vamseeachanta
vamseeachanta/workspace-hub
相关职业SOC
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill document-rag-pipeline-step-1-database-schema命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
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.
正在显示 SKILL.md
| name | document-rag-pipeline-step-1-database-schema |
| description | Sub-skill of document-rag-pipeline: Step 1: Database Schema (+5). |
| version | 1.1.0 |
| category | data |
| type | reference |
| scripts_exempt | true |
import sqlite3
from pathlib import Path
from datetime import datetime
def create_database(db_path):
"""Create SQLite database with full schema."""
conn = sqlite3.connect(db_path, timeout=30)
cursor = conn.cursor()
*See sub-skills for full details.*
## Step 2: PDF Text Extraction
```python
import fitz # PyMuPDF
def extract_pdf_text(pdf_path):
"""Extract text from PDF using PyMuPDF."""
try:
doc = fitz.open(pdf_path)
text_parts = []
for page_num in range(len(doc)):
*See sub-skills for full details.*
## Step 3: OCR for Scanned PDFs
```python
import fitz
import pytesseract
from PIL import Image
import io
def ocr_pdf(pdf_path, dpi=200):
"""OCR scanned PDF using Tesseract."""
try:
doc = fitz.open(pdf_path)
*See sub-skills for full details.*
## Step 4: Text Chunking
```python
def chunk_text(text, chunk_size=1000, overlap=200):
"""Split text into overlapping chunks."""
chunks = []
start = 0
text_len = len(text)
while start < text_len:
end = start + chunk_size
chunk = text[start:end]
*See sub-skills for full details.*
## Step 5: Embedding Generation
```python
from sentence_transformers import SentenceTransformer
import numpy as np
import pickle
import os
# Force CPU mode (for CUDA compatibility issues)
os.environ["CUDA_VISIBLE_DEVICES"] = ""
def create_embeddings(db_path, model_name='all-MiniLM-L6-v2', batch_size=100):
*See sub-skills for full details.*
## Step 6: Semantic Search
```python
def semantic_search(db_path, query, top_k=10, sample_size=50000):
"""Search for similar chunks using cosine similarity."""
# Force CPU mode
os.environ["CUDA_VISIBLE_DEVICES"] = ""
model = SentenceTransformer('all-MiniLM-L6-v2')
query_emb = model.encode(query, normalize_embeddings=True)
*See sub-skills for full details.*