mirror of
https://github.com/supabase/supabase.git
synced 2026-10-10 11:55:05 +03:00
egor-romanov committed
1 parent
05f7a5e4d5
commit
bbde81f0de
10 files changed
+12
-12
No files matched your search
+12
-12
@@ -5,11 +5,11 @@ tags:
|
||||
- AI
|
||||
- tutorial
|
||||
- postgres
|
||||
date: '2023-05-24'
|
||||
date: '2023-05-25'
|
||||
toc_depth: 2
|
||||
author: egor_romanov,paul_copplestone
|
||||
image: 2023-05-24-chatgpt-plugins-support-postgres/chatgpt-plugins-support-postgres.jpeg
|
||||
thumb: 2023-05-24-chatgpt-plugins-support-postgres/chatgpt-plugins-support-postgres.jpeg
|
||||
image: 2023-05-25-chatgpt-plugins-support-postgres/chatgpt-plugins-support-postgres.jpeg
|
||||
thumb: 2023-05-25-chatgpt-plugins-support-postgres/chatgpt-plugins-support-postgres.jpeg
|
||||
---
|
||||
|
||||
One of the challenges that ChatGPT faces is being able to answer questions from a private dataset. We can solve this with “retrieval plugins”, which allow ChatGPT to access information from a database.
|
||||
@@ -132,13 +132,13 @@ This will require several steps:
|
||||
<img
|
||||
className="dark:hidden !m-0"
|
||||
alt="diagram reference"
|
||||
src="/images/blog/2023-05-24-chatgpt-plugins-support-postgres/chatgpt-plugin-scheme--light.svg"
|
||||
src="/images/blog/2023-05-25-chatgpt-plugins-support-postgres/chatgpt-plugin-scheme--light.svg"
|
||||
/>
|
||||
|
||||
<img
|
||||
className="hidden dark:block !m-0"
|
||||
alt="diagram reference"
|
||||
src="/images/blog/2023-05-24-chatgpt-plugins-support-postgres/chatgpt-plugin-scheme--dark.svg"
|
||||
src="/images/blog/2023-05-25-chatgpt-plugins-support-postgres/chatgpt-plugin-scheme--dark.svg"
|
||||
/>
|
||||
|
||||
### Step 1: Fork the ChatGPT Retrieval Plugin repository
|
||||
@@ -189,7 +189,7 @@ Using `supabase-cli` is not required and you can use any other docker image or h
|
||||
|
||||
To create embeddings Plugin uses OpenAI API and `text-embedding-ada-002` model. Each time we add some data to our datastore, or try to query relevant information from it, embedding will be created either for inserted data chunk, or for the query itself. To make it work we need to export `OPENAI_API_KEY`. If you already have an account in OpenAI, you just need to go to [User Settings - API keys](https://platform.openai.com/account/api-keys) and Create new secret key.
|
||||
|
||||
|
||||
|
||||
|
||||
### Step 6: Run the plugin!
|
||||
|
||||
@@ -234,23 +234,23 @@ Now, it is time to add our plugin to ChatGPT.
|
||||
|
||||
To integrate our plugin with ChatGPT, register it in the ChatGPT dashboard. Assuming you have access to ChatGPT Plugins and plugin development, select the Plugins model in a new chat, then choose "Plugin store" and "Develop your own plugin." Enter `localhost:3333` into the domain input, and your plugin is now part of ChatGPT.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
You can now ask questions about Postgres and receive answers derived from the documentation!
|
||||
|
||||
Let's try it out: ask ChatGPT to find out when to use `check` and when to use `using`. You will be able to see what queries were sent to our plugin and what it responded to.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
And after ChatGPT receives a response from the plugin it will answer your question with the data from the documentation.
|
||||
|
||||
|
||||
|
||||
|
||||
## Wrap up
|
||||
|
||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
Reference in new issue
Block a user