File size: 4,212 Bytes
325b94c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | from typing import List
import time
# =========================
# Query Bundle Builder
# =========================
def build_query_bundle(sub: dict, chapter_title: str, section_title: str) -> List[str]:
planning = sub.get("planning", {})
queries = []
if planning.get("core_idea"):
queries.append(planning["core_idea"])
for kp in planning.get("key_points", [])[:3]:
if isinstance(kp, str):
queries.append(kp)
for q in sub.get("suggested_queries", [])[:2]:
queries.append(q)
queries.append(sub.get("title", ""))
queries.append(f"{chapter_title} - {section_title}")
seen = set()
final = []
for q in queries:
q = q.strip()
if q and q not in seen:
seen.add(q)
final.append(q)
return final
# =========================
# Citations
# =========================
def make_in_text_citation(author, year, page_start):
a = author or "مؤلف"
y = year if isinstance(year, int) else "د.ت"
p = page_start if isinstance(page_start, int) else "؟"
return f"({a}، {y}، ص {p})"
def make_reference_apa(author, year, title):
a = author or "مؤلف"
y = year if isinstance(year, int) else "د.ت"
t = title or "مصدر بدون عنوان"
return f"{a}. ({y}). {t}."
# =========================
# RAG for Subsection (MULTI-BOOK)
# =========================
def build_rag_context_for_subsection(
rag_engines: List,
sub: dict,
chapter_title: str,
section_title: str,
top_k: int = 5,
) -> dict:
queries = build_query_bundle(sub, chapter_title, section_title)
all_hits = []
# 🔥 search in ALL source books
for rag in rag_engines:
hits = rag.retrieve(queries=queries)
all_hits.extend(hits)
if not all_hits:
return {
"query_bundle": queries,
"selected_k": 0,
"chunks": [],
"coverage_note": "لم يتم العثور على مراجع مناسبة لهذا المحور.",
}
# sort globally
all_hits = sorted(all_hits, key=lambda x: x.score, reverse=True)[:top_k]
chunks = []
for h in all_hits:
payload = h.payload or {}
chunks.append(
{
"chunk_id": h.id,
"score": h.score,
"doc_id": payload.get("doc_id"),
"page_start": payload.get("page_start"),
"page_end": payload.get("page_end"),
"title": payload.get("title"),
"author": payload.get("author"),
"year": payload.get("year"),
"text": payload.get("text"),
"in_text_citation": make_in_text_citation(
payload.get("author"),
payload.get("year"),
payload.get("page_start"),
),
"reference_apa": make_reference_apa(
payload.get("author"),
payload.get("year"),
payload.get("title"),
),
}
)
return {
"query_bundle": queries,
"selected_k": len(chunks),
"chunks": chunks,
"coverage_note": "تم اختيار أفضل المراجع المتوافقة مع فكرة المحور وحدوده.",
}
# =========================
# Book-Level Automation
# =========================
def run_rag_automation_on_book(
planned_book: dict,
rag_engines: List,
top_k: int = 5,
sleep_s: float = 0.1,
) -> dict:
for chapter in planned_book.get("chapters", []):
ch_title = chapter.get("chapter_title", "")
for section in chapter.get("sections", []):
sec_title = section.get("title", "")
for sub in section.get("subsections", []):
rag_context = build_rag_context_for_subsection(
rag_engines=rag_engines,
sub=sub,
chapter_title=ch_title,
section_title=sec_title,
top_k=top_k,
)
sub["rag_context"] = rag_context
time.sleep(sleep_s)
return planned_book
|