From 122f037990da9c008130cde0ec5bd54259b3d0b0 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Wed, 7 May 2025 14:19:35 -0700
Subject: [PATCH] fix(ollama/completion): add 'max_completion_token' support
 for ollama

---
 .../llms/ollama/completion/transformation.py  | 11 ++++++++---
 .../proxy/_experimental/out/onboarding.html   |  1 -
 litellm/proxy/_new_secret_config.yaml         | 19 ++++++-------------
 3 files changed, 14 insertions(+), 17 deletions(-)
 delete mode 100644 litellm/proxy/_experimental/out/onboarding.html

diff --git a/litellm/llms/ollama/completion/transformation.py b/litellm/llms/ollama/completion/transformation.py
index c619fd8cfb7..b2557a53e95 100644
--- a/litellm/llms/ollama/completion/transformation.py
+++ b/litellm/llms/ollama/completion/transformation.py
@@ -150,6 +150,7 @@ class OllamaConfig(BaseConfig):
             "frequency_penalty",
             "stop",
             "response_format",
+            "max_completion_tokens",
         ]
 
     def map_openai_params(
@@ -160,7 +161,7 @@ class OllamaConfig(BaseConfig):
         drop_params: bool,
     ) -> dict:
         for param, value in non_default_params.items():
-            if param == "max_tokens":
+            if param == "max_tokens" or param == "max_completion_tokens":
                 optional_params["num_predict"] = value
             if param == "stream":
                 optional_params["stream"] = value
@@ -257,9 +258,13 @@ class OllamaConfig(BaseConfig):
         model_response.choices[0].finish_reason = "stop"
         if request_data.get("format", "") == "json":
             response_content = json.loads(response_json["response"])
-            
+
             # Check if this is a function call format with name/arguments structure
-            if isinstance(response_content, dict) and "name" in response_content and "arguments" in response_content:
+            if (
+                isinstance(response_content, dict)
+                and "name" in response_content
+                and "arguments" in response_content
+            ):
                 # Handle as function call (original behavior)
                 function_call = response_content
                 message = litellm.Message(
diff --git a/litellm/proxy/_experimental/out/onboarding.html b/litellm/proxy/_experimental/out/onboarding.html
deleted file mode 100644
index 755880844d4..00000000000
--- a/litellm/proxy/_experimental/out/onboarding.html
+++ /dev/null
@@ -1 +0,0 @@
-<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-75a5453f51d60261.js"/><script src="/ui/_next/static/chunks/fd9d1056-205af899b895cbac.js" async=""></script><script src="/ui/_next/static/chunks/117-1c5bfc45bfc4237d.js" async=""></script><script src="/ui/_next/static/chunks/main-app-475d6efe4080647d.js" async=""></script><title>LiteLLM Dashboard</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-42372ed130431b0a.js" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-75a5453f51d60261.js" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/a34f9d1faa5f3315-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/86f6cc749f6b8493.css\",\"style\"]\n3:HL[\"/ui/_next/static/css/cd177eb0911192ea.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"4:I[12846,[],\"\"]\n6:I[19107,[],\"ClientPageRoot\"]\n7:I[12011,[\"665\",\"static/chunks/3014691f-b7b79b78e27792f3.js\",\"42\",\"static/chunks/42-69f5b4e6a9942a9f.js\",\"899\",\"static/chunks/899-57685cedd1dcbc78.js\",\"250\",\"static/chunks/250-e09809f7285da8f4.js\",\"461\",\"static/chunks/app/onboarding/page-d7c45deba6448e6a.js\"],\"default\",1]\n8:I[4707,[],\"\"]\n9:I[36423,[],\"\"]\nb:I[61060,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"0:[\"$\",\"$L4\",null,{\"buildId\":\"7THZiS_TuVf500dDwTSz5\",\"assetPrefix\":\"/ui\",\"urlParts\":[\"\",\"onboarding\"],\"initialTree\":[\"\",{\"children\":[\"onboarding\",{\"children\":[\"__PAGE__\",{}]}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"onboarding\",{\"children\":[\"__PAGE__\",{},[[\"$L5\",[\"$\",\"$L6\",null,{\"props\":{\"params\":{},\"searchParams\":{}},\"Component\":\"$7\"}],null],null],null]},[null,[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\",\"onboarding\",\"children\"],\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"notFoundStyles\":\"$undefined\"}]],null]},[[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/86f6cc749f6b8493.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\"}],[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/cd177eb0911192ea.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_cf7686\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[]}]}]}]],null],null],\"couldBeIntercepted\":false,\"initialHead\":[null,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"LiteLLM Dashboard\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script></body></html>
\ No newline at end of file
diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml
index e1a444a6d9c..11069452097 100644
--- a/litellm/proxy/_new_secret_config.yaml
+++ b/litellm/proxy/_new_secret_config.yaml
@@ -60,16 +60,9 @@ model_list:
   - model_name: gemini/gemini-2.0-flash
     litellm_params:
       model: gemini/gemini-2.0-flash
-
-litellm_settings:
-  num_retries: 0
-  check_provider_endpoint: true
-  cache: true
-  callbacks: ["otel"]
-
-files_settings:
-  - custom_llm_provider: gemini
-    api_key: os.environ/GEMINI_API_KEY
-
-general_settings:
-  store_prompts_in_spend_logs: true
\ No newline at end of file
+  - model_name: llama-qwen
+    litellm_params:
+      model: ollama/qwen2:0.5b
+    model_info:
+      input_cost_per_token: 0.75
+      output_cost_per_token: 3