revised troubleshooting tip for local llm and fixed typo in release notes

This commit is contained in:
Knox Lively
2024-05-04 00:43:57 -06:00
parent a8abd4d93c
commit 302ac75c29
4 changed files with 11 additions and 4 deletions
+4
View File
@@ -48,6 +48,10 @@ If you encounter issues while using your own LLM provider with Wave AI, consider
- **Incorrect model selection:** If you have multiple LLMs installed, make sure to set the `aimodel` parameter to the specific model you want to use.
- **Unexpected behavior or inconsistent results:** If you encounter unexpected behavior or inconsistent results when using your own LLM provider with Wave AI, try [resetting](#reset-wave-ai) the `aibaseurl` and `aimodel` parameters to their default values and reconfiguring your LLM provider from scratch. This can help rule out any configuration issues that might be causing problems.
<Tip>
If you continue to face issues after trying these troubleshooting steps, feel free to reach out to us on [Discord](https://discord.gg/XfvZ334gwU).
</Tip>
## Reset Wave AI
At any time if you find that you wish to return to the default Wave AI experience, you can reset the `aibaseurl` and `aimodel` parameters to their default state by using the following commands.
+3 -2
View File
@@ -50,8 +50,9 @@ If you encounter issues while using LocalAI with Wave AI, consider the following
- **Incorrect model selection:** If you have multiple LocalAI models installed, make sure to set the `aimodel` parameter to the specific model you want to use.
- **Unexpected behavior or inconsistent results:** If you encounter unexpected behavior or inconsistent results when using LocalAI with Wave AI, try [resetting](#reset-wave-ai) the `aibaseurl` and `aimodel` parameters to their default values and reconfiguring LocalAI from scratch. This can help rule out any configuration issues that might be causing problems.
If you continue to face issues after trying these troubleshooting steps, please see the [Additional Resources](#additional-resources) section below for further assistance.
<Tip>
If you continue to face issues after trying these troubleshooting steps, please see the [Additional Resources](#additional-resources) section below for further assistance, or feel free to reach out to us on [Discord](https://discord.gg/XfvZ334gwU).
</Tip>
## Reset Wave AI
At any time if you find that you wish to return to the default Wave AI experience, you can reset the `aibaseurl` and `aimodel` parameters to their default state by using the following commands.
+3 -1
View File
@@ -46,7 +46,9 @@ If you encounter issues while using Ollama with Wave AI, consider the following
- **Incorrect model selection:** If you have multiple Ollama models installed, make sure to set the `aimodel` parameter to the specific model you want to use. You can list available models using the ollama list command in your terminal.
- **Unexpected behavior or inconsistent results:** If you encounter unexpected behavior or inconsistent results when using Ollama with Wave AI, try [resetting](#reset-wave-ai) the `aibaseurl` and `aimodel` parameters to their default values and reconfiguring Ollama from scratch. This can help rule out any configuration issues that might be causing problems.
If you continue to face issues after trying these troubleshooting steps, please see the [Additional Resources](#additional-resources) section below for further assistance.
<Tip>
If you continue to face issues after trying these troubleshooting steps, please see the [Additional Resources](#additional-resources) section below for further assistance, or feel free to reach out to us on [Discord](https://discord.gg/XfvZ334gwU).
</Tip>
## Reset Wave AI
At any time if you find that you wish to return to the default Wave AI experience, you can reset the `aibaseurl` and `aimodel` parameters to their default state by using the following commands.
+1 -1
View File
@@ -30,7 +30,7 @@ New sudo support, better theming and keybinding support, with a ton of performan
* AI: cleaned up labels/names now that our AI integration is not tied to Chat-GPT (BYOLLM support)
* UI: light mode fixes and cleanup
* UI: restyled command input box (removed background color / outline)
* UI: restyled some of the command input auxillary views to be more consistent
* UI: restyled some of the command input auxiliary views to be more consistent
* UI: new labels for dropdowns, correctly truncates longer values
* UI: new native context menus for blocks and tabs for quicker access to some functionality
* Internal: Ephemeral Command support to help drive background updates for the command prompt and future use for completions