2 个仓库
Maintains pandas DataFrames and other rich data structures across conversation turns for iterative analysis.
Distinct from Structured Data Management: Distinct from Structured Data Management: focuses on preserving in-memory data structures across conversational turns rather than defining application-level data schemas.
Explore 2 awesome GitHub repositories matching data & databases · Session-Persistent DataFrames. Refine with filters or upvote what's useful.
TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the
TaskWeaver maintains rich data structures like pandas DataFrames across conversation turns for iterative analysis.
dtale 是一个基于 Web 的 pandas 数据框交互式网格与可视化工具,设计为探索性数据分析工具。它提供了一个基于浏览器的界面用于分析表格数据结构,允许用户在无需编写手动代码的情况下计算统计数据、检测异常值并计算相关性。 该项目作为嵌入式数据查看器运行,可通过 iframe 或自定义路由集成到 Web 应用中,并对 Django、Flask 与 Streamlit 提供特定支持。它通过交互式数据网格与能够生成直方图、箱线图与 3D 散点图的数据可视化库的组合,实现了对数据集的探索。 该平台涵盖了广泛的数据管理与分析能力,包括表格数据清理、重塑与交互式过滤。它包括用于缺失数据分析、相关性计算与预测能力评分的观测工具。对于会话管理,它支持多实例追踪与跨并发工作进程的状态持久化。 该界面受用户名与密码认证保护,并支持从分隔文件、电子表格与 ArcticDB 数据存储中进行数据摄入。
Persists and shares the state of analyzed pandas DataFrames across multiple sessions or worker processes.