Document OpenAI and Mistral embedders#4655
Merged
Conversation
Add reference tables and guide sections for the openai-embedder and mistral-embedder component types introduced in vespa-engine/vespa#36373. Generalize the VoyageAI best-practices block into provider-agnostic subsections under "Tricks and tips" (separate feed/search embedders, cost optimization with model variants, rate limit isolation, thread pool tuning, dynamic batching) so the guidance covers all three cloud embedders. Keep the voyage-4-nano local-inference note in the VoyageAI section.
Contributor
There was a problem hiding this comment.
Pull request overview
Adds documentation for the new OpenAI and Mistral cloud embedders and reorganizes embedding “tricks and tips” to be provider-agnostic across cloud providers.
Changes:
- Added OpenAI embedder documentation and a reference configuration table.
- Added Mistral embedder documentation and a reference configuration table (including quantization cross-reference to VoyageAI semantics).
- Refactored VoyageAI “Best practices” into shared “Tricks and tips” sections (separate feed/search embedders, rate limits, thread pool tuning, dynamic batching), keeping the
voyage-4-nanolocal-inference note in the VoyageAI section.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| en/reference/rag/embedding.html | Adds OpenAI + Mistral embedder reference sections and config tables; links Mistral quantization semantics to VoyageAI. |
| en/rag/embedding.html | Adds OpenAI + Mistral guide sections; restructures provider-agnostic operational guidance under “Tricks and tips”. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Add the `batching` element row to the OpenAI and Mistral reference config tables. Follow-up to the PR #4655 review: dynamic batching is being added to these embedders in vespa-engine/vespa#36461.
thomasht86
reviewed
Apr 20, 2026
thomasht86
reviewed
Apr 20, 2026
| <pre>{% highlight xml %} | ||
| <container version="1.0"> | ||
| <component id="openai" type="openai-embedder"> | ||
| <model>text-embedding-3-small</model> |
Contributor
There was a problem hiding this comment.
add URL to make it easy to see how to use custom URLs?
Member
Author
There was a problem hiding this comment.
I prefer having a simplified example here, and rather let the user discover how to override the endpoint by reading the reference documentation.
thomasht86
reviewed
Apr 20, 2026
Apply suggestion from PR #4655 review: the embedder can target any OpenAI-compatible API, not just self-hosted ones.
Narrow the GPU / fp16 recommendation to local ONNX-based embedders and add a pointer for cloud embedders to the existing thread-pool and dynamic-batching tuning sections. Addresses PR #4655 review feedback.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
openai-embedderandmistral-embeddercomponent types introduced in Add OpenAI and Mistral embedders; share HTTP scaffolding with VoyageAI vespa#36373.voyage-4-nanolocal-inference note inside the VoyageAI section.quantizationreference row cross-links to the VoyageAI row for sharedauto/int8/binarysemantics.