feat(embedder): add Cohere dense embedder#941
Merged
MaojiaSheng merged 6 commits intovolcengine:mainfrom Mar 30, 2026
Merged
Conversation
|
|
|
Failed to generate code suggestions for PR |
MaojiaSheng
approved these changes
Mar 26, 2026
Collaborator
|
@Dicoangelo Thanks, but there are some conflicts that need to be resovled |
Adds CohereDenseEmbedder using Cohere's Embed API v2. - Supports embed-v4.0, embed-english-v3.0, embed-multilingual-v3.0 - Server-side dimension reduction for embed-v4.0 (256/512/1024/1536) - Client-side truncation + renormalization fallback for v3 models - Asymmetric search via input_type (search_query/search_document) - Batch embedding with 96-item chunking (Cohere API limit) - Full factory integration: provider validation, dimension resolution none
16 tests covering: - Init validation (api_key required, defaults, model dimensions) - Dimension handling (v4 server-side, v3 client-side truncation, invalid dims) - Embedding calls (single, batch, query vs document input_type) - output_dimension sent for embed-v4.0 - Error handling (API errors → RuntimeError) - Resource cleanup (close) none
Extends RerankConfig with provider field and api_key for Cohere.
Adds CohereRerankClient with same interface as VikingDB RerankClient.
HierarchicalRetriever auto-selects rerank backend based on provider.
Config example:
"rerank": {"provider": "cohere", "api_key": "...", "threshold": 0.15}
Quality improvement: META tokenomics query 0.55 → 0.77 relevance score.
none
9 tests covering: - Rerank batch scoring with index-to-order mapping - Empty input handling - API error graceful fallback (returns None) - Original order preservation from Cohere's sorted response - Resource cleanup - RerankConfig provider auto-detection (cohere/vikingdb/empty) none
More vector candidates for reranker to evaluate = better precision. With Cohere rerank-v3.5, 10 candidates gives the cross-encoder enough material to find the best match without excessive latency. none
Dicoangelo
force-pushed
the
feat/cohere-embedder
branch
from
ac0552f to
5fd06bb
Compare
…lient.from_config() Cohere was special-cased in hierarchical_retriever.py while openai/litellm went through the centralized RerankClient.from_config() dispatch. This commit adds CohereRerankClient.from_config() and routes it through the same path. Also fixes a bug where from_config() used config.provider directly instead of _effective_provider(), which meant auto-detected providers (e.g. api_key without explicit provider="cohere") would not dispatch correctly. none
MaojiaSheng
approved these changes
Mar 30, 2026
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
3 participants
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
CohereDenseEmbedderusing Cohere's Embed API v2 (/v2/embed)embed-v4.0,embed-english-v3.0,embed-multilingual-v3.0,embed-*-light-v3.0embed-v4.0(256/512/1024/1536) viaoutput_dimensioninput_type(search_query/search_document)_create_embedderregistryChanges
openviking/models/embedder/cohere_embedders.py—CohereDenseEmbedderclassopenviking/models/embedder/__init__.py— export +__all__entryopenviking_cli/utils/config/embedding_config.py—"cohere"in provider validation, dimension resolution, factory registryConfig example
{ "embedding": { "dense": { "provider": "cohere", "model": "embed-v4.0", "api_key": "your-cohere-api-key", "dimension": 1024 } } }Test plan
provider: "cohere"passes Pydantic validationembed-v4.0→ 1536 default, configurable to 1024none