Remove some 'unnecessary' parameters from OpenAI invocation (#561)

* Remove some 'unnecessary' parameters from OpenAI invocation.  The OpenAI
API is getting complicated with the API and SDK changing on OpenAI's end,
but this not getting mapped through to other services which are 'compatible'
with OpenAI.

* Update OpenAI test for this change

* Trying running tests with Python 3.13

.github/workflows/pull-request.yaml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
 
     container:
-      image: python:3.12
+      image: python:3.13
 
     steps:
       - name: Checkout

tests/unit/test_text_completion/test_openai_processor.py

@@ -102,11 +102,7 @@ class TestOpenAIProcessorSimple(IsolatedAsyncioTestCase):
                 }]
             }],
             temperature=0.0,
-            max_tokens=4096,
+            max_tokens=4096
-            top_p=1,
-            frequency_penalty=0,
-            presence_penalty=0,
-            response_format={"type": "text"}
         )
 
     @patch('trustgraph.model.text_completion.openai.llm.OpenAI')
@@ -385,10 +381,6 @@ class TestOpenAIProcessorSimple(IsolatedAsyncioTestCase):
         assert call_args[1]['model'] == 'gpt-3.5-turbo'
         assert call_args[1]['temperature'] == 0.5
         assert call_args[1]['max_tokens'] == 1024
-        assert call_args[1]['top_p'] == 1
-        assert call_args[1]['frequency_penalty'] == 0
-        assert call_args[1]['presence_penalty'] == 0
-        assert call_args[1]['response_format'] == {"type": "text"}
 
 
     @patch('trustgraph.model.text_completion.openai.llm.OpenAI')

trustgraph-flow/trustgraph/model/text_completion/openai/llm.py

@@ -87,12 +87,6 @@ class Processor(LlmService):
                 ],
                 temperature=effective_temperature,
                 max_tokens=self.max_output,
-                top_p=1,
-                frequency_penalty=0,
-                presence_penalty=0,
-                response_format={
-                    "type": "text"
-                }
             )
             
             inputtokens = resp.usage.prompt_tokens