From 8bd04f5a899e99e07dd87c93e2b57b877ae624fd Mon Sep 17 00:00:00 2001 From: Denis Shulyaka Date: Wed, 26 Mar 2025 14:03:14 +0300 Subject: [PATCH 1/3] Add Web search to OpenAI Conversation integration --- source/_integrations/openai_conversation.markdown | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/source/_integrations/openai_conversation.markdown b/source/_integrations/openai_conversation.markdown index c209db566ff..e54b08ca06b 100644 --- a/source/_integrations/openai_conversation.markdown +++ b/source/_integrations/openai_conversation.markdown @@ -64,6 +64,12 @@ Temperature: description: A value that determines the level of creativity and risk-taking the model should use when generating text. A higher temperature means the model is more likely to generate unexpected results, while a lower temperature results in more deterministic results. See the [OpenAI Completion Documentation](https://platform.openai.com/docs/guides/completion/introduction) for more information. Top P: description: An alternative to temperature, top_p determines the proportion of the most likely word choices the model should consider when generating text. A higher top_p means the model will only consider the most likely words, while a lower top_p means a wider range of words, including less likely ones, will be considered. For more information, see the [OpenAI Completion API Reference](https://platform.openai.com/docs/api-reference/completions/create#completions/create-top_p). +Enable web search: + description: Enable OpenAI-provided [Web search tool](https://openai.com/index/new-tools-for-building-agents/#web-search). Note that it is only available for gpt-4o and gpt-4o-mini models. +Search context size: + The search is performed with a separate fine-tuned `gpt-4o-search-preview` or `gpt-4o-mini-search-preview` model with its own context and its own [pricing](https://platform.openai.com/docs/pricing#web-search). This parameter controls how much context is retrieved from the web to help the tool formulate a response. The tokens used by the search tool do not affect the context window of the main model. These tokens are also not carried over from one turn to another — they're simply used to formulate the tool response and then discarded. This parameter would affect the search quality, cost, and latency. +Include home location: + This parameter allows using the location of your Home Assistant instance during search to provide more relevant search results. {% endconfiguration_basic %} ## Talking to Super Mario over the phone From 8625743ba4f64ed8027ca515e1ff6f93a6d1a9c2 Mon Sep 17 00:00:00 2001 From: Denis Shulyaka Date: Wed, 26 Mar 2025 14:10:48 +0300 Subject: [PATCH 2/3] Attempt to fix deployment --- source/_integrations/openai_conversation.markdown | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/source/_integrations/openai_conversation.markdown b/source/_integrations/openai_conversation.markdown index e54b08ca06b..8e964fd5e34 100644 --- a/source/_integrations/openai_conversation.markdown +++ b/source/_integrations/openai_conversation.markdown @@ -67,7 +67,7 @@ Top P: Enable web search: description: Enable OpenAI-provided [Web search tool](https://openai.com/index/new-tools-for-building-agents/#web-search). Note that it is only available for gpt-4o and gpt-4o-mini models. Search context size: - The search is performed with a separate fine-tuned `gpt-4o-search-preview` or `gpt-4o-mini-search-preview` model with its own context and its own [pricing](https://platform.openai.com/docs/pricing#web-search). This parameter controls how much context is retrieved from the web to help the tool formulate a response. The tokens used by the search tool do not affect the context window of the main model. These tokens are also not carried over from one turn to another — they're simply used to formulate the tool response and then discarded. This parameter would affect the search quality, cost, and latency. + The search is performed with a separate fine-tuned "gpt-4o-search-preview" or "gpt-4o-mini-search-preview" model with its own context and its own [pricing](https://platform.openai.com/docs/pricing#web-search). This parameter controls how much context is retrieved from the web to help the tool formulate a response. The tokens used by the search tool do not affect the context window of the main model. These tokens are also not carried over from one turn to another — they're simply used to formulate the tool response and then discarded. This parameter would affect the search quality, cost, and latency. Include home location: This parameter allows using the location of your Home Assistant instance during search to provide more relevant search results. {% endconfiguration_basic %} From 643579d1f43141342621607757a63e0d6d7a9683 Mon Sep 17 00:00:00 2001 From: Denis Shulyaka Date: Wed, 26 Mar 2025 15:42:43 +0300 Subject: [PATCH 3/3] Fix parameter description --- source/_integrations/openai_conversation.markdown | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/source/_integrations/openai_conversation.markdown b/source/_integrations/openai_conversation.markdown index 8e964fd5e34..c2e52221cf8 100644 --- a/source/_integrations/openai_conversation.markdown +++ b/source/_integrations/openai_conversation.markdown @@ -67,9 +67,9 @@ Top P: Enable web search: description: Enable OpenAI-provided [Web search tool](https://openai.com/index/new-tools-for-building-agents/#web-search). Note that it is only available for gpt-4o and gpt-4o-mini models. Search context size: - The search is performed with a separate fine-tuned "gpt-4o-search-preview" or "gpt-4o-mini-search-preview" model with its own context and its own [pricing](https://platform.openai.com/docs/pricing#web-search). This parameter controls how much context is retrieved from the web to help the tool formulate a response. The tokens used by the search tool do not affect the context window of the main model. These tokens are also not carried over from one turn to another — they're simply used to formulate the tool response and then discarded. This parameter would affect the search quality, cost, and latency. + description: The search is performed with a separate fine-tuned "gpt-4o-search-preview" or "gpt-4o-mini-search-preview" model with its own context and its own [pricing](https://platform.openai.com/docs/pricing#web-search). This parameter controls how much context is retrieved from the web to help the tool formulate a response. The tokens used by the search tool do not affect the context window of the main model. These tokens are also not carried over from one turn to another — they're simply used to formulate the tool response and then discarded. This parameter would affect the search quality, cost, and latency. Include home location: - This parameter allows using the location of your Home Assistant instance during search to provide more relevant search results. + description: This parameter allows using the location of your Home Assistant instance during search to provide more relevant search results. {% endconfiguration_basic %} ## Talking to Super Mario over the phone