added request_timeout to ollama, default set to 30.0 in settings.yaml and settings-ollama.yaml

private_gpt/components/llm/llm_component.py

@@ -131,6 +131,7 @@ class LLMComponent:
                     temperature=settings.llm.temperature,
                     context_window=settings.llm.context_window,
                     additional_kwargs=settings_kwargs,
+                    request_timeout=ollama_settings.request_timeout
                 )
             case "mock":
                 self.llm = MockLLM()

settings-ollama.yaml

@@ -19,6 +19,7 @@ ollama:
   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: 30.0 # Time elapsed until ollama times out the request. Default is 30s. Format is float.
 
 vectorstore:
   database: qdrant

settings.yaml

@@ -86,3 +86,4 @@ ollama:
   llm_model: llama2
   embedding_model: nomic-embed-text
   api_base: http://localhost:11434
+  request_timeout: 30.0