跨模态本地搜索工具

pip install recallforge[mlx]       # Apple Silicon (recommended, 4-bit quantization)
pip install "recallforge[mlx,server]"  # Apple Silicon + HTTP/SSE server
pip install recallforge[cuda]      # NVIDIA GPU
pip install recallforge[torch]     # CPU / other PyTorch targets
pip install recallforge[docs]      # add richer PDF extraction (optional)

git clone https://github.com/brianmeyer/recallforge.git
cd recallforge
pip install -e ".[mlx]"

{
  "mcpServers": {
    "recallforge": {
      "command": "recallforge",
      "args": ["serve", "--mode", "hybrid"]
    }
  }
}

recallforge serve --mode embed --backend mlx --quantize 4bit

recallforge serve --http --host 127.0.0.1 --port 7433 --mode embed

graph TD
    subgraph Local Filesystem
        Docs[📄 Documents]
        Imgs[🖼️ Images]
        Vids[🎬 Video]
        Aud[🎙️ Audio + Transcript]
        Conv[Conversation Turns]
    end

    subgraph RecallForge Ingest
        Docs --> TxtExt[Text Extractor]
        Imgs --> VLM[Qwen3-VL Encoder]
        Vids --> Frame[Frame & Audio Extractor]
        Aud --> TxtExt
        Conv --> TxtExt
        Frame --> VLM
        TxtExt --> VLM
    end

    subgraph LanceDB Storage
        VLM -->|2048-dim Vectors| VecDB[(Vector Space)]
        TxtExt -->|Text/Transcripts| FTS[(Tantivy FTS)]
    end

    subgraph MCP Search Pipeline
        Query[Agent Query] --> BM25[BM25 Text Search]
        Query --> Dense[Vector Similarity Search]
        BM25 --> RRF[RRF Fusion]
        Dense --> RRF
        RRF --> Rerank[Cross-Encoder Reranker]
        Rerank --> Output[Final Context to Agent]
    end

# Index anything
recallforge index ./photos ./docs
recallforge index ~/Movies/demo.mp4
recallforge index ~/Recordings/standup.wav   # requires standup.srt/.vtt/.txt/.transcript.json
recallforge index ~/Documents/roadmap.pptx

# Search any modality
recallforge search "whiteboard diagram from last meeting"
recallforge search --image ./photos/whiteboard.png
recallforge search --video ~/Movies/demo.mp4

# Watch a folder for changes (auto-index)
recallforge watch start ~/Documents --collection docs
recallforge watch list
recallforge watch stop ~/Documents

# Status
recallforge status

from recallforge import get_backend, get_storage
from recallforge.search import HybridSearcher

backend = get_backend()
storage = get_storage()
backend.warm_up()

# Index
storage.index_document(
    path="notes.md",
    text="My notes about AI...",
    collection="my_docs",
    model="Qwen3-VL-Embedding-2B",
    embed_func=backend.embed_text,
)

# Search
searcher = HybridSearcher(backend=backend, storage=storage, limit=10)
results = searcher.search("artificial intelligence")
for r in results:
    print(f"[{r.score:.3f}] {r.title}")

recallforge flags
recallforge crash-report --output recallforge-crash-report.json --message "what happened"

src/recallforge/
├── backends/
│   ├── mlx_backend.py    # MLX 4-bit/bf16 (Apple Silicon)
│   └── torch_backend.py  # PyTorch (CUDA/MPS/CPU)
├── storage/
│   └── lancedb_backend.py # LanceDB + Tantivy FTS
├── cache.py              # LRU query cache with index-version invalidation
├── search.py             # Hybrid search pipeline (BM25 + vector + RRF)
├── server.py             # MCP server (26 tools, stdio + HTTP/SSE)
├── documents.py          # PDF/DOCX/PPTX extraction
├── video.py              # Frame/transcript extraction
├── audio.py              # Transcript-first audio ingest
├── feature_flags.py      # Alpha/beta feature flag registry
├── diagnostics.py        # Local-only crash report helpers
├── watch_folder.py       # Folder monitoring with dedup
└── cli.py                # CLI interface

pytest tests/ -m "not live"    # Unit tests (no model download needed)
pytest tests/ -m live -v       # Integration tests (requires models)