docs(model-providers): fix structure, model lists, and a wrong published token limit - #498
Merged
g-despot merged 2 commits intoAug 8, 2026
Conversation
…hed token limit The ColModernVBERT query token limit read 8,092, a transposition. The model's own tokenizer_config.json gives model_max_length 8192. It renders on two pages through a shared include. The AWS Bedrock page listed 21 model IDs that had gone stale. Core detects model families by substring, so newer models already work; the list is replaced with that explanation and a pointer to the live AWS list, so it cannot rot again. Also: a duplicated 'Vectorizer parameters' heading merged, default markers added to three model lists that had none, a Reranker section added to two provider index pages whose reranker page existed but was unreachable, and the v1.33+ opt-out variable for API-based modules documented alongside the older opt-in.
![orca-security-eu[bot]](https://avatars.githubusercontent.com/in/276244?s=60&v=4){kind=small}
There was a problem hiding this comment.
Orca Security Scan Summary
| Status | Check | Issues by priority | |
|---|---|---|---|
 Passed |
Secrets |  0  0  0  0 |
View in Orca |
Contributor
There was a problem hiding this comment.
Pull request overview
Corrects model-provider documentation structure, defaults, model compatibility guidance, and token limits.
Changes:
- Adds missing reranker navigation and consolidates parameter documentation.
- Updates model defaults, Bedrock guidance, and API-module configuration.
- Corrects the ColModernVBERT token limit.
Reviewed changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
docs/weaviate/model-providers/transformers/index.md |
Adds reranker navigation. |
docs/weaviate/model-providers/jinaai/reranker.md |
Marks the server-default model. |
docs/weaviate/model-providers/jinaai/index.md |
Adds reranker navigation. |
docs/weaviate/model-providers/jinaai/embeddings-multimodal.md |
Consolidates parameters and marks the default. |
docs/weaviate/model-providers/jinaai/embeddings-colbert.md |
Marks the server-default model. |
docs/weaviate/model-providers/index.md |
Documents API-module opt-out behavior. |
docs/weaviate/model-providers/google/embeddings-multimodal.md |
Documents the default model. |
docs/weaviate/model-providers/aws/generative.md |
Replaces stale model IDs with dynamic guidance. |
docs/weaviate/client-libraries/_includes/feedback.mdx |
Removes legacy feedback content. |
_includes/weaviate-embeddings-multimodal-models.mdx |
Corrects the query token limit. |
_includes/wcs/restart-warning.mdx |
Removes obsolete warning content. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
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.
Low tier of the docs deep review, 1 of 7. 7 findings, 11 files.
Stacked on the review integration branch, which carries #493 and #494-#497. Retargets to
mainas that stack merges.A wrong published spec: the ColModernVBERT query token limit read 8,092. The model's own
tokenizer_config.jsongivesmodel_max_length: 8192. It renders on two pages through a shared include.The AWS Bedrock list had 21 stale model IDs. Core detects families by substring, so newer models already work; the list is replaced by that explanation plus a pointer to AWS's live list, so it cannot rot again. A follow-on sentence that promised "one of the available models" and a default was corrected too, since the section no longer provides either.
Also: a duplicated
Vectorizer parametersheading merged, default markers added to three lists that had none, a Reranker section added to two provider index pages whose reranker page existed but was unreachable, and the v1.33+ opt-out for API-based modules documented beside the older opt-in.Verified:
yarn build-devexit 0; links and anchors at or better than baseline.