kkdai/linebot-multimodal-rag — explained in plain English
Analysis updated 2026-05-18
Upload PDFs, text files, or images through LINE and search them later by asking questions.
Send a photo and find related documents already stored in your knowledge base.
Run a personal or team knowledge base entirely through a chat interface.
Query documents in one language even when they were uploaded in another.
| kkdai/linebot-multimodal-rag | huta0kj/skill-scanner-agent | markmamed/imu-surgical-intention-perception | |
|---|---|---|---|
| Stars | 31 | 31 | 31 |
| Language | Python | Python | Python |
| Setup difficulty | hard | moderate | hard |
| Complexity | 4/5 | 3/5 | 4/5 |
| Audience | developer | developer | researcher |
Figures from each repo's GitHub metadata at analysis time.
Requires a GCP project with a GCS bucket, a LINE Messaging API channel, and a Gemini API key.
This is a LINE Bot that turns your chat app into a personal knowledge base you can search with words or pictures. You upload documents, PDFs, text files, CSVs, images, directly inside LINE, and the bot stores them in a searchable index. Later, you type a question in plain language and the bot finds the relevant passages from your own uploaded files and answers you. You can also send a photo and ask the bot to search your knowledge base for related information. The system uses the Gemini File Search API to handle the heavy lifting of chunking, embedding, and indexing your files, so each user's data is kept separate, you only ever search your own uploads. The Python backend runs on FastAPI and is designed to be deployed to a cloud environment. The bot supports text files, PDFs, and images up to 100 MB, and can handle queries in multiple languages even if the stored documents are in a different language. Audio and video are not supported.
A LINE chat bot that turns uploaded files and photos into a searchable personal knowledge base.
Mainly Python. The stack also includes Python, FastAPI, Gemini File Search API.
The README does not state a license.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.