feat(voyage): add voyage-context-4 and voyage-4 series models - #5
Closed
fzowl wants to merge 6 commits into
Closed
Conversation
- Add voyage-context-4 contextual embedding model (120k ctx) - Add voyage-4, voyage-4-large, voyage-4-lite, voyage-4-nano - Add voyage-multimodal-3.5 - Normalize contextual embedding input: pass list[str] to API, keep list[list[str]] only when caller provides it - Add tests for context-4 detection and input normalization
…struct Fill in remaining Voyage embedding models absent from the price map. Synced across both root and backup model price maps.
- Feature voyage-context-4 as the recommended contextual model - Add voyage-4 / voyage-4-large / voyage-4-lite to the supported models and model selection tables with pricing
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds
voyage-context-4and the rest of the current Voyage AI lineup to the cost/context maps, and ensures the contextualized embeddings API is always called withlist[str].Models added (both
model_prices_and_context_window.jsonandlitellm/model_prices_and_context_window_backup.json)Prices verified against the Voyage AI pricing page; context lengths against the embeddings / contextualized-chunk docs.
voyage-4-nanois an open-weight model (Hugging Face), no listed API price -> cost0.0.Contextual embedding input (list[str])
VoyageContextualEmbeddingConfig.transform_embedding_requestnormalizes a barestrto[str]and passeslist[str]straight to the contextualized embeddings API;list[list[str]]is forwarded only when the caller already supplied that nested shape.Tests
voyage-context-4added to contextual model detection testtest_contextual_embedding_request_input_normalization(str / list[str] / list[list[str]])tests/llm_translation/test_voyage_ai.py: 16 passed, 1 skippedDouble-check
voyage-multimodal-3.5should carry a per-pixel cost (mirrors existingvoyage-multimodal-3, token cost only).