feat: implement local code scout, training pipeline, and MCP tools

This commit is contained in:
emil28092005
2026-09-16 03:57:09 +03:00
parent 2e5ab98c56
commit ba24db2be5
33 changed files with 4347 additions and 27 deletions
+58
View File
@@ -0,0 +1,58 @@
{
"dataset": "code-search-net/code_search_net",
"revision": "bd0cf261e357a3eb5c8fba490d23ec1a1cd59555",
"seed": 17,
"selection": "seeded hash priority, maximum 200 samples per repository",
"normalization": "remove Python docstrings/comments; first documentation paragraph",
"deduplication": "repository, exact token hash, normalized token hash, exact query hash",
"splits": {
"test": {
"source_rows": 22176,
"filtered_quality": 1930,
"selected": 3000,
"repositories": 444,
"max_repository_examples": 200,
"source_sha256": "3167e79ee7f081d825bf97b96d3a6b2d96428b00f6a98125be943384d8afae5f",
"prepared_sha256": "b9e150337e195838efb5fe3f4ecafd63dfa99a55cf3635764c893912f4747596"
},
"validation": {
"source_rows": 23107,
"filtered_quality": 2560,
"overlap_query_hash": 4,
"overlap_structural_hash": 22,
"selected": 2000,
"repositories": 397,
"max_repository_examples": 65,
"source_sha256": "22eaacb46ed7e74d582409b85692ef63f5a43e99f9395c2eb736b5c8451422bb",
"prepared_sha256": "e1b934c33f12322e4a56d0d17a987966c40961b035e15939fd716b76d4e017a2"
},
"train": {
"source_rows": 412178,
"filtered_quality": 45464,
"overlap_structural_hash": 626,
"overlap_query_hash": 220,
"selected": 30000,
"repositories": 6819,
"max_repository_examples": 200,
"source_sha256": "ad9e3a4ab10c2c1d8926d2b26ca2bfcc3aadda1477ba29a933391f93806b9fed",
"prepared_sha256": "3eeed3185b74f934462aaccbd3c567f8db20754a1bf6f5f3686779f8b39f4338"
}
},
"overlap_audit": {
"train/validation/id": 0,
"train/validation/repo": 0,
"train/validation/code_hash": 0,
"train/validation/structural_hash": 0,
"train/validation/query_hash": 0,
"train/test/id": 0,
"train/test/repo": 0,
"train/test/code_hash": 0,
"train/test/structural_hash": 0,
"train/test/query_hash": 0,
"validation/test/id": 0,
"validation/test/repo": 0,
"validation/test/code_hash": 0,
"validation/test/structural_hash": 0,
"validation/test/query_hash": 0
}
}
+14
View File
@@ -0,0 +1,14 @@
{
"training_examples": 30000,
"query_word_quantiles": [
5.0,
9.0,
23.0
],
"nonempty_code_line_quantiles": [
4.0,
9.0,
29.0
],
"queries_still_present_in_code": 0
}
+12
View File
@@ -0,0 +1,12 @@
{
"split": "validation",
"queries": 2000,
"candidates": 2000,
"method": "bm25",
"mrr": 0.6081888214934283,
"mrr_at_10": 0.6021025793650794,
"recall_at_1": 0.526,
"recall_at_5": 0.7045,
"recall_at_10": 0.755,
"median_rank": 1.0
}