feat: HAProxy load balancing for multi-endpoint services - #23
Merged
Conversation
added 2 commits
June 3, 2026 16:15
…/OCR - Add HAProxy containers (supervisor, embedding, whisper, OCR) to docker-compose - Auto-detect *_ENDPOINTS env vars and override *_PATH to HAProxy URLs - roundrobin balancing with httpclose for even distribution - Health checks on /models and /health endpoints - Stats UI on ports 8404-8407 - Content handler MIME type support (BaseContentTypeHandler.get_mime_type) - Fix whisper transcription for non-WAV files (was hardcoding audio/wav) - Fix Docker build: use lock file for pinned dependency resolution - Fix warmup: skip Docling when OCR_PATH is remote - Add shared/utils.py with parse_endpoints and resolve helpers - Update docs: overview, quickstart, operations with HAProxy sections - 33 tests passing, ruff clean
…, and README - Updated quickstart.md distributed deployment diagram with HAProxy containers - Updated overview.md sequence diagram to show HAProxy in supervisor and embedding paths - Added multi-endpoint section to README quick start
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds HAProxy-based load balancing for multi-endpoint LLM, embedding, whisper, and OCR services. When *_ENDPOINTS env vars are set with comma-separated backend URLs, HAProxy containers start automatically and distribute requests across all backends. roundrobin balancing, health checks, stats UI. 33 tests passing, ruff clean.