Merge pull request #11697 from foraxe/fix-keep-alive-top-level

fix: Promote keep_alive to top-level in payload for Ollama API (dev branch)

backend/open_webui/routers/ollama.py

@@ -1169,7 +1169,7 @@ async def generate_chat_completion(
     prefix_id = api_config.get("prefix_id", None)
     if prefix_id:
         payload["model"] = payload["model"].replace(f"{prefix_id}.", "")
-
+    # payload["keep_alive"] = -1 # keep alive forever
     return await send_post_request(
         url=f"{url}/api/chat",
         payload=json.dumps(payload),

backend/open_webui/utils/payload.py

@@ -110,6 +110,11 @@ def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
         "num_thread": int,
     }
 
+    # Extract keep_alive from options if it exists
+    if "options" in form_data and "keep_alive" in form_data["options"]:
+        form_data["keep_alive"] = form_data["options"]["keep_alive"]
+        del form_data["options"]["keep_alive"]
+
     return apply_model_params_to_body(params, form_data, mappings)
 
 
@@ -231,6 +236,11 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
                 "system"
             ]  # To prevent Ollama warning of invalid option provided
 
+        # Extract keep_alive from options if it exists
+        if "keep_alive" in ollama_options:
+            ollama_payload["keep_alive"] = ollama_options["keep_alive"]
+            del ollama_options["keep_alive"]
+
     # If there is the "stop" parameter in the openai_payload, remap it to the ollama_payload.options
     if "stop" in openai_payload:
         ollama_options = ollama_payload.get("options", {})