Skip to content

Document OpenAI and Mistral embedders#4655

Merged
bjorncs merged 6 commits intomasterfrom
bjorncs/openai-mistral-embedder-docs
Apr 20, 2026
Merged

Document OpenAI and Mistral embedders#4655
bjorncs merged 6 commits intomasterfrom
bjorncs/openai-mistral-embedder-docs

Conversation

@bjorncs
Copy link
Copy Markdown
Member

@bjorncs bjorncs commented Apr 20, 2026

Summary

  • Add reference tables and guide sections for the new openai-embedder and mistral-embedder component types introduced in Add OpenAI and Mistral embedders; share HTTP scaffolding with VoyageAI 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) covering all three cloud embedders.
  • Keep the voyage-4-nano local-inference note inside the VoyageAI section.
  • Mistral quantization reference row cross-links to the VoyageAI row for shared auto/int8/binary semantics.

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.
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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-nano local-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.

Comment thread en/rag/embedding.html Outdated
Comment thread en/rag/embedding.html
Comment thread en/reference/rag/embedding.html
Comment thread en/reference/rag/embedding.html
bjorncs and others added 2 commits April 20, 2026 13:19
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.
Comment thread en/rag/embedding.html Outdated
Comment thread en/rag/embedding.html
<pre>{% highlight xml %}
<container version="1.0">
<component id="openai" type="openai-embedder">
<model>text-embedding-3-small</model>
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add URL to make it easy to see how to use custom URLs?

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I prefer having a simplified example here, and rather let the user discover how to override the endpoint by reading the reference documentation.

Comment thread en/rag/embedding.html
bjorncs added 2 commits April 20, 2026 13:57
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.
@bjorncs bjorncs requested a review from thomasht86 April 20, 2026 12:33
Copy link
Copy Markdown
Contributor

@thomasht86 thomasht86 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great!

@bjorncs bjorncs merged commit 08b7199 into master Apr 20, 2026
@bjorncs bjorncs deleted the bjorncs/openai-mistral-embedder-docs branch April 20, 2026 13:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants