feat(llm): Ollama timeout setting (#1773)

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

* Update settings-ollama.yaml

* Update settings.yaml

* updated settings.py and tidied up settings-ollama-yaml

* feat(UI): Faster startup and document listing (#1763)

* fix(ingest): update script label (#1770)

huggingface -> Hugging Face

* Fix lint errors

---------

Co-authored-by: Stephen Gresham <steve@gresham.id.au>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>

private_gpt/components/llm/llm_component.py

@@ -131,6 +131,7 @@ def __init__(self, settings: Settings) -> None:
                     temperature=settings.llm.temperature,
                     context_window=settings.llm.context_window,
                     additional_kwargs=settings_kwargs,
+                    request_timeout=ollama_settings.request_timeout,
                 )
             case "azopenai":
                 try:

private_gpt/settings/settings.py

@@ -241,6 +241,10 @@ 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 AzureOpenAISettings(BaseModel):

settings-ollama.yaml

@@ -14,11 +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)
+  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

settings.yaml

@@ -89,6 +89,7 @@ ollama:
   llm_model: llama2
   embedding_model: nomic-embed-text
   api_base: http://localhost:11434
+  request_timeout: 120.0
 
 azopenai:
   api_key: ${AZ_OPENAI_API_KEY:}