dataforge/fn_registry
1
0
Fork 0
Code Issues Pull Requests 3 Actions Packages Projects Releases Wiki Activity

chore: auto-commit (799 archivos)

Browse Source 
- .claude/CLAUDE.md
- .claude/commands/subagentes.md
- .claude/rules/INDEX.md
- .mcp.json
- bash/functions/cybersecurity/analyze_dns.md
- bash/functions/cybersecurity/audit_http_headers.md
- bash/functions/cybersecurity/audit_ssh_config.md
- bash/functions/cybersecurity/check_firewall.md
- bash/functions/cybersecurity/detect_suspicious_users.md
- bash/functions/cybersecurity/encrypt_file.md
- ...

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Egutierrez
2026-05-14 00:28:20 +02:00
parent d110aa40f9
commit cfdf515228
805 changed files with 5515 additions and 810 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/functions/pipelines/extraction_pipeline.md
+1 -1
View File
@@ -7,7 +7,7 @@ version: "1.0.0"
purity: impure
signature: "def extraction_pipeline(file_path: str, entity_presets: list[dict], relation_types: list[str], llm_chat_json: Callable[[list[dict]], dict], chunk_size: int = 500, chunk_overlap: int = 50, confidence_threshold: float = 0.5, dedup_threshold: float = 0.85, on_progress: Callable[[str, float], None] | None = None) -> ExtractionResult"
description: "Pipeline completa de extraccion de entidades y relaciones desde un documento. Orquesta extract_text_from_file -> preprocess_text -> split_text_into_chunks -> extract_entities_llm por chunk -> deduplicate_entities -> extract_relations_llm por chunk -> deduplicate_relations."
tags: [pipeline, extraction, entities, relations, llm, nlp, fuzzygraph, datascience]
tags: [pipeline, extraction, entities, relations, llm, nlp, fuzzygraph, datascience, pendiente-usar]
uses_functions:
- extract_text_from_file_py_core
- preprocess_text_py_core