market-ingest
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMarket Ingest
市场数据摄入
Fetch market data for a symbol, normalize to OHLCV vectors, and store with HNSW indexing for fast pattern search.
获取标的资产的市场数据,将其归一化为OHLCV向量,并通过HNSW索引存储以实现快速模式搜索。
When to use
使用场景
When you need to ingest raw market data (price and volume) for a symbol and prepare it for pattern detection and similarity search. This is the first step before running pattern detection or comparison.
当你需要摄入标的资产的原始市场数据(价格和成交量),并为模式检测和相似度搜索做准备时使用。这是运行模式检测或对比前的第一步。
Steps
步骤
- Fetch data -- retrieve OHLCV data for the symbol from the configured data source (REST API, CSV file, or manual input)
- Normalize -- convert raw prices to relative values:
- Open:
(open - prev_close) / prev_close - High:
(high - open) / open - Low:
(low - open) / open - Close:
(close - open) / open - Volume: Z-score against rolling mean/std
- Open:
- Vectorize -- encode each candle as a 64-dimension padded vector (5 normalized OHLCV values + padding)
- Store -- call to persist normalized OHLCV data in the
mcp__claude-flow__agentdb_hierarchical-storenamespace with symbol and date as keysmarket-data - Index -- call to add vectors to the HNSW index for nearest-neighbor search
mcp__claude-flow__ruvllm_hnsw_add - Report -- summarize: candles ingested, date range, price range, average volume
- 获取数据——从配置的数据源(REST API、CSV文件或手动输入)检索标的资产的OHLCV数据
- 归一化——将原始价格转换为相对值:
- 开盘价:
(open - prev_close) / prev_close - 最高价:
(high - open) / open - 最低价:
(low - open) / open - 收盘价:
(close - open) / open - 成交量:基于滚动均值/标准差计算Z-score
- 开盘价:
- 向量化——将每根K线编码为64维填充向量(5个归一化OHLCV值 + 填充值)
- 存储——调用,将归一化后的OHLCV数据以标的资产和日期为键,持久化存储在
mcp__claude-flow__agentdb_hierarchical-store命名空间中market-data - 索引——调用,将向量添加到HNSW索引中以支持最近邻搜索
mcp__claude-flow__ruvllm_hnsw_add - 报告——汇总信息:摄入的K线数量、日期范围、价格范围、平均成交量
CLI alternative
CLI替代方案
bash
npx @claude-flow/cli@latest memory store --namespace market-data --key "symbol-SYMBOL-DATE" --value "OHLCV_JSON"bash
npx @claude-flow/cli@latest memory store --namespace market-data --key "symbol-SYMBOL-DATE" --value "OHLCV_JSON"