feat(model): Add ChatGPT API Support (briansunter#84)

fishpigbird · Mar 2, 2023 · bff969a · bff969a
1 parent e468dd2
commit bff969a
Show file tree

Hide file tree

Showing 4 changed files with 13,392 additions and 6,016 deletions.
diff --git a/README.md b/README.md
@@ -17,7 +17,7 @@
 
 ---
 
-<p align="center"> A plugin for GPT-3 AI assisted note taking in Logseq
+<p align="center"> A plugin for GPT-3 AI assisted note taking in Logseq. Uses OpenAI's ChatGPT API `gpt-3.5-turbo` model by default.
     <br>
 </p>
 
@@ -120,6 +120,13 @@ This will generate an image using the DALL-E model, save the image to the `asset
 
 ![logseq dalle](docs/dalle.gif)
 
+
+### ChatGPT Guidance
+You can adjust the `chatPrompt` setting to adjust how ChatGPT should respond to your input. By default, the setting is set to `Do not refer to yourself in your answers. Do not say as an AI language model...` to prevent the model from including unnecessary text in the response.
+
+You can add guidance such as "respond in chinese" or "respond in spanish" to the prompt to get the model to respond in a different language.
+
+This setting is only used when the model is set to `gpt-3.5-turbo`
 ### Inject Prefix
 
 Allows you to inject a prefix into the GPT-3 output before it is inserted into the block, such as a [[gpt3]] tag or markdown formatting like `>` for a blockquote. This is useful for identifying blocks that were generated by GPT-3.