Aaronwilkowitz/sharepoint #1299
Conversation
| " // This is where we are doing the search\n", | ||
| " const list = await client.api('/search/query').post(requestBody);\n", | ||
| " const processList = async () => {\n", | ||
| " // This will go through and for each search response, grab the contents of the file and summarize with gpt-3.5-turbo\n", |
There was a problem hiding this comment.
we should probably change this to 4o-mini
| "\n", | ||
| "### Considerations\n", | ||
| "\n", | ||
| "Note that all the same limitations of Actions apply here, with regards to returning 100K characters or less and the [45 second timeout](https://platform.openai.com/docs/actions/production/timeouts).\n", |
There was a problem hiding this comment.
this might be slightly confusing for the doc return part...since we are returning the doc and not plaintext charagers
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you proceed, make sure to first familiarize yourself with the following information: \n", |
There was a problem hiding this comment.
probably worth adding here (and in the other one) a link out to the middleware notebook. I know it's referenced later too
| "\n", | ||
| "2. For each file that is found, convert it to a consistent readable format and retrieve all the text.\n", | ||
| "\n", | ||
| "3. Use GPT 3.5-turbo (gpt-3.5-turbo-0125) to extract the relevant text from the files based on the initial user’s question. Note the pricing of GPT 3.5 turbo [here](https://openai.com/pricing#language-models) - since we are dealing with small token chunks, the cost of this step is nominal. \n", |
| " 1. Basics\n", | ||
| "\n", | ||
| " 1. _Do you want to deploy code or container image?:_ **Code**\n", | ||
| "\n", |
There was a problem hiding this comment.
probably worth calling out here that you can change these to others, but these settings will be compatible with the sharepoint cookbooks
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "This particular GPT Action provides an overview of how to build an **Azure Function**, MSFT's cloud-based function builder. This documentation helps a user set up Azure Functions to connect to a GPT Action - and to a sample application. " |
There was a problem hiding this comment.
Maybe a comment on why this is useful? Like how you can use this to connect to different systems you have, and pre-process (eg summarizing text before returning to chatgpt, or converting to the proper file format)
There was a problem hiding this comment.
and some mention about how this example uses OAuth
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "*This is application specific.*" |
There was a problem hiding this comment.
maybe another reference to the sharepoint instructions, linking to the specific header, as an example?
Co-authored-by: maxreid-openai <max.reid@openai.com>
Co-authored-by: maxreid-openai <max.reid@openai.com>
2 participants
Summary
Updated Max's Sharepoint article into 3 - 2 GPT Actions on solution 1 & solution 2, then an article on using Azure middleware.
Motivation
Why are these changes necessary? How do they improve the cookbook?
Max's article is great but doesn't follow our new GPT Actions Library format, so we wanted to update it to make it follow the right process.
For new content
When contributing new content, read through our contribution guidelines, and mark the following action items as completed:
We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.