Document OpenAI compatible API provider usage #2777
Conversation
Added instructions for using OpenAI compatible API provider, including required parameters and a JSON example.
|
|
WalkthroughThis pull request adds documentation to the waveai-modes file explaining how to configure an OpenAI-compatible API provider. The addition covers required configuration fields (ai:endpoint, ai:apitoken, ai:model), specifies "openai-chat" as the ai:mode value, clarifies that ai:endpoint must be a full endpoint URL, and includes a concrete JSON configuration example. The documentation section is added in two locations within the file, resulting in 27 added lines with no deletions. Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@docs/docs/waveai-modes.mdx`:
- Around line 202-203: Update the documentation line to use the correct provider
wording and config key: change "OpenAPI compatible API provider" to
"OpenAI‑compatible API provider" and replace the config key reference from
"ai:mode" to "ai:apitype" (so the sentence reads that you must provide
ai:endpoint, ai:apitoken, ai:model and set ai:apitype to "openai-chat"); adjust
any nearby occurrences of "OpenAPI" and "ai:mode" to the corrected terms to keep
the doc consistent.
- Around line 206-209: Update the documentation text to replace the
incorrect/unclear token "baseurl" with the standardized phrasing "base URL"
wherever it appears in the paragraph referencing ai:endpoint (e.g., the sentence
"The ai:endpoint is *NOT* a baseurl." and the explanatory line "If you provide
only the baseurl..."); ensure the ai:endpoint example
(https://api.x.ai/v1/chat/completions) and surrounding sentences use "base URL"
for consistency and clarity.
| To use an OpenAPI compatible API provider, you need to provide the ai:endpoint, ai:apitoken, ai:model parameters, | ||
| and use "openai-chat" as the ai:mode. |
There was a problem hiding this comment.
Fix incorrect field name and provider terminology.
The config key should be ai:apitype, not ai:mode, and this section should say “OpenAI‑compatible,” not “OpenAPI compatible,” to match the rest of the doc and avoid broken configs.
✅ Proposed wording fix
-To use an OpenAPI compatible API provider, you need to provide the ai:endpoint, ai:apitoken, ai:model parameters,
-and use "openai-chat" as the ai:mode.
+To use an OpenAI-compatible API provider, you need to provide the ai:endpoint, ai:apitoken, ai:model parameters,
+and set "openai-chat" as the ai:apitype.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| To use an OpenAPI compatible API provider, you need to provide the ai:endpoint, ai:apitoken, ai:model parameters, | |
| and use "openai-chat" as the ai:mode. | |
| To use an OpenAI-compatible API provider, you need to provide the ai:endpoint, ai:apitoken, ai:model parameters, | |
| and set "openai-chat" as the ai:apitype. |
🧰 Tools
🪛 LanguageTool
[grammar] ~202-~202: Use a hyphen to join words.
Context: ...### OpenAI Compatible To use an OpenAPI compatible API provider, you need to pro...
(QB_NEW_EN_HYPHEN)
🤖 Prompt for AI Agents
In `@docs/docs/waveai-modes.mdx` around lines 202 - 203, Update the documentation
line to use the correct provider wording and config key: change "OpenAPI
compatible API provider" to "OpenAI‑compatible API provider" and replace the
config key reference from "ai:mode" to "ai:apitype" (so the sentence reads that
you must provide ai:endpoint, ai:apitoken, ai:model and set ai:apitype to
"openai-chat"); adjust any nearby occurrences of "OpenAPI" and "ai:mode" to the
corrected terms to keep the doc consistent.
| The ai:endpoint is *NOT* a baseurl. The endpoint should contain the full endpoint, not just the baseurl. | ||
| For example: https://api.x.ai/v1/chat/completions | ||
|
|
||
| If you provide only the baseurl, you are likely to get a 404 message. |
There was a problem hiding this comment.
Tighten wording: use “base URL.”
“baseurl” is a spelling/formatting issue in docs; use “base URL” for clarity and consistency.
✍️ Suggested edit
-The ai:endpoint is *NOT* a baseurl. The endpoint should contain the full endpoint, not just the baseurl.
+The ai:endpoint is *NOT* a base URL. The endpoint should contain the full endpoint URL, not just the base URL.🧰 Tools
🪛 LanguageTool
[grammar] ~206-~206: Ensure spelling is correct
Context: ...de. :::note The ai:endpoint is NOT a baseurl. The endpoint should contain the full e...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
[grammar] ~209-~209: Ensure spelling is correct
Context: ...t/completions If you provide only the baseurl, you are likely to get a 404 message. :...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
🤖 Prompt for AI Agents
In `@docs/docs/waveai-modes.mdx` around lines 206 - 209, Update the documentation
text to replace the incorrect/unclear token "baseurl" with the standardized
phrasing "base URL" wherever it appears in the paragraph referencing ai:endpoint
(e.g., the sentence "The ai:endpoint is *NOT* a baseurl." and the explanatory
line "If you provide only the baseurl..."); ensure the ai:endpoint example
(https://api.x.ai/v1/chat/completions) and surrounding sentences use "base URL"
for consistency and clarity.
2 participants
Added instructions for using OpenAI compatible API provider, including required parameters and a JSON example.
It took me a while to notice that, unlike most the common usage of a baseurl, waveterm needs the full endpoint.