fix(main.py): automatically infer mode for text completion models

litellm/main.py

@@ -3784,6 +3784,9 @@ async def ahealth_check(
 
             api_base = model_params.get("api_base") or get_secret("OPENAI_API_BASE")
 
+            if custom_llm_provider == "text-completion-openai":
+                mode = "completion"
+
             response = await openai_chat_completions.ahealth_check(
                 model=model,
                 messages=model_params.get(

litellm/proxy/_new_secret_config.yaml

@@ -13,13 +13,13 @@ model_list:
       api_version: "2023-07-01-preview"
       stream_timeout: 0.001
   model_name: azure-gpt-3.5
-- model_name: text-embedding-ada-002
-  litellm_params:
-    model: text-embedding-ada-002
-    api_key: os.environ/OPENAI_API_KEY
+# - model_name: text-embedding-ada-002
+#   litellm_params:
+#     model: text-embedding-ada-002
+#     api_key: os.environ/OPENAI_API_KEY
 - model_name: gpt-instruct
   litellm_params:
-    model: gpt-3.5-turbo-instruct
+    model: text-completion-openai/gpt-3.5-turbo-instruct
     # api_key: my-fake-key
     # api_base: https://exampleopenaiendpoint-production.up.railway.app/
 

proxy_server_config.yaml

@@ -55,6 +55,9 @@ model_list:
       api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/
       stream_timeout: 0.001
       rpm: 1
+  - model_name: gpt-instruct # [PROD TEST] - tests if `/health` automatically infers this to be a text completion model
+    litellm_params:
+      model: text-completion-openai/gpt-3.5-turbo-instruct
 litellm_settings:
   drop_params: True
   # max_budget: 100