From f68f45f3a2d1a5270b3aa608ef90b512e30876e5 Mon Sep 17 00:00:00 2001 From: Research Assistant Date: Mon, 25 May 2026 16:42:11 +0800 Subject: [PATCH] fix: improve search accuracy with multi-token LIKE and guided agent search queries - _like_query: split multi-token queries into per-field AND matching - lookup_paper: same multi-token AND for title lookup - read-known-paper.md: restructure Step 1 by known-info type (zotero_key, DOI, author+year, title keyword, fuzzy) - discover-papers.md Arm 2: note on author+year search pattern - retrieval-routing.md Arm 2: same author+year search guidance --- paperforge/memory/fts.py | 17 ++++++++-- paperforge/memory/query.py | 14 ++++++--- .../paperforge/atoms/retrieval-routing.md | 1 + .../paperforge/molecules/discover-papers.md | 1 + .../paperforge/molecules/read-known-paper.md | 31 ++++++++++++++----- 5 files changed, 49 insertions(+), 15 deletions(-) diff --git a/paperforge/memory/fts.py b/paperforge/memory/fts.py index 4a760b08..19c5f499 100644 --- a/paperforge/memory/fts.py +++ b/paperforge/memory/fts.py @@ -82,7 +82,18 @@ def _fts_query(conn, query, filter_clause, filter_params, limit): def _like_query(conn, query, filter_clause, filter_params, limit): - like_param = f"%{query}%" + tokens = re.findall(r"[\w\u4e00-\u9fff]+", query) + if not tokens: + tokens = [query] + + field_clauses = [] + params = [] + for field in ["p.title", "p.abstract", "p.doi", "p.citation_key"]: + token_clauses = [f"{field} LIKE ?" for _ in tokens] + params.extend(f"%{t}%" for t in tokens) + field_clauses.append("(" + " AND ".join(token_clauses) + ")") + + where_clause = "(" + " OR ".join(field_clauses) + ")" sql = f""" SELECT p.zotero_key, p.citation_key, p.title, p.year, p.doi, p.first_author, p.journal, p.domain, p.lifecycle, @@ -90,10 +101,10 @@ def _like_query(conn, query, filter_clause, filter_params, limit): substr(p.abstract, 1, 300) as abstract, 0 as rank FROM papers p - WHERE (p.title LIKE ? OR p.abstract LIKE ? OR p.doi LIKE ? OR p.citation_key LIKE ?){filter_clause} + WHERE {where_clause}{filter_clause} ORDER BY p.year DESC LIMIT ? """ conn.row_factory = sqlite3.Row - rows = conn.execute(sql, [like_param, like_param, like_param, like_param] + filter_params + [limit]).fetchall() + rows = conn.execute(sql, params + filter_params + [limit]).fetchall() return [dict(r) for r in rows] diff --git a/paperforge/memory/query.py b/paperforge/memory/query.py index 5e0df910..c2b8c3a5 100644 --- a/paperforge/memory/query.py +++ b/paperforge/memory/query.py @@ -2,6 +2,7 @@ from __future__ import annotations import json import logging +import re from pathlib import Path from paperforge.memory.builder import compute_hash @@ -79,7 +80,7 @@ def get_memory_status(vault: Path) -> dict: def _entry_from_row(row) -> dict: """Reconstruct an entry dict from a papers row (sqlite3.Row).""" - entry = {k: row[k] for k in row.keys()} + entry = {k: row[k] for k in row} for key in ("has_pdf", "do_ocr", "analyze"): if key in entry and entry[key] is not None: entry[key] = bool(entry[key]) @@ -108,11 +109,16 @@ def lookup_paper(conn, query: str) -> list[dict]: if row: return [_entry_from_row(row)] + tokens = re.findall(r"[\w\u4e00-\u9fff]+", q) + if not tokens: + tokens = [q] + title_conditions = " AND ".join("LOWER(title) LIKE ?" for _ in tokens) + title_params = [f"%{t.lower()}%" for t in tokens] rows = conn.execute( - """SELECT * FROM papers - WHERE LOWER(title) LIKE '%' || LOWER(?) || '%' + f"""SELECT * FROM papers + WHERE {title_conditions} LIMIT 20""", - (q,), + title_params, ).fetchall() if rows: return [_entry_from_row(r) for r in rows] diff --git a/paperforge/skills/paperforge/atoms/retrieval-routing.md b/paperforge/skills/paperforge/atoms/retrieval-routing.md index a78a6c52..f021345b 100644 --- a/paperforge/skills/paperforge/atoms/retrieval-routing.md +++ b/paperforge/skills/paperforge/atoms/retrieval-routing.md @@ -56,6 +56,7 @@ $PYTHON -m paperforge --vault "$VAULT" search "" --json --limit 30 - Uses FTS5 on title, abstract, authors, journal, domain, collection_path - Fast, always works - Limit 30 by default; user can request more +- **Author+year search**: put author name in ``, year in `--year-from`/`--year-to` (e.g. `search "Brighton" --year-from 1983 --year-to 1983`) #### Arm 3 — Collection/domain inventory (full list, no truncation) diff --git a/paperforge/skills/paperforge/molecules/discover-papers.md b/paperforge/skills/paperforge/molecules/discover-papers.md index 40e5ac05..5381a485 100644 --- a/paperforge/skills/paperforge/molecules/discover-papers.md +++ b/paperforge/skills/paperforge/molecules/discover-papers.md @@ -68,6 +68,7 @@ $PYTHON -m paperforge --vault "$VAULT" search "" --json --limit 30 \ - FTS5 搜索标题、摘要、作者、期刊、domain、collection 路径 - 返回 JSON：`data.matches[]` 包含 `zotero_key`、`title`、`year`、`first_author` 等 +- **作者+年份搜索**：query 放作者名，年份放 `--year-from`/`--year-to`（如 `search "Brighton" --year-from 1983 --year-to 1983`） #### Arm 3 — Collection/Domain 列举（完整列表，不截断） diff --git a/paperforge/skills/paperforge/molecules/read-known-paper.md b/paperforge/skills/paperforge/molecules/read-known-paper.md index d3fc3248..e307b113 100644 --- a/paperforge/skills/paperforge/molecules/read-known-paper.md +++ b/paperforge/skills/paperforge/molecules/read-known-paper.md @@ -25,31 +25,46 @@ ### Step 1: 定位论文 -用户可能给 zotero_key、DOI、标题片段、作者+年份。按以下方式查找： +用户可能给 zotero_key、DOI、标题关键词、作者+年份。按以下方式查找： -**如果用户给的是 zotero_key：** +**如果知道 zotero_key：** ```bash $PYTHON -m paperforge --vault "$VAULT" paper-context --json ``` -返回 JSON 包含 paper 元数据、OCR 状态、prior_notes 等。 +**如果知道 DOI：** -**如果用户给的是 DOI、标题片段、作者+年份，先解析成候选：** +```bash +$PYTHON -m paperforge --vault "$VAULT" paper-context --json +``` + +**如果知道 作者+年份：** + +```bash +$PYTHON -m paperforge --vault "$VAULT" search "" --year-from --year-to --json --limit 10 +``` + +**如果知道 标题关键词：** + +```bash +$PYTHON -m paperforge --vault "$VAULT" search "<关键词>" --json --limit 10 +``` + +**如果只有模糊描述：** ```bash $PYTHON -m paperforge --vault "$VAULT" paper-status "" --json ``` -如果 `paper-status` 直接唯一命中，取返回的 `zotero_key` 再调 `paper-context`。 - -**paper-status 无法唯一定位时的备选：** +如果无唯一命中： ```bash $PYTHON -m paperforge --vault "$VAULT" search "" --json --limit 5 ``` -如果多候选，列出让用户选；用户选定后，再用选中的 `zotero_key` 调 `paper-context`。 +无论哪种方式命中，取 `zotero_key` 调 `paper-context` 获取完整信息。 +如果多候选，列出让用户选。 如果无结果，告知用户并停止。 ### Step 2: 加载文献内容