KeyArgo
/
private-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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>
This commit is contained in:
Iván Martínez 2024-03-20 21:33:46 +01:00 committed by GitHub
parent c2d694852b
commit 6f6c785dac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
private_gpt/components/llm/llm_component.py
View File

@ -131,6 +131,7 @@ class LLMComponent:
temperature=settings.llm.temperature, temperature=settings.llm.temperature,
context_window=settings.llm.context_window, context_window=settings.llm.context_window,
additional_kwargs=settings_kwargs, additional_kwargs=settings_kwargs,
request_timeout=ollama_settings.request_timeout,
) )
case "azopenai": case "azopenai":
try: try:

4
private_gpt/settings/settings.py
View File

@ -241,6 +241,10 @@ class OllamaSettings(BaseModel):
1.1, 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)", 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): class AzureOpenAISettings(BaseModel):

1
settings-ollama.yaml
View File

@ -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) 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_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) 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: vectorstore:
database: qdrant database: qdrant

1
settings.yaml
View File

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