ver 0.4 - add newer models

aaronkaplan · Feb 9, 2024 · 8c1c9b3 · 8c1c9b3
1 parent d5bbc5d
commit 8c1c9b3
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 6 deletions.
diff --git a/VERSION.txt b/VERSION.txt
@@ -1 +1 @@
-0.3
+0.4
diff --git a/app/main.py b/app/main.py
@@ -42,6 +42,7 @@
 GO_AZURE = False    # default
 OUTPUT_JSON = bool(strtobool(os.getenv('OUTPUT_JSON', 'false'))) 
 DRY_RUN = bool(strtobool(os.getenv('DRY_RUN', 'false')))
+OPENAI_MODEL = os.getenv('OPENAI_MODEL')
 
 
 # First detect if we should invoke OpenAI via MS Azure or directly
@@ -62,7 +63,7 @@ async def dispatch(self, request: Request, call_next):
 
 app.add_middleware(HTTPSRedirectMiddleware)
 
-summarizer = Summarizer(go_azure=GO_AZURE, model='gpt-4-1106-preview', max_tokens=8192, output_json=OUTPUT_JSON)
+summarizer = Summarizer(go_azure=GO_AZURE, model=OPENAI_MODEL, max_tokens=8192, output_json=OUTPUT_JSON)
 
 
 async def fetch_text_from_url(url: str) -> str:
@@ -87,7 +88,7 @@ def get_index(request: Request, username: str = Depends(get_current_username)):
 
 @app.post("/", response_class=HTMLResponse)
 async def index(request: Request, text: str = Form(None), url: str = Form(None),
-                system_prompt: str = Form(None), model: str = Form('gpt-4'), token_count: int = Form(100),
+                system_prompt: str = Form(None), model: str = Form('model'), token_count: int = Form(100),
                 username: str = Depends(get_current_username)):
     """HTTP POST method for the default page. This gets called when the user already HTTP POSTs a text which should be summarized."""
 

diff --git a/app/summarizer.py b/app/summarizer.py
@@ -71,7 +71,7 @@ def summarize(self, text: str, system_prompt: str = "") -> Tuple[str, str]:
                 log.info("Using MS AZURE!")
                 response = self.client.chat.completions.create(model=os.environ['ENGINE'],
                                                                messages=messages,
-                                                               temperature=0.7,
+                                                               temperature=0.3,
                                                                top_p=0.95,
                                                                stop=None,
                                                                max_tokens=self.max_tokens,
@@ -84,7 +84,7 @@ def summarize(self, text: str, system_prompt: str = "") -> Tuple[str, str]:
                     response_format = None
                 response = self.client.chat.completions.create(model=self.model,
                                                                messages=messages,
-                                                               temperature=0.7,
+                                                               temperature=0.3,
                                                                top_p=0.95,
                                                                stop=None,
                                                                max_tokens=self.max_tokens,

diff --git a/templates/index.html b/templates/index.html
@@ -200,9 +200,11 @@ <h3>Summarize this</h3>
                   <select id="model" name="model">
                     <option value="gpt-3.5-turbo">gpt-3.5-turbo</option>
                     <option value="gpt-3.5-turbo-16k">gpt-3.5-turbo-16k</option>
+                    <option value="gpt-3.5-turbo-0125" selected>gpt-3.5-turbo-0125	(16k)</option>
                     <option value="gpt-4">gpt-4</option>
                     <option value="gpt-4-32k">gpt-4-32k</option>
-                    <option value="gpt-4-1106-preview" selected>gpt-4-1106-preview</option>
+                    <option value="gpt-4-1106-preview">gpt-4-1106-preview</option>
+                    <option value="gpt-4-0125-preview">gpt-4-0125-preview (128k)</option>
                   </select>
                 </div>
               </div>