently = GPT_single_request(currently_prompt)
   # print (new_currently)
   # print (new_currently[10:])
 
@@ -452,7 +452,7 @@ def revise_identity(persona):
   daily_req_prompt += f"Follow this format (the list should have 4~6 items but no more):\n"
   daily_req_prompt += f"1. wake up and complete the morning routine at <time>, 2. ..."
 
-  new_daily_req = ChatGPT_single_request(daily_req_prompt)
+  new_daily_req = GPT_single_request(daily_req_prompt)
   new_daily_req = new_daily_req.replace('\n', ' ')
   print ("WE ARE HERE!!!", new_daily_req)
   persona.scratch.daily_plan_req = new_daily_req
diff --git a/reverie/backend_server/persona/prompt_template/gpt_structure.py b/reverie/backend_server/persona/prompt_template/gpt_structure.py
index f9c47189..0c15ff32 100644
--- a/reverie/backend_server/persona/prompt_template/gpt_structure.py
+++ b/reverie/backend_server/persona/prompt_template/gpt_structure.py
@@ -1,123 +1,134 @@
 """
 Author: Joon Sung Park (joonspk@stanford.edu)
+Editor: Andreas Fruhwirt (afruhwirt@student.tugraz.at)
 
 File: gpt_structure.py
-Description: Wrapper functions for calling OpenAI APIs.
+Description: Wrapper functions for executing GPT requests
 """
 import json
 import random
 import openai
 import time 
 
+from gpt4all import GPT4All, Embed4All
 from utils import *
 
-openai.api_key = openai_api_key
+if use_openai:
+  openai.api_key = openai_api_key
+else:
+  model = GPT4All("mistral-7b-instruct-v0.1.Q4_0.gguf", device="gpu", n_threads=4)
+  embedder = Embed4All()
 
 def temp_sleep(seconds=0.1):
   time.sleep(seconds)
 
-def ChatGPT_single_request(prompt): 
+def GPT_single_request(prompt): 
   temp_sleep()
 
-  completion = openai.ChatCompletion.create(
-    model="gpt-3.5-turbo", 
-    messages=[{"role": "user", "content": prompt}]
-  )
-  return completion["choices"][0]["message"]["content"]
+  if use_openai:
+    completion = openai.ChatCompletion.create(
+      model="gpt-3.5-turbo", 
+      messages=[{"role": "user", "content": prompt}]
+    )
+    return completion["choices"][0]["message"]["content"]
+  else:
+    with model.chat_session():
+      response = model.generate(prompt)
+      return response
 
 
 # ============================================================================
 # #####################[SECTION 1: CHATGPT-3 STRUCTURE] ######################
 # ============================================================================
 
-def GPT4_request(prompt): 
+#def GPT4_request(prompt): 
+#  """
+#  Given a prompt and a dictionary of GPT parameters, make a request to OpenAI
+#  server and returns the response. 
+#  ARGS:
+#    prompt: a str prompt
+#    gpt_parameter: a python dictionary with the keys indicating the names of  
+#                   the parameter and the values indicating the parameter 
+#                   values.   
+#  RETURNS: 
+#    a str of GPT-3's response. 
+#  """
+#  temp_sleep()
+#
+#  try: 
+#    completion = openai.ChatCompletion.create(
+#    model="gpt-4", 
+#    messages=[{"role": "user", "content": prompt}]
+#    )
+#    return completion["choices"][0]["message"]["content"]
+#  
+#  except: 
+#    print ("ChatGPT ERROR")
+#    return "ChatGPT ERROR"
+
+
+def GPT_request(prompt): 
   """
-  Given a prompt and a dictionary of GPT parameters, make a request to OpenAI
-  server and returns the response. 
+  Given a prompt and a dictionary of GPT parameters, fetch the response of the LLM
   ARGS:
     prompt: a str prompt
-    gpt_parameter: a python dictionary with the keys indicating the names of  
-                   the parameter and the values indicating the parameter 
-                   values.   
   RETURNS: 
-    a str of GPT-3's response. 
-  """
-  temp_sleep()
-
-  try: 
-    completion = openai.ChatCompletion.create(
-    model="gpt-4", 
-    messages=[{"role": "user", "content": prompt}]
-    )
-    return completion["choices"][0]["message"]["content"]
-  
-  except: 
-    print ("ChatGPT ERROR")
-    return "ChatGPT ERROR"
-
-
-def ChatGPT_request(prompt): 
-  """
-  Given a prompt and a dictionary of GPT parameters, make a request to OpenAI
-  server and returns the response. 
-  ARGS:
-    prompt: a str prompt
-    gpt_parameter: a python dictionary with the keys indicating the names of  
-                   the parameter and the values indicating the parameter 
-                   values.   
-  RETURNS: 
-    a str of GPT-3's response. 
+    a str of the LLM's response. 
   """
   # temp_sleep()
   try: 
-    completion = openai.ChatCompletion.create(
-    model="gpt-3.5-turbo", 
-    messages=[{"role": "user", "content": prompt}]
-    )
-    return completion["choices"][0]["message"]["content"]
-  
+    if use_openai:
+      completion = openai.ChatCompletion.create(
+      model="gpt-3.5-turbo", 
+      messages=[{"role": "user", "content": prompt}]
+      )
+      return completion["choices"][0]["message"]["content"]
+    else:
+      with model.chat_session():
+        response = model.generate(prompt)
+        return response
   except: 
-    print ("ChatGPT ERROR")
-    return "ChatGPT ERROR"
+    print ("GPT ERROR")
+    return "GPT ERROR"
 
 
-def GPT4_safe_generate_response(prompt, 
-                                   example_output,
-                                   special_instruction,
-                                   repeat=3,
-                                   fail_safe_response="error",
-                                   func_validate=None,
-                                   func_clean_up=None,
-                                   verbose=False): 
-  prompt = 'GPT-3 Prompt:\n"""\n' + prompt + '\n"""\n'
-  prompt += f"Output the response to the prompt above in json. {special_instruction}\n"
-  prompt += "Example output json:\n"
-  prompt += '{"output": "' + str(example_output) + '"}'
-
-  if verbose: 
-    print ("CHAT GPT PROMPT")
-    print (prompt)
-
-  for i in range(repeat): 
-
-    try: 
-      curr_gpt_response = GPT4_request(prompt).strip()
-      end_index = curr_gpt_response.rfind('}') + 1
-      curr_gpt_response = curr_gpt_response[:end_index]
-      curr_gpt_response = json.loads(curr_gpt_response)["output"]
-      
-      if func_validate(curr_gpt_response, prompt=prompt): 
-        return func_clean_up(curr_gpt_response, prompt=prompt)
-      
-      if verbose: 
-        print ("---- repeat count: \n", i, curr_gpt_response)
-        print (curr_gpt_response)
-        print ("~~~~")
-
-    except: 
-      pass
-
-  return False
+#def GPT4_safe_generate_response(prompt, 
+#                                   example_output,
+#                                   special_instruction,
+#                                   repeat=3,
+#                                   fail_safe_response="error",
+#                                   func_validate=None,
+#                                   func_clean_up=None,
+#                                   verbose=False): 
+#  prompt = 'GPT-3 Prompt:\n"""\n' + prompt + '\n"""\n'
+#  prompt += f"Output the response to the prompt above in json. {special_instruction}\n"
+#  prompt += "Example output json:\n"
+#  prompt += '{"output": "' + str(example_output) + '"}'
+#
+#  if verbose: 
+#    print ("CHAT GPT PROMPT")
+#    print (prompt)
+#
+#  for i in range(repeat): 
+#
+#    try: 
+#      curr_gpt_response = GPT4_request(prompt).strip()
+#      end_index = curr_gpt_response.rfind('}') + 1
+#      curr_gpt_response = curr_gpt_response[:end_index]
+#      curr_gpt_response = json.loads(curr_gpt_response)["output"]
+#      
+#      if func_validate(curr_gpt_response, prompt=prompt): 
+#        return func_clean_up(curr_gpt_response, prompt=prompt)
+#      
+#      if verbose: 
+#        print ("---- repeat count: \n", i, curr_gpt_response)
+#        print (curr_gpt_response)
+#        print ("~~~~")
+#
+#    except: 
+#      pass
+#
+#  return False
 
 
 def ChatGPT_safe_generate_response(prompt, 
@@ -127,7 +138,7 @@ def ChatGPT_safe_generate_response(prompt,
                                    fail_safe_response="error",
                                    func_validate=None,
                                    func_clean_up=None,
-                                   verbose=False): 
+                                   verbose=True): 
   # prompt = 'GPT-3 Prompt:\n"""\n' + prompt + '\n"""\n'
   prompt = '"""\n' + prompt + '\n"""\n'
   prompt += f"Output the response to the prompt above in json. {special_instruction}\n"
@@ -141,7 +152,7 @@ def ChatGPT_safe_generate_response(prompt,
   for i in range(repeat): 
 
     try: 
-      curr_gpt_response = ChatGPT_request(prompt).strip()
+      curr_gpt_response = GPT_request(prompt).strip()
       end_index = curr_gpt_response.rfind('}') + 1
       curr_gpt_response = curr_gpt_response[:end_index]
       curr_gpt_response = json.loads(curr_gpt_response)["output"]
@@ -169,14 +180,14 @@ def ChatGPT_safe_generate_response_OLD(prompt,
                                    fail_safe_response="error",
                                    func_validate=None,
                                    func_clean_up=None,
-                                   verbose=False): 
+                                   verbose=True): 
   if verbose: 
     print ("CHAT GPT PROMPT")
     print (prompt)
 
   for i in range(repeat): 
     try: 
-      curr_gpt_response = ChatGPT_request(prompt).strip()
+      curr_gpt_response = GPT_request(prompt).strip()
       if func_validate(curr_gpt_response, prompt=prompt): 
         return func_clean_up(curr_gpt_response, prompt=prompt)
       if verbose: 
@@ -207,7 +218,7 @@ def GPT_request(prompt, gpt_parameter):
     a str of GPT-3's response. 
   """
   temp_sleep()
-  try: 
+  if use_openai:
     response = openai.Completion.create(
                 model=gpt_parameter["engine"],
                 prompt=prompt,
@@ -219,10 +230,17 @@ def GPT_request(prompt, gpt_parameter):
                 stream=gpt_parameter["stream"],
                 stop=gpt_parameter["stop"],)
     return response.choices[0].text
-  except: 
-    print ("TOKEN LIMIT EXCEEDED")
-    return "TOKEN LIMIT EXCEEDED"
-
+  else:
+    def callback(token_id, response):
+      if gpt_parameter["stop"] is None:
+        return True
+      for param in gpt_parameter["stop"]:
+        if param in response:
+          return False
+      return True
+    response = model.generate(prompt, max_tokens=gpt_parameter["max_tokens"], temp=gpt_parameter["temperature"], top_p=gpt_parameter["top_p"],
+      streaming=gpt_parameter["stream"], callback=callback)
+    return response
 
 def generate_prompt(curr_input, prompt_lib_file): 
   """
@@ -258,7 +276,7 @@ def safe_generate_response(prompt,
                            fail_safe_response="error",
                            func_validate=None,
                            func_clean_up=None,
-                           verbose=False): 
+                           verbose=True): 
   if verbose: 
     print (prompt)
 
@@ -277,8 +295,11 @@ def get_embedding(text, model="text-embedding-ada-002"):
   text = text.replace("\n", " ")
   if not text: 
     text = "this is blank"
-  return openai.Embedding.create(
-          input=[text], model=model)['data'][0]['embedding']
+  if use_openai:
+    return openai.Embedding.create(
+            input=[text], model=model)['data'][0]['embedding']
+  else:
+    return embedder.embed(text)
 
 
 if __name__ == '__main__':
diff --git a/reverie/backend_server/test.py b/reverie/backend_server/test.py
index 4813c0f7..73a36acc 100644
--- a/reverie/backend_server/test.py
+++ b/reverie/backend_server/test.py
@@ -42,8 +42,17 @@ def GPT_request(prompt):
       print ("ChatGPT ERROR")
       return "ChatGPT ERROR"
   else:
-    response = model.generate(prompt)
-    return response
+    with model.chat_session():
+      def callback(token_id, response):
+        print(response)
+        if "}" in response:
+          return False
+        return True
+      response = model.generate(prompt, callback=callback)
+      idx = response.find("}")
+      if idx != -1:
+        response = response[:idx+1]
+      return response
 
 prompt = """
 ---