feat(search): open_taki v2 protocol — LLM-powered extraction with parallel indexing#3036
Open
flash7777 wants to merge 2 commits into
Open
feat(search): open_taki v2 protocol — LLM-powered extraction with parallel indexing#3036flash7777 wants to merge 2 commits into
flash7777 wants to merge 2 commits into
Conversation
Auto-detect open_taki as drop-in Tika replacement. When detected, uses v2 protocol for LLM-powered extraction with routing: - Meta (title, entities, summary) → always bleve - Content → bleve or vector-only based on routing config - Embedding → returned for vector DB integration - Graceful fallback to classic Tika v1 if v2 fails Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When open_taki is detected, IndexSpace uses a configurable worker pool for parallel extraction instead of sequential processing. This leverages the LLM backend's batch capacity (vLLM max-num-seqs=16). - 8 workers by default (configurable via SEARCH_EXTRACTOR_TIKA_MAX_WORKERS) - Only active with open_taki v2 (classic Tika stays sequential) - Workers use direct upsert (no batch, thread-safe) - IsTaki() exported on Tika extractor for runtime detection Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Up to standards ✅🟢 Issues
|
| Metric | Results |
|---|---|
| Duplication | 0 |
NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Drop-in support for open_taki as Apache Tika replacement. When open_taki is detected at the configured Tika URL, the search service automatically uses the v2 protocol for enhanced extraction with parallel indexing.
No config changes needed — same
SEARCH_EXTRACTOR_TIKA_TIKA_URLenv var. Just point it at an open_taki instance instead of Apache Tika.What open_taki provides over Tika
Changes
content/content.go—TakiExtractionstruct inDocument(method, summary, entities, embedding, routing)content/tika.go— Auto-detect open_taki via/tikahealth endpoint. When detected:X-Taki-Protocol: v2with feature headerssearch/service.go— ParallelIndexSpacewhen taki v2 detected:SEARCH_EXTRACTOR_TIKA_MAX_WORKERS, default 8)routing.content_target=vectorconfig/content.go+defaults/defaultconfig.go—MaxWorkersconfig fieldBackward compatible
MaxWorkersoptional (default 8)Tested
Deployed and tested on cloud.brandis.eu with OpenCloud kosmos edition: