Commit graph

6 commits

Author SHA1 Message Date
Kagura
84985ee9bc
fix(reranker): use httpx for Cohere Azure endpoints to avoid 404 errors (#790)
When using Azure AI Foundry Cohere rerank endpoints, the Cohere SDK
incorrectly appends /v1/rerank to the base_url, but Azure endpoints
already include the full path (e.g., /models/.../invoke). This causes
double-pathing and 404 errors.

This commit modifies CohereCrossEncoder to detect when base_url is
provided and use httpx directly for custom endpoints, while keeping
the native Cohere SDK for standard API usage. The Azure Cohere API
response format is compatible with the native format.

Fixes #783

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-31 17:44:42 +02:00
Nicolò Boschi
e5209b18b3
docs: add RERANKER_ZEROENTROPY_BASE_URL to configuration page (#779)
Document the new configurable base URL for the ZeroEntropy reranker
provider added in #766. Also fix a type error where RERANK_URL was
renamed to rerank_url but one usage was missed.
2026-03-30 17:51:04 +02:00
Timur Iskhakov
a915584e39
feat: add configurable base URL for ZeroEntropy reranker (#766) 2026-03-30 17:43:19 +02:00
Nicolò Boschi
d2bfa84bca
docs: add config vars for local reranker FP16 and bucket batching (#589)
* docs: add config vars for local reranker FP16 and bucket batching (#588)

* fix: add missing reranker local fields to CLI config override and fix ty type error

- Add reranker_local_fp16, reranker_local_bucket_batching, reranker_local_batch_size
  to the manual HindsightConfig() constructor call in main.py (CLI override block)
- Replace direct module attribute assignment with setattr() in the transformers 5.x
  monkey-patch so ty can resolve it without raising unresolved-attribute
2026-03-16 17:35:09 +01:00
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
Nicolò Boschi
15ea23d5d6
feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560)
* feat: introduce hindsight-api-slim and hindsight-all-slim packages

Closes #552

- Move all source code from hindsight-api/ to new hindsight-api-slim/
- hindsight-api-slim has heavy ML deps (torch, sentence-transformers,
  transformers, einops, flashrank, mlx, mlx-lm, safetensors) and
  pg0-embedded as optional extras: [local-ml], [embedded-db], [all]
- hindsight-api becomes a zero-code meta-package depending on
  hindsight-api-slim[all] for full backward compatibility
- Add hindsight-all-slim meta-package: hindsight-api-slim + client + embed
- hindsight-all updated to depend on hindsight-api-slim[all]
- pg0.py: lazy-import pg0 with clear ImportError pointing to [embedded-db]
- Dockerfile: replace sed hack with proper uv sync --extra flags
- Update release.yml, test.yml, lint.sh, release.sh, CLAUDE.md and
  all path references throughout the repo

* refactor: rename hindsight/ directory to hindsight-all/

* docs: document hindsight-api-slim and hindsight-all-slim package variants

Add package variants table and extras explanation to installation.md

* docs: remove emojis from installation.md, use professional tone

* docs: link Docker slim variant to pip package variants section

* docs: consolidate Docker image variants into single table

* ci: fix working-directory paths after package restructure

- Replace all hindsight-api → hindsight-api-slim in test.yml
- Replace hindsight → hindsight-all in test.yml
- Add --extra embedded-db to test-embed API install step

* ci: add local-ml and embedded-db extras to API sync steps

These extras were previously implicit in the old hindsight-api package
(which bundled everything). Now that hindsight-api-slim uses optional
extras, we must explicitly request local-ml and embedded-db in CI.

* ci: add API install step with embedded-db to test-embed smoke test

The smoke test starts hindsight-api as a daemon, which requires pg0-embedded.
Add a dedicated install step for hindsight-api-slim with embedded-db extra
so the daemon can start successfully.

* ci: remove --no-install-project when using optional extras

When --no-install-project is combined with --extra, the optional deps
are not installed because extras require the project to be active.
Remove --no-install-project from steps that need local-ml or embedded-db.

* ci: fix ordering of uv sync steps to preserve optional extras

When uv sync runs for a different workspace member, it removes optional
extras installed for other members. Fix by always running extra-requiring
API sync last, after other workspace member syncs.

Also remove --no-install-project from embedded-db sync in test-embed,
as --no-install-project prevents optional extras from being active.

* ci: add local-ml extra to test-embed API install for smoke test

The smoke test starts the full API server which needs sentence-transformers
for local embeddings (default provider). Add local-ml extra to the install.

* ci: simplify extras with --all-extras and add slim pip smoke test

- Replace explicit --extra local-ml --extra embedded-db with --all-extras
  for cleaner, more maintainable sync steps
- Add test-pip-slim job: tests hindsight-api-slim[embedded-db] without
  local ML models, using Cohere for embeddings/reranking (mirrors Docker
  slim smoke test approach)

* ci: simplify slim smoke test to health check only (mirrors Docker test)
2026-03-13 13:50:03 +01:00
Renamed from hindsight-api/hindsight_api/engine/cross_encoder.py (Browse further)