메뉴
Sub-skill of document-rag-pipeline: Build Knowledge Base (+2).
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/vamseeachanta/workspace-hub --skill document-rag-pipeline-build-knowledge-base명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | document-rag-pipeline-build-knowledge-base |
| description | Sub-skill of document-rag-pipeline: Build Knowledge Base (+2). |
| version | 1.1.0 |
| category | data |
| type | reference |
| scripts_exempt | true |
# Full pipeline with OCR and embeddings
python build_knowledge_base.py /path/to/documents --embed
# Skip OCR (faster, text PDFs only)
python build_knowledge_base.py /path/to/documents --no-ocr --embed
# Just build inventory (no extraction)
python build_knowledge_base.py /path/to/documents
# Semantic search
python build_knowledge_base.py /path/to/documents --search "subsea wellhead design"
# More results
python build_knowledge_base.py /path/to/documents --search "fatigue analysis" --top-k 20
#!/bin/bash
# search_docs.sh - Quick semantic search
DB_PATH="${1:-/path/to/_inventory.db}"
QUERY="$2"
CUDA_VISIBLE_DEVICES="" python3 -c "
import sqlite3, pickle, numpy as np
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')
query_emb = model.encode('$QUERY', normalize_embeddings=True)
conn = sqlite3.connect('$DB_PATH')
cursor = conn.cursor()
cursor.execute('''
SELECT tc.chunk_text, tc.embedding, d.filename
FROM text_chunks tc
JOIN documents d ON tc.document_id = d.id
WHERE tc.embedding IS NOT NULL
ORDER BY RANDOM() LIMIT 50000
''')
results = []
for text, emb_blob, filename in cursor.fetchall():
emb = pickle.loads(emb_blob)
sim = float(np.dot(query_emb, emb))
results.append((sim, filename, text[:200]))
for score, fname, text in sorted(results, reverse=True)[:10]:
print(f'[{score:.3f}] {fname}')
print(f' {text}...\n')
"