DX-3073: update Vector embedding model docs to match the console - #878
Merged
Merged
Conversation
The console only offers openai/text-embedding-3-small (dense) and BM25 (sparse) since DX-2310. Drop the BGE models from the model tables, the BGE-M3 sparse section and the info example, and retake the create-index screenshot. Closes #766 Claude-Session: https://claude.ai/code/session_01Vxm3XqQhCauGVEoLZxxNVM
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
Contributor
|
Docs7 for upstash.com
Commit |
context7
Bot
temporarily deployed
to
Docs7 Preview: DX-3073-vector-embedding-models
September 28, 2026 12:54
Destroyed
Copilot stopped reviewing on behalf of
CahidArda due to an error
September 28, 2026 13:13
Contributor
There was a problem hiding this comment.
Note
Copilot was unable to run its full agentic suite in this review.
Copilot review overview
Review effort: Lite
Findings: 3
Open (4)
llms-full.txt(which uses… · New
What changed in this PR
Updates the Vector documentation/examples to reflect the currently hosted embedding options (OpenAI text-embedding-3-small for dense/hybrid and BM25 for sparse), removing older BGE-related references.
Changes:
- Replace BGE-M3 references with
text-embedding-3-small(1536 dims) in docs and API examples. - Remove BGE model listings/sections and add guidance that BGE models aren’t available for new indexes.
- Update BM25 wording and mirror the doc updates into
llms-full.txt.
| File | Description |
|---|---|
| vector/features/sparseindexes.mdx | Updates sparse index docs to reference BM25 and uses text-embedding-3-small in the dense-vs-sparse example. |
| vector/features/embeddingmodels.mdx | Updates hosted model lists, removes BGE options, and adds a note about deprecation for new indexes. |
| vector/api/endpoints/info.mdx | Updates the /info example response to reflect the new dense embedding model and dimension. |
| llms-full.txt | Mirrors the same doc/example updates into the consolidated text artifact. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
context7
Bot
temporarily deployed
to
Docs7 Preview: DX-3073-vector-embedding-models
September 28, 2026 13:51
Destroyed
This branch was successfully deployed
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.
Fixes #766.
Since DX-2310 (upstash-console-v2#1011, Dec 2025) the console's create-index wizard hides the BGE models. It now offers only
openai/text-embedding-3-smallfor dense/hybrid indexes andBM25for sparse/hybrid indexes. The docs still listed the BGE models and never mentionedtext-embedding-3-small.Changes
vector/features/embeddingmodels.mdx: the dense table now listsopenai/text-embedding-3-small(1536 dims, 8191 tokens, MTEB 62.3) and the sparse table lists only BM25. Added a note that the BGE models are no longer available for new indexes. Removed the video guide, since it walks through the BGE models.vector/features/sparseindexes.mdx: removed the "BGE-M3 Sparse Vectors" section, and the intro example now usestext-embedding-3-small.vector/api/endpoints/info.mdx: the example response usesTEXT_EMBEDDING_3_SMALL/ 1536.img/vector/create_index_with_model.png: retook the screenshot from the current console, showingopenai/text-embedding-3-small.To confirm
https://claude.ai/code/session_01Vxm3XqQhCauGVEoLZxxNVM