add openai/gpt-4o-mini

main.py

@@ -37,6 +37,7 @@ API_KEY = os.environ.get("CHAT_AUTH_KEY", "default_secret_key")
 api_key_header = APIKeyHeader(name=API_KEY_NAME, auto_error=False)
 
 ModelID = Literal[
+    "openai/gpt-4o-mini",
     "meta-llama/llama-3-70b-instruct",
     "anthropic/claude-3.5-sonnet",
     "deepseek/deepseek-coder",
@@ -68,14 +69,14 @@ class QueryModel(BaseModel):
 class NewsQueryModel(BaseModel):
     query: str = Field(..., description="News topic to search for")
     model_id: ModelID = Field(
-        default="meta-llama/llama-3-70b-instruct",
+        default="openai/gpt-4o-mini",
         description="ID of the model to use for response generation"
     )
     class Config:
         schema_extra = {
             "example": {
                 "query": "Latest developments in AI",
-                "model_id": "meta-llama/llama-3-70b-instruct"
+                "model_id": "openai/gpt-4o-mini"
             }
         }
 
@@ -103,7 +104,7 @@ def limit_tokens(input_string, token_limit=6000):
 def calculate_tokens(msgs):
     return sum(len(encoding.encode(str(m))) for m in msgs)
 
-def chat_with_llama_stream(messages, model="gpt-3.5-turbo", max_llm_history=4, max_output_tokens=2500):
+def chat_with_llama_stream(messages, model="openai/gpt-4o-mini", max_llm_history=4, max_output_tokens=2500):
     logger.info(f"Starting chat with model: {model}")
     while calculate_tokens(messages) > (8000 - max_output_tokens):
         if len(messages) > max_llm_history:
@@ -206,6 +207,7 @@ async def coding_assistant(query: QueryModel, background_tasks: BackgroundTasks,
     - openai/gpt-3.5-turbo-instruct
     - qwen/qwen-72b-chat
     - google/gemma-2-27b-it
+    - openai/gpt-4o-mini
     Requires API Key authentication via X-API-Key header.
     """
     logger.info(f"Received coding assistant query: {query.user_query}")
@@ -321,7 +323,7 @@ async def news_assistant(query: NewsQueryModel, api_key: str = Depends(verify_ap
 class SearchQueryModel(BaseModel):
     query: str = Field(..., description="Search query")
     model_id: ModelID = Field(
-        default="meta-llama/llama-3-70b-instruct",
+        default="openai/gpt-4o-mini",
         description="ID of the model to use for response generation"
     )
     class Config: