diff --git a/private_gpt/settings/settings.py b/private_gpt/settings/settings.py
index 62af3f34..6528512f 100644
--- a/private_gpt/settings/settings.py
+++ b/private_gpt/settings/settings.py
@@ -229,6 +229,10 @@ class OllamaSettings(BaseModel):
         1.1,
         description="Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)",
     )
+    request_timeout: float = Field(
+        120.0,
+        description="Time elapsed until ollama times out the request. Default is 120s. Format is float. "
+    )
 
 
 class UISettings(BaseModel):
diff --git a/settings-ollama.yaml b/settings-ollama.yaml
index 048c0f02..d7e1a12c 100644
--- a/settings-ollama.yaml
+++ b/settings-ollama.yaml
@@ -14,12 +14,12 @@ ollama:
   llm_model: mistral
   embedding_model: nomic-embed-text
   api_base: http://localhost:11434
-  tfs_z: 1.0            # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting.
-  top_k: 40             # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
-  top_p: 0.9            # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
-  repeat_last_n: 64     # Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
-  repeat_penalty: 1.2   # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
-  request_timeout: 120.0 # Time elapsed until ollama times out the request. Default is 120s. Format is float.
+  tfs_z: 1.0              # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting.
+  top_k: 40               # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
+  top_p: 0.9              # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
+  repeat_last_n: 64       # Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
+  repeat_penalty: 1.2     # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
+  request_timeout: 120.0  # Time elapsed until ollama times out the request. Default is 120s. Format is float.
 
 vectorstore:
   database: qdrant