FileChat for Openclaw

A personal Retrieval-Augmented Generation library that syncs Google Drive documents with a local vector database for instant semantic querying.

eladrave
v1.0.0
Mar 23, 2026
1
769
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install filechat-old-ugnire

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install filechat-old-ugnire using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is FileChat?

FileChat is a powerful knowledge management tool within the Openclaw Skills ecosystem. It bridge the gap between static cloud storage and active AI intelligence by automatically chunking, embedding, and indexing documents from a designated Google Drive folder into a local persistent ChromaDB instance.

By leveraging the Google Workspace CLI and Gemini embedding models, this skill enables users to have natural conversations with their own private data. It transforms a standard storage folder into a searchable, interactive document library that respects privacy while providing high-speed retrieval of information.

FileChat Use Cases

  • Searching for specific information across multiple PDF or text documents stored in Google Drive.
  • Retrieving and downloading specific files from the cloud via chat commands.
  • Storing and instantly indexing new local files to a centralized document knowledge base.
  • Synchronizing an entire document repository for offline semantic search capabilities.

How FileChat Works

  1. Environment Initialization: The skill checks for necessary credentials including a Google Drive folder ID and Gemini API key.
  2. Synchronization & Ingestion: Running the sync script triggers the traversal of Google Drive sub-folders to download and process new or updated documents.
  3. Vectorization: Documents are chunked and converted into vector embeddings using the text-embedding-004 model.
  4. Persistent Storage: Data is indexed into a local ChromaDB instance for lightning-fast semantic retrieval.
  5. Query & Retrieval: When a user asks a question, the skill performs a vector search, retrieves relevant text snippets, and formulates a response citing original sources.

FileChat Setup

To begin using this entry in the Openclaw Skills collection, ensure you have the required dependencies and environment variables configured.

First, install the Google Workspace CLI and local dependencies:

# Install GWS CLI
npm install -g @googleworkspace/cli

# Install skill dependencies
cd ./skills/filechat && npm install

Configure your environment variables in ./skills/filechat/.env:

echo "GEMINI_API_KEY=your_key_here" > ./skills/filechat/.env
echo "FILECHAT_DRIVE_FOLDER_ID=your_folder_id_here" >> ./skills/filechat/.env

FileChat Data Schema & Taxonomy

FileChat organizes data by bridging cloud metadata with local vector structures:

Component Type Description
ChromaDB Vector Store Local database containing document chunks and embeddings.
Google Drive Source Storage The primary source of truth for physical files and folder hierarchy.
Metadata JSON Stores File IDs, filenames, and parent folder relationships for accurate citations.
Local Cache File System Temporary storage for downloaded files during the ingestion and sync process.

FileChat Advanced Features

  • Multi-format support including PDFs, shortcuts, and nested directory traversal.
  • Integration with the OpenClaw media attachment syntax for direct file delivery in chat.
  • Automated sync triggers to keep the local vector database consistent with cloud changes.
  • Semantic search using advanced Gemini embedding models for high-context retrieval.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*