skills.rest
hiyenwong
hiyenwongCOMMUNITY
Explore all skills by this author →
𝕏@khonsu_51GitHub

chat-history-lancedb

Store and search chat histories locally with LanceDB vector embeddings and RAG retrieval.

2|Updated Feb 12, 2026
Search Tags:#embeddings#rag#session-management#lancedb#vector-search#chat-history
One-click install
npx skills add https://github.com/hiyenwong/ai_collection --skill chat-history-lancedb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chat-history-lancedb
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/chat-history-lancedb
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill chat-history-lancedb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

LanceDB-based chat history management solves the challenge of locally storing and quickly retrieving conversations, including vector-based search and context-aware retrieval (RAG).

Core Features & Use Cases

  • Local LanceDB storage to maintain chat histories with timestamps and session metadata.
  • Vector-based semantic search and RAG context retrieval to surface relevant conversations across sessions.
  • CLI-driven workflows for creating sessions, saving messages, exporting/importing sessions, and building contextual prompts.

Quick Start

Install dependencies, build, then run the CLI to create a session and start saving messages.

Frequently Asked Questions about chat-history-lancedb

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I store chat history locally for offline RAG retrieval?▼

Store chat history locally by saving conversations with timestamps and session metadata into a LanceDB database. This enables offline access and provides a foundation for RAG retrieval using vector embeddings.

How does vector-based semantic search work across past chat sessions?▼

Vector-based semantic search converts saved messages into embeddings, allowing you to query past chat sessions by meaning rather than exact text. This surfaces relevant conversations across different sessions for context discovery.

Do I need an embedding provider to manage local chat histories with LanceDB?▼

Yes, an embedding provider is required. It generates the vector embeddings from your chat messages needed to perform semantic search and RAG context retrieval within the LanceDB-backed database.

Can I export and import chat sessions using a local vector database?▼

Yes, you can export and import chat sessions. A CLI-driven workflow lets you create sessions, save messages, and transfer your local LanceDB chat history data across different personal or small-team environments.

What is the best way to build contextual prompts from past conversations?▼

Build contextual prompts by using RAG context retrieval to search your local LanceDB chat history. This aggregates relevant past messages across sessions into a unified prompt for your ongoing workflow.

Is local LanceDB storage suitable for small-team chat history management?▼

Local LanceDB storage is applicable for personal or small-team workflows that require offline access and organized sessions. It leverages a local database to maintain chat histories without needing external cloud services.

Related Skills

Explore More Software Engineering Skills→
dglijin-ossdglijin-oss
10

elite-longterm-memory-local

Store and search memories locally using LanceDB and Ollama embeddings.

Community
Advanced
ArtyMcLabinArtyMcLabin
8

slack

Send Slack messages and manage channels via the Slack API.

Community
Intermediate
quanngynxquanngynx

ai-elements

Create AI chat interface components for Next.js and shadcn/ui projects.

Community
Basic
DexploarerDexploarer
7

Railway Qdrant Manager

Deploy Qdrant vector databases on Railway with collection management and vector operations.

Community
Advanced