Commit graph

8 commits

Author SHA1 Message Date
Nicolò Boschi
224b7b74c1
feat: accept pdf, images and office files (#390)
* feat: accept pdf, images and office files

* refactor: rename FileConverter to FileParser, simplify file retain API

- Rename engine/converters/ → engine/parsers/, FileConverter → FileParser,
  ConverterRegistry → FileParserRegistry, MarkitdownConverter → MarkitdownParser
- Rename env var HINDSIGHT_API_FILE_CONVERTER → HINDSIGHT_API_FILE_PARSER
- Remove async/document_tags params from FileRetainRequest (always async now)
- Add retain_files() to Python Hindsight client and retainFiles() to TypeScript client
- Add sample.pdf to doc examples for working file upload demonstrations
- Update test_file_retain.py to use new parser names and always-async behavior
- Fix Go client missing os import in api_files.go
- Simplify postgresql.py storage to minimal schema

* fix: update rust CLI tests to use is_supported_file instead of is_text_file

* fix: patch Go api_files.go to add missing 'os' import after generation

* fix: insert 'os' import after 'net/url' in api_files.go patch for correct position

* chore: regenerate OpenAPI spec and clients (converter→parser description update)
2026-02-17 18:15:03 +01:00
Nicolò Boschi
95c4220477
feat: support for pgvectorscale (DiskANN) (#378)
* feat: support for pgvectorscale (DiskANN)

* feat: support for pgvectorscale (DiskANN)
2026-02-16 14:19:56 +01:00
Nicolò Boschi
d871c3009d
feat: support timescale pg_textsearch as text search extension (#359)
* feat: support timescale pg_textsearch as text search extension

* refactor: deduplicate text search query in retrieve_semantic_bm25_combined

Instead of maintaining 3 complete query copies (native, vchord, pg_textsearch),
now we:
- Build backend-specific parts (score_expr, order_by, where_filter)
- Use a single query template with injected backend-specific parts

This makes maintenance easier - changes to the semantic CTE or overall structure
only need to be made once.
2026-02-12 17:38:13 +01:00
Nicolò Boschi
c029807add
feat: support for other text and vector search pg extensions (#355)
* feat: support for other text and vector search pg extensions

* test: increase timeout for test_batch_chunking_behavior to account for VectorChord BM25 tokenization overhead

* feat: support for other text and vector search pg extensions
2026-02-12 14:13:04 +01:00
Damien
a713b68b1f
Implement the vchord / pgvector support (#350)
* Implement the vchord / pgvector support

* feat(alembic): detect vector extension and create appropriate index
2026-02-12 10:47:07 +01:00
Nicolò Boschi
93ddd41621
feat: add reverse proxy support (#346)
* feat: add reverse proxy support

* improve

* improve

* improve

* improve

* improve

* fix: update integration test to use modern 'docker compose' command

- Replace 'docker-compose' with 'docker compose' (Docker Compose v2+)
- Add fallback to legacy docker-compose command for compatibility
- Fixes test failures on systems using Docker Compose plugin

* ci: trigger test rerun

* fix: make docker-compose detection more robust for CI

- Add get_docker_compose_command() to detect available command
- Use shutil.which() to check command availability
- Dynamically use correct command (docker compose vs docker-compose)
- Should work in both modern and legacy Docker environments

* fix: docker-compose networking in base path integration test

Fix connection refused error in test_reverse_proxy_simple_config by
handling host vs bridge networking modes correctly:

- Linux (host mode): nginx listens on 18080 directly, no port mapping
- Mac/Windows (bridge mode): nginx listens on 80, mapped to 18080

With host networking, port mappings in docker-compose don't work since
the container binds directly to the host's network namespace.
2026-02-12 10:09:53 +01:00
Nicolò Boschi
a3a9d7b37d
doc: prepare doc for 0.4.10 (#325)
* doc: prepare doc for 0.4.10

* fixe

* ci
2026-02-09 11:42:37 +01:00
Van Vuong Ngo
5179d5f77d
feat: add docker-compose example (#313)
* feat: add docker-compose example

* fix T&V

* doc: add how to quick start hindsight with docker-compose

* chore: fix typo
2026-02-09 10:14:21 +01:00