15ea23d5d6
* 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)
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
"""
|
|
Test chunking functionality for large documents.
|
|
"""
|
|
import pytest
|
|
from hindsight_api.engine.retain.fact_extraction import chunk_text
|
|
|
|
|
|
def test_chunk_text_small():
|
|
"""Test that small text is not chunked."""
|
|
text = "This is a short text. It should not be chunked."
|
|
chunks = chunk_text(text, max_chars=1000)
|
|
|
|
assert len(chunks) == 1, "Small text should not be chunked"
|
|
assert chunks[0] == text
|
|
|
|
|
|
def test_chunk_text_large():
|
|
"""Test that large text is chunked at sentence boundaries."""
|
|
# Create a text with 10 sentences of ~100 chars each
|
|
sentences = [f"This is sentence number {i}. " + "x" * 80 for i in range(10)]
|
|
text = " ".join(sentences)
|
|
|
|
# Chunk with max 300 chars - should create multiple chunks
|
|
chunks = chunk_text(text, max_chars=300)
|
|
|
|
assert len(chunks) > 1, "Large text should be chunked"
|
|
|
|
# Verify all chunks are under the limit
|
|
for chunk in chunks:
|
|
assert len(chunk) <= 300, f"Chunk exceeds max_chars: {len(chunk)}"
|
|
|
|
# Verify we didn't lose any content
|
|
combined = " ".join(chunks)
|
|
# Account for possible whitespace differences
|
|
assert len(combined.replace(" ", "")) >= len(text.replace(" ", "")) * 0.95
|
|
|
|
|
|
def test_chunk_text_64k():
|
|
"""Test chunking a 64k character text (like a podcast transcript)."""
|
|
# Create a 64k character text
|
|
sentence = "This is a typical podcast conversation sentence. "
|
|
text = sentence * (64000 // len(sentence))
|
|
|
|
chunks = chunk_text(text, max_chars=120000)
|
|
|
|
# Should create at least 1 chunk (if text fits) or more
|
|
assert len(chunks) >= 1
|
|
|
|
# All chunks should be under the limit
|
|
for chunk in chunks:
|
|
assert len(chunk) <= 120000, f"Chunk exceeds max_chars: {len(chunk)}"
|
|
|
|
# Verify we didn't lose content
|
|
combined_length = sum(len(chunk) for chunk in chunks)
|
|
assert combined_length >= len(text) * 0.95, "Lost too much content during chunking"
|
|
|