github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-18 12:58:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Fix docstring for ollama parameter "keep_alive" (#23973)

Browse Source 
Fix doc-string for ollama integration
This commit is contained in:
frob 2024-07-16 16:48:38 +02:00 committed by GitHub
parent 0c1889c713
commit c59e663365
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
libs/community/langchain_community/llms/ollama.py
View File

@ -112,18 +112,20 @@ class _OllamaCommon(BaseLanguageModel):
"""Timeout for the request stream"""
keep_alive: Optional[Union[int, str]] = None
"""How long the model will stay loaded into memory."""
"""How long the model will stay loaded into memory.
raw: Optional[bool] = None
"""raw or not.""
The parameter (Default: 5 minutes) can be set to:
1. a duration string in Golang (such as "10m" or "24h");
2. a number in seconds (such as 3600);
3. any negative number which will keep the model loaded \
in memory (e.g. -1 or "-1m");
4. 0 which will unload the model immediately after generating a response;
See the [Ollama documents](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately)"""
raw: Optional[bool] = None
"""raw or not."""
headers: Optional[dict] = None
"""Additional headers to pass to endpoint (e.g. Authorization, Referer).
This is useful when Ollama is hosted on cloud services that require