diff options
| author | ampersandru <43594741+ampersandru@users.noreply.github.com> | 2026-01-18 12:22:17 -0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-01-18 20:22:17 +0000 |
| commit | dfad809fe2fcc5c6179fce2e0b3d36331232442f (patch) | |
| tree | c4f89bf212d7387a5a2bddb47c6e90c8f46c5126 /docs/versioned_docs | |
| parent | 137c699b25e6272407181fc5be936b43cd263c5e (diff) | |
| download | karakeep-dfad809fe2fcc5c6179fce2e0b3d36331232442f.tar.zst | |
docs: enhance OLLAMA_KEEP_ALIVE variable description (#2410)
* Enhance OLLAMA_KEEP_ALIVE variable description
Expanded the explanation for OLLAMA_KEEP_ALIVE variable to include examples for better clarity. Added examples of -1m for indefinite, 0 for instant.
* Enhance OLLAMA_KEEP_ALIVE variable description
Updated the description of the OLLAMA_KEEP_ALIVE variable to include examples for better clarity.
Diffstat (limited to 'docs/versioned_docs')
| -rw-r--r-- | docs/versioned_docs/version-v0.30.0/03-configuration/01-environment-variables.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/docs/versioned_docs/version-v0.30.0/03-configuration/01-environment-variables.md b/docs/versioned_docs/version-v0.30.0/03-configuration/01-environment-variables.md index f02063a7..ef1222ac 100644 --- a/docs/versioned_docs/version-v0.30.0/03-configuration/01-environment-variables.md +++ b/docs/versioned_docs/version-v0.30.0/03-configuration/01-environment-variables.md @@ -96,7 +96,7 @@ Either `OPENAI_API_KEY` or `OLLAMA_BASE_URL` need to be set for automatic taggin | OPENAI_BASE_URL | No | Not set | If you just want to use OpenAI you don't need to pass this variable. If, however, you want to use some other openai compatible API (e.g. azure openai service), set this to the url of the API. | | OPENAI_PROXY_URL | No | Not set | HTTP proxy server URL for OpenAI API requests (e.g., `http://proxy.example.com:8080`). | | OLLAMA_BASE_URL | No | Not set | If you want to use ollama for local inference, set the address of ollama API here. | -| OLLAMA_KEEP_ALIVE | No | Not set | Controls how long the model will stay loaded into memory following the request (example value: "5m"). | +| OLLAMA_KEEP_ALIVE | No | Not set | Controls how long the model will stay loaded into memory following the request (examples: "5m" for 5 minutes, "-1m" to keep the model loaded indefinitely, "0" to unload the model instantly after processing is complete). | | INFERENCE_TEXT_MODEL | No | gpt-4.1-mini | The model to use for text inference. You'll need to change this to some other model if you're using ollama. | | INFERENCE_IMAGE_MODEL | No | gpt-4o-mini | The model to use for image inference. You'll need to change this to some other model if you're using ollama and that model needs to support vision APIs (e.g. llava). | | EMBEDDING_TEXT_MODEL | No | text-embedding-3-small | The model to be used for generating embeddings for the text. | |