From 4c8d8722bd68519aa2bc18c4f2c1225ed8468dc9 Mon Sep 17 00:00:00 2001 From: Alexis VIALARET Date: Tue, 16 Jan 2024 09:49:49 +0100 Subject: [PATCH] doc: add usability disclaimer for gemini --- docs/recipe_llms_configs.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/docs/recipe_llms_configs.md b/docs/recipe_llms_configs.md index 2d0a744..597fc96 100644 --- a/docs/recipe_llms_configs.md +++ b/docs/recipe_llms_configs.md @@ -34,6 +34,12 @@ LLMConfig: &LLMConfig ## Vertex AI gemini-pro +!!! warning + + Right now Gemini models' safety settings are **very** sensitive, and is is not possible to disable them. That makes this model pretty much useless for the time being as it blocks most requests and/or responses. + + Github issue to follow: https://github.com/langchain-ai/langchain/pull/15344#issuecomment-1888597151 + !!! info "You will first need to login to GCP" ```shell