# via007/bilibili-rag

B站收藏夹RAG知识库：收藏不吃灰，B 站收藏夹 → 语音转写 → 向量检索 → 对话问答

Repository: https://github.com/via007/bilibili-rag
Canonical: https://ross.abutalabs.com/products/bilibili-rag
Language: Python
License: Apache-2.0
License Family: permissive
Topics: rag-bilibili-knowledge-base-llm-chroma-qwen
Last push: 2026-08-12T13:10:02+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 83, longevity 15
- inputs: {"age_days": 220, "days_push": 21, "days_rel": 36, "gap_med": 38, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1306, forks 94 (observed 2026-08-28T04:04:18.942329+00:00)

## What it is
A self-hosted RAG application that turns a Bilibili user's favorited videos into a searchable, conversational knowledge base. It pulls favorites via QR login, transcribes audio with ASR, embeds into ChromaDB, and serves a chat Q&A web UI with source-cited answers and Markdown export.

## Use cases
- turn my bilibili favorites into a searchable knowledge base
- chat with my saved lecture and talk videos
- transcribe bilibili videos to text and index them
- ask questions about videos I bookmarked
- build a personal RAG knowledge base from video content
- export AI notes from saved videos to markdown

## When to choose
- you have a large Bilibili favorites list you never revisit and want it queryable
- you want a self-hosted RAG pipeline with transcription, vector search, and cited answers
- you prefer local SQLite + ChromaDB storage and Docker deployment

## When to avoid
- you need to ingest content from platforms other than Bilibili
- you want a fully offline solution without DashScope/OpenAI API keys
- you need production-grade multi-user deployment rather than a personal tool

## Facets
- artifact type: application
- maturity: active
- function: rag, speech-recognition, vector-database, chatbot, search-engine, web-framework
- domain: large-language-models, self-hosted, developer-tools
- platform: python, self-hosted, cross-platform
- tags: bilibili, video-transcription, personal-knowledge-base, chromadb, qwen, asr, sqlite, note-export, retrieval-augmented-generation, natural-language-processing, docker, web-server

## Member repositories
- via007/bilibili-rag (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.942329+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:50:59.521463+00:00, confidence not recorded.
  - readme: https://github.com/via007/bilibili-rag (fetched 2026-08-28T04:04:18.942329+00:00, sha 4953f27c9d86)
- Data as of 2026-08-30T08:39:29.467469+00:00.