@sap-ux/fiori-docs-embeddings 1.0.1 → 1.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -4
- package/data/embeddings/embeddings.bin +0 -0
- package/data/embeddings/metadata.json +2 -2
- package/data/embeddings/records.jsonl +749 -0
- package/index.d.ts +5 -0
- package/package.json +6 -5
- package/data/embeddings/documents_000.lance/_transactions/0-6825d769-a2cc-4ac7-8564-832013613cc0.txn +0 -0
- package/data/embeddings/documents_000.lance/_versions/1.manifest +0 -0
- package/data/embeddings/documents_000.lance/data/a288f3e6-3af0-4671-b4a9-1552dca642b7.lance +0 -0
- package/data/embeddings/table_index.json +0 -8
package/README.md
CHANGED
|
@@ -27,7 +27,7 @@ https://www.npmjs.com/package/@sap/ux-ui5-tooling (@sap/ux-ui5-tooling documenta
|
|
|
27
27
|
|
|
28
28
|
- Parses markdown, JSON, TypeScript, and other file types
|
|
29
29
|
- Generates AI-powered vector embeddings using transformers
|
|
30
|
-
- Stores embeddings in a
|
|
30
|
+
- Stores embeddings in a flat binary vector store (`embeddings.bin` + `records.jsonl`)
|
|
31
31
|
- Provides tools for semantic and keyword search across documentation
|
|
32
32
|
|
|
33
33
|
## Installation
|
|
@@ -88,7 +88,7 @@ Generated data is organized as:
|
|
|
88
88
|
```
|
|
89
89
|
data/
|
|
90
90
|
├── docs/ # Parsed documentation files
|
|
91
|
-
├── embeddings/ #
|
|
91
|
+
├── embeddings/ # Flat binary vector store (embeddings.bin, records.jsonl, metadata.json)
|
|
92
92
|
└── search/ # Search indexes
|
|
93
93
|
```
|
|
94
94
|
|
|
@@ -96,8 +96,8 @@ data/
|
|
|
96
96
|
|
|
97
97
|
- **Multi-source indexing** - Supports GitHub repositories and JSON APIs
|
|
98
98
|
- **File type support** - Markdown, JSON, TypeScript, JavaScript, XML, YAML, and more
|
|
99
|
-
- **Vector embeddings** - Uses
|
|
100
|
-
- **Local storage** - All data stored locally
|
|
99
|
+
- **Vector embeddings** - Uses `@huggingface/transformers` with the `Xenova/all-MiniLM-L6-v2` model (q8 quantized)
|
|
100
|
+
- **Local storage** - All data stored locally as a flat binary vector store (no native database dependency)
|
|
101
101
|
- **Caching** - Intelligent caching to avoid unnecessary API calls
|
|
102
102
|
- **Chunking** - Smart document chunking for optimal embedding generation
|
|
103
103
|
|
|
Binary file
|