mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-05 23:03:55 +00:00
lukaszraczylo
f79782a008
* Resolves issue #13 - Switched model to bge-small-en-v1.5 - Added lazy re-embedding - Added model version tracking per vector - Added conversion of vectors to the new model * Add lfs support to the workflow. * Implements importance scoring with decay + voting #6 * Resolves issue #5 by marking observations as superseeded and scheduled for deletion * Implement pattern detection #7 * Improve injections and observations accuracy - Session start: Recent observations for project context (recency-based) - User prompt: Semantically relevant observations (similarity-based with threshold) * Added two stage retrieval with bi and cross encoder #8 * Implement query expansion and reformulation #9 * Knowledge graph and relationships ( resolves #4 ) - File Overlap Detection: Detects relationships when observations modify/read the same files - Concept Overlap Detection: Detects relationships based on shared semantic concepts - Type Progression Detection: Infers relationships from natural observation type progressions (e.g., discovery → bugfix = "fixes") - Temporal Proximity Detection: Detects relationships between observations in the same session within 5 minutes - Narrative Mention Detection: Detects explicit relationship language in narratives (e.g., "fixes", "depends on", "supersedes") * Add visualisation of the relations to the dashboard. * fixup! Add visualisation of the relations to the dashboard. * Update documentation with new settings and screenshots.
58 lines
1.2 KiB
JSON
58 lines
1.2 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "[PAD]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100": {
|
|
"content": "[UNK]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"101": {
|
|
"content": "[CLS]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"102": {
|
|
"content": "[SEP]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"103": {
|
|
"content": "[MASK]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "[CLS]",
|
|
"do_basic_tokenize": true,
|
|
"do_lower_case": true,
|
|
"mask_token": "[MASK]",
|
|
"model_max_length": 512,
|
|
"never_split": null,
|
|
"pad_token": "[PAD]",
|
|
"sep_token": "[SEP]",
|
|
"strip_accents": null,
|
|
"tokenize_chinese_chars": true,
|
|
"tokenizer_class": "BertTokenizer",
|
|
"unk_token": "[UNK]"
|
|
}
|