feat: expose embedding/extraction model config in node-type registry#1174
Merged
Conversation
- SearchVector: add embedding_model, embedding_provider params - ProcessFileEmbedding: add embedding_model, embedding_provider params - ProcessImageEmbedding: add embedding_model, embedding_provider params - ProcessChunks: add embedding_model, embedding_provider params - SearchUnified.embedding: add embedding_model, embedding_provider params - ProcessExtraction: add extraction_model, extraction_provider params - All params are optional, default to null (worker falls back to runtime config)
Contributor
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 optional
embedding_model/embedding_providerparameters to 5 embedding-related node types, andextraction_model/extraction_providertoProcessExtraction. This lets blueprint authors specify which model and provider to use per-node, rather than relying solely on runtime config.All new parameters are optional strings with no defaults — when omitted (null), workers fall back to the existing resolution chain (llm_module → env vars).
Node types updated:
SearchVectorembedding_model,embedding_providerProcessFileEmbeddingembedding_model,embedding_providerProcessImageEmbeddingembedding_model,embedding_providerProcessChunksembedding_model,embedding_providerSearchUnified(embedding sub-config)embedding_model,embedding_providerProcessExtractionextraction_model,extraction_providerCompanion PR: The SQL generator and seed changes that consume these parameters are in constructive-db
feat/embedding-model-config.Review & Testing Checklist for Human
embedding_model/embedding_providervsextraction_model/extraction_provider) match what the constructive-db SQL generators extract fromdata->>'...'SearchUnified.embeddingnesting is correct — the new params should be siblings offield_name,dimensions,chunks, etc. inside theembeddingproperties object, not at the top levelbase_urlparameter was accidentally included (intentionally excluded for billing bypass concerns)Notes
base_urlwas intentionally excluded per discussion — exposing it would allow users to bypass the inference billing system.Link to Devin session: https://app.devin.ai/sessions/64aab8157bae43e69f70f33c193dc903
Requested by: @pyramation