jeans/home-assistant.io
jeans/home-assistant.io
1
0
Fork 0
mirror of https://github.com/home-assistant/home-assistant.io.git synced 2025-07-21 16:27:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update ollama documentation with the context size parameter (#34460)

Browse Source 
* Update ollama documentation for context size

* Update source/_integrations/ollama.markdown

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update source/_integrations/ollama.markdown

* Update source/_integrations/ollama.markdown

---------

Co-authored-by: c0ffeeca7 <38767475+c0ffeeca7@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
This commit is contained in:
Allen Porter 2024-08-27 15:55:51 -07:00 committed by GitHub
parent a6d0f39cb4
commit 54d292841d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
source/_integrations/ollama.markdown
View File

@ -38,6 +38,8 @@ Model:
Prompt template:
description: The starting text for the AI language model to generate new text from. This text can include information about your Home Assistant instance, devices, and areas and is written using [Home Assistant Templating](/docs/configuration/templating/).
Context window size:
description: "The context window size is the number of tokens the model can take as input. Home Assistant defaults to 8k, which is larger than the default value in Ollama Server (2k), and you may adjust it based on the maximum context size of the specific model used. A larger value will better support larger homes with more entities, and smaller values may lower Ollama server RAM usage."
Max history messages:
description: Maximum number of messages to keep for each conversation (0 = no limit). Limiting this value will cause older messages in a conversation to be dropped.