holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions
fleet-memory/hindsight-api-slim/hindsight_api/engine
History
Fabio Scarsi e7da7d0e4f
feat: local reranker FP16, bucket batching, and transformers 5.x compatibility (#588) 
Three independent, cumulative improvements to LocalSTCrossEncoder:

1. transformers 5.x compatibility patch for XLM-RoBERTa models (Jina v2)
2. FP16 inference (opt-in via HINDSIGHT_API_RERANKER_LOCAL_FP16)
3. Length-sorted bucket batching (opt-in via HINDSIGHT_API_RERANKER_LOCAL_BUCKET_BATCHING)

All behind .env switches with conservative defaults preserving current behavior.

Fixes #586, Closes #587
2026-03-16 15:38:33 +01:00
..
consolidation feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
directives feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
parsers feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
providers fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 2026-03-13 16:43:01 +01:00
reflect fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 2026-03-13 16:43:01 +01:00
retain feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
search feat: compound tag filtering via tag_groups (#562) 2026-03-13 14:30:11 +01:00
storage feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
__init__.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
cross_encoder.py feat: local reranker FP16, bucket batching, and transformers 5.x compatibility (#588) 2026-03-16 15:38:33 +01:00
db_budget.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
db_utils.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
embeddings.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
entity_resolver.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
interface.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
jina_mlx_reranker.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
llm_interface.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
llm_wrapper.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
memory_engine.py feat: compound tag filtering via tag_groups (#562) 2026-03-13 14:30:11 +01:00
operation_metadata.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
query_analyzer.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
response_models.py fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 2026-03-13 16:43:01 +01:00
task_backend.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
utils.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00