Spaces:
Sleeping
Sleeping
merge: Integrate remote formatting changes with local fixes
Browse files
CHANGELOG.md
CHANGED
|
@@ -200,7 +200,7 @@ Each entry includes:
|
|
| 200 |
- **Notes**:
|
| 201 |
- **Integration Validation**: Complete text → embedding → storage → search workflow tested and working
|
| 202 |
- **End-to-End Testing**: Successfully validated EmbeddingService + VectorDatabase integration
|
| 203 |
-
- **Performance Verification**:
|
| 204 |
- **Quality Achievement**: 25+ new tests added, comprehensive error handling, full documentation
|
| 205 |
- **Foundation Complete**: ChromaDB + HuggingFace embeddings fully integrated and tested
|
| 206 |
- **Phase 2A Status**: ✅ COMPLETED SUCCESSFULLY - Ready for Phase 2B Enhanced Ingestion Pipeline
|
|
|
|
| 200 |
- **Notes**:
|
| 201 |
- **Integration Validation**: Complete text → embedding → storage → search workflow tested and working
|
| 202 |
- **End-to-End Testing**: Successfully validated EmbeddingService + VectorDatabase integration
|
| 203 |
+
- **Performance Verification**: Model caching working efficiently, operations observed to be fast (no timing recorded)
|
| 204 |
- **Quality Achievement**: 25+ new tests added, comprehensive error handling, full documentation
|
| 205 |
- **Foundation Complete**: ChromaDB + HuggingFace embeddings fully integrated and tested
|
| 206 |
- **Phase 2A Status**: ✅ COMPLETED SUCCESSFULLY - Ready for Phase 2B Enhanced Ingestion Pipeline
|
tests/test_embedding/test_embedding_service.py
CHANGED
|
@@ -144,7 +144,7 @@ def test_special_characters_handling():
|
|
| 144 |
service = EmbeddingService()
|
| 145 |
|
| 146 |
texts_with_special_chars = [
|
| 147 |
-
"Policy with
|
| 148 |
"Text with numbers: 123,456.78 and symbols @#$%",
|
| 149 |
"Markdown: # Header\n## Subheader\n- List item",
|
| 150 |
"Mixed: Policy-2024 (v1.2) — updated 12/01/2025",
|
|
|
|
| 144 |
service = EmbeddingService()
|
| 145 |
|
| 146 |
texts_with_special_chars = [
|
| 147 |
+
"Policy with emojis 😀 and úñicode",
|
| 148 |
"Text with numbers: 123,456.78 and symbols @#$%",
|
| 149 |
"Markdown: # Header\n## Subheader\n- List item",
|
| 150 |
"Mixed: Policy-2024 (v1.2) — updated 12/01/2025",
|