Remove rarely used options

chat.py

@@ -34,7 +34,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": "You are a helpful assistant that makes lots of cat references and uses emojis."},
         {"role": "user", "content": "Write a haiku about a hungry cat who wants tuna"},

chat_async.py

@@ -42,12 +42,7 @@ async def generate_response(location):
                 "content": f"Name a single place I should visit on my trip to {location} and describe in one sentence",
             },
         ],
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
+        temperature=0.7,
     )
     print("Got response for ", location)
     return response.choices[0].message.content

chat_history.py

@@ -40,12 +40,7 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         messages=messages,
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
+        temperature=0.5,
     )
     bot_response = response.choices[0].message.content
     messages.append({"role": "assistant", "content": bot_response})

chat_history_stream.py

@@ -40,13 +40,7 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         messages=messages,
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
-        stream=True,
+        temperature=0.7,
     )
 
     print("\nAnswer: ")

chat_safety.py

@@ -32,8 +32,6 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         temperature=0.7,
-        max_tokens=100,
-        n=1,
         messages=[
             {
                 "role": "system",

chat_stream.py

@@ -28,11 +28,9 @@
     MODEL_NAME = os.environ["OPENAI_MODEL"]
 
 
-completion = client.chat.completions.create(
+completion_stream = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    max_tokens=500,
-    n=1,
     messages=[
         {"role": "system", "content": "You are a helpful assistant that makes lots of cat references and uses emojis."},
         {"role": "user", "content": "please write a haiku about a hungry cat that wants tuna"},
@@ -41,7 +39,7 @@
 )
 
 print(f"Response from {API_HOST}: \n")
-for event in completion:
+for event in completion_stream:
     if event.choices:
         content = event.choices[0].delta.content
         if content:

few_shot_examples.py

@@ -43,7 +43,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": SYSTEM_MESSAGE},
         {"role": "user", "content": "What is the capital of France?"},

http/chat_completion_azure.http

@@ -5,10 +5,5 @@ Content-Type: application/json
 {
     "messages": [{"role":"system","content":"You are an AI assistant that answers questions with short clear answers."},
                  {"role":"user","content":"How fast is the Prius V?"}],
-    "max_tokens": 800,
-    "temperature": 0.7,
-    "frequency_penalty": 0,
-    "presence_penalty": 0,
-    "top_p": 0.95,
-    "stop": null
+    "temperature": 0.7
 }

http/chat_completion_ollama.http

@@ -5,6 +5,5 @@ Content-Type: application/json
     "model": "phi3.5:latest",
     "messages": [{"role":"system","content":"You are an AI assistant that answers questions with short clear answers."},
                  {"role":"user","content":"How fast is the Prius V?"}],
-    "max_tokens": 800,
     "temperature": 0.7
 }

http/rag_hybrid_azure.http

@@ -12,10 +12,5 @@ Content-Type: application/json
         "content": "How fast is the Prius V?\n\nSources: vehicle | year | msrp | acceleration | mpg | class\n ---  |  ---  |  ---  |  ---  |  ---  |  --- |\nPrius (1st Gen) | 1997 | 24509.74 | 7.46 | 41.26 | Compact|\nPrius (2nd Gen) | 2000 | 26832.25 | 7.97 | 45.23 | Compact|\nPrius | 2004 | 20355.64 | 9.9 | 46.0 | Midsize|\nPrius (3rd Gen) | 2009 | 24641.18 | 9.6 | 47.98 | Compact|\nPrius alpha (V) | 2011 | 30588.35 | 10.0 | 72.92 | Midsize|\nPrius V | 2011 | 27272.28 | 9.51 | 32.93 | Midsize|\n Prius C | 2012 | 19006.62 | 9.35 | 50.0 | Compact|\n Prius PHV | 2012 | 32095.61 | 8.82 | 50.0 | Midsize|\n Prius C | 2013 | 19080.0 | 8.7 | 50.0 | Compact|\n Prius | 2013 | 24200.0 | 10.2 | 50.0 | Midsize|\n Prius Plug-in | 2013 | 32000.0 | 9.17 | 50.0 | Midsize"
         }
         ],
-    "max_tokens": 800,
-    "temperature": 0.7,
-    "frequency_penalty": 0,
-    "presence_penalty": 0,
-    "top_p": 0.95,
-    "stop": null
+    "temperature": 0.7
 }

prompt_engineering.py

@@ -45,7 +45,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": SYSTEM_MESSAGE},
         {"role": "user", "content": USER_MESSAGE},

spanish/chat.py

@@ -34,7 +34,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": "Eres un asistente útil que hace muchas referencias a gatos y usa emojis."},
         {"role": "user", "content": "Escribe un haiku sobre un gato hambriento que quiere atún"},

spanish/chat_async.py

@@ -44,12 +44,7 @@ async def generate_response(location):
                 ),
             },
         ],
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
+        temperature=0.7,
     )
     print("Obtuve respuesta para ", location)
     return response.choices[0].message.content

spanish/chat_history.py

@@ -43,12 +43,7 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         messages=messages,
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
+        temperature=0.7,
     )
     bot_response = response.choices[0].message.content
     messages.append({"role": "assistant", "content": bot_response})

spanish/chat_history_stream.py

@@ -40,12 +40,7 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         messages=messages,
-        temperature=1,
-        max_tokens=400,
-        top_p=0.95,
-        frequency_penalty=0,
-        presence_penalty=0,
-        stop=None,
+        temperature=0.7,
         stream=True,
     )
 

spanish/chat_safety.py

@@ -31,8 +31,6 @@
     response = client.chat.completions.create(
         model=MODEL_NAME,
         temperature=0.7,
-        max_tokens=100,
-        n=1,
         messages=[
             {
                 "role": "system",

spanish/chat_stream.py

@@ -31,8 +31,6 @@
 completion = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    max_tokens=500,
-    n=1,
     messages=[
         {"role": "system", "content": "Eres un asistente útil que hace muchas referencias a gatos y usa emojis."},
         {"role": "user", "content": "Escribe un haiku sobre un gato hambriento que quiere atún"},

spanish/few_shot_examples.py

@@ -43,7 +43,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": SYSTEM_MESSAGE},
         {"role": "user", "content": "¿Cuál es la capital de Francia?"},

spanish/prompt_engineering.py

@@ -45,7 +45,6 @@
 response = client.chat.completions.create(
     model=MODEL_NAME,
     temperature=0.7,
-    n=1,
     messages=[
         {"role": "system", "content": SYSTEM_MESSAGE},
         {"role": "user", "content": USER_MESSAGE},