feat(datasource): unify default embedding model on EmbeddingGemma - #1422
Open
vkehfdl1 wants to merge 1 commit into
Open
feat(datasource): unify default embedding model on EmbeddingGemma#1422vkehfdl1 wants to merge 1 commit into
vkehfdl1 wants to merge 1 commit into
Conversation
katok embeds KakaoTalk with a local EmbeddingGemma (embeddinggemma-300m-q4, 768-dim, 100+ languages). discrawl defaulted to bge-m3, which forced operators to pull and track two local embedding models. Default discrawl to embeddinggemma (served through Ollama) so every CLI-backed datasource shares one multilingual embedder. The other crawler CLIs (wacrawl, telecrawl, slacrawl, notcrawl) have no upstream semantic/vector search - slacrawl's internal/embed package is an explicit stub and the rest have no embedding code at all - so there is no semantic mode to enable on the AutoRAG side yet.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
DEFAULT_DISCRAWL_EMBEDDING_MODEL:bge-m3→embeddinggemma, unifying every CLI-backed datasource on the same EmbeddingGemma family katok uses for KakaoTalk (embeddinggemma-300m-q4, 768-dim, 100+ languages, fully local via Ollama)ollama pull embeddinggemma)Semantic support in the other crawlers — checked, not available
Whether wacrawl/telecrawl/slacrawl/notcrawl support semantic search upstream:
wacrawltelecrawlslacrawlinternal/embedis an explicit stub ("reserved for optional embedding support after the base crawler ... stable"); SPEC lists embeddings as "later"notcrawlSo there is no semantic mode to enable on the AutoRAG side for those four; they stay FTS-only until the upstream CLIs ship vectors. Discord (discrawl) remains the only crawler with semantic/hybrid, now on the unified EmbeddingGemma default.
Verification
bun run typecheckcleanbun run test— 90 files / 1298 tests passing@biomejs/biome@2.5.6 checkon changed files clean