From e0079267f4c33f31ad12a8d887a9145daef7f9af Mon Sep 17 00:00:00 2001 From: Steve Androulakis Date: Fri, 24 Jan 2025 17:07:19 -0800 Subject: [PATCH] readme --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0c40e5e..a2a9d23 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ The agent can use OpenAI's GPT-4o, Google Gemini, Anthropic Claude, or a local L - `LLM_PROVIDER=openai` for OpenAI's GPT-4o - `LLM_PROVIDER=google` for Google Gemini - `LLM_PROVIDER=anthropic` for Anthropic -- `LLM_PROVIDER=ollama` for the local LLM via Ollama (not recommended for this use case) +- `LLM_PROVIDER=ollama` for running LLMs via [Ollama](https://ollama.ai) (not recommended for this use case) ### Option 1: OpenAI @@ -51,7 +51,7 @@ To use a local LLM with Ollama: 2. Set `LLM_PROVIDER=ollama` in your `.env` file and `OLLAMA_MODEL_NAME` to the name of the model you installed. -Note: The local LLM is disabled by default as ChatGPT 4o was found to be MUCH more reliable for this use case. However, you can switch to Ollama if desired. +Note: I found the other (hosted) LLMs to be MUCH more reliable for this use case. However, you can switch to Ollama if desired, and choose a suitably large model if your computer has the resources. ## Agent Tools * Requires a Rapidapi key for sky-scrapper (how we find flights). Set this in the `RAPIDAPI_KEY` environment variable in .env