feat: funciones Python datascience, finance, cybersecurity y pipelines

Datascience: aggregate_by_group, deduplicate_entities/relations, detect_drift, diff_entities/relations, extract_entities/relations_llm, hotness_score, melt, merge_graphs, pivot, build_entity/relation_schema_prompt. Finance: avellaneda_stoikov_quotes, generate_gbm_prices, generate_taker_order, hawkes_intensity + módulo finance.py. Cybersecurity: envelope_encrypt/decrypt + módulo cybersecurity.py. Pipelines: extraction_pipeline, monte_carlo_market, run_market_sim. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 17:11:32 +02:00
parent 928a3319d5
commit 837563c3ba
62 changed files with 5376 additions and 0 deletions
@@ -0,0 +1,43 @@
+"""Genera la seccion del system prompt que describe los entity types disponibles para extraccion."""
+
+
+def build_entity_schema_prompt(entity_presets: list[dict]) -> str:
+    """Genera texto legible para el LLM describiendo los entity types disponibles.
+
+    Formatea los presets del registry en una seccion del system prompt que indica
+    al LLM que tipos de entidades puede extraer y que atributos tiene cada uno.
+
+    Args:
+        entity_presets: Lista de presets con campos 'label', 'type_ref' y
+                        opcionalmente 'metadata_fields'. Ejemplo:
+                        [{"type_ref": "osint_person_go_cybersecurity",
+                          "label": "Person",
+                          "metadata_fields": ["full_name", "alias"]}]
+
+    Returns:
+        String formateado con la seccion del prompt. Retorna string vacio si
+        la lista de presets esta vacia.
+    """
+    if not entity_presets:
+        return ""
+
+    lines = ["Entity types available for extraction:", ""]
+
+    for i, preset in enumerate(entity_presets, start=1):
+        label = preset.get("label", "Unknown")
+        type_ref = preset.get("type_ref", "")
+        metadata_fields = preset.get("metadata_fields", [])
+
+        lines.append(f"{i}. {label} (type_ref: {type_ref})")
+
+        if metadata_fields:
+            attrs = ", ".join(metadata_fields)
+            lines.append(f"   Attributes: {attrs}")
+
+        lines.append("")
+
+    # Remove trailing blank line
+    if lines and lines[-1] == "":
+        lines.pop()
+
+    return "\n".join(lines)