README

[dependencies]
memvid-core = "2.0"

[dependencies]
memvid-core = { version = "2.0", features = ["lex", "vec", "temporal_track"] }

use memvid_core::{Memvid, PutOptions, SearchRequest};

fn main() -> memvid_core::Result<()> {
    // Create a new memory file
    let mut mem = Memvid::create("knowledge.mv2")?;

    // Add documents with metadata
    let opts = PutOptions::builder()
        .title("Meeting Notes")
        .uri("mv2://meetings/2024-01-15")
        .tag("project", "alpha")
        .build();
    mem.put_bytes_with_options(b"Q4 planning discussion...", opts)?;
    mem.commit()?;

    // Search
    let response = mem.search(SearchRequest {
        query: "planning".into(),
        top_k: 10,
        snippet_chars: 200,
        ..Default::default()
    })?;

    for hit in response.hits {
        println!("{}: {}", hit.title.unwrap_or_default(), hit.text);
    }

    Ok(())
}

git clone https://github.com/memvid/memvid.git
cd memvid

cargo build

cargo build --release

cargo build --release --features "lex,vec,temporal_track"

cargo test

cargo test -- --nocapture

cargo test test_name

cargo test --test lifecycle
cargo test --test search
cargo test --test mutation

cargo run --example basic_usage

cargo run --example pdf_ingestion

cargo run --example clip_visual_search --features clip

cargo run --example test_whisper --features whisper -- /path/to/audio.mp3

# Default (FP32 small, highest accuracy)
cargo run --example test_whisper --features whisper -- audio.mp3

# Quantized tiny (75% smaller, faster)
MEMVID_WHISPER_MODEL=whisper-tiny-en-q8k cargo run --example test_whisper --features whisper -- audio.mp3

use memvid_core::{WhisperConfig, WhisperTranscriber};

// Default FP32 small model
let config = WhisperConfig::default();

// Quantized tiny model (faster, smaller)
let config = WhisperConfig::with_quantization();

// Specific model
let config = WhisperConfig::with_model("whisper-tiny-en-q8k");

let transcriber = WhisperTranscriber::new(&config)?;
let result = transcriber.transcribe_file("audio.mp3")?;
println!("{}", result.text);

mkdir -p ~/.cache/memvid/text-models

# Download ONNX model
curl -L 'https://huggingface.co/BAAI/bge-small-en-v1.5/resolve/main/onnx/model.onnx' \
  -o ~/.cache/memvid/text-models/bge-small-en-v1.5.onnx

# Download tokenizer
curl -L 'https://huggingface.co/BAAI/bge-small-en-v1.5/resolve/main/tokenizer.json' \
  -o ~/.cache/memvid/text-models/bge-small-en-v1.5_tokenizer.json

curl -L 'https://huggingface.co/BAAI/bge-base-en-v1.5/resolve/main/onnx/model.onnx' \
  -o ~/.cache/memvid/text-models/bge-base-en-v1.5.onnx
curl -L 'https://huggingface.co/BAAI/bge-base-en-v1.5/resolve/main/tokenizer.json' \
  -o ~/.cache/memvid/text-models/bge-base-en-v1.5_tokenizer.json

curl -L 'https://huggingface.co/nomic-ai/nomic-embed-text-v1.5/resolve/main/onnx/model.onnx' \
  -o ~/.cache/memvid/text-models/nomic-embed-text-v1.5.onnx
curl -L 'https://huggingface.co/nomic-ai/nomic-embed-text-v1.5/resolve/main/tokenizer.json' \
  -o ~/.cache/memvid/text-models/nomic-embed-text-v1.5_tokenizer.json

curl -L 'https://huggingface.co/thenlper/gte-large/resolve/main/onnx/model.onnx' \
  -o ~/.cache/memvid/text-models/gte-large.onnx
curl -L 'https://huggingface.co/thenlper/gte-large/resolve/main/tokenizer.json' \
  -o ~/.cache/memvid/text-models/gte-large_tokenizer.json

use memvid_core::text_embed::{LocalTextEmbedder, TextEmbedConfig};
use memvid_core::types::embedding::EmbeddingProvider;

// Use default model (BGE-small)
let config = TextEmbedConfig::default();
let embedder = LocalTextEmbedder::new(config)?;

let embedding = embedder.embed_text("hello world")?;
assert_eq!(embedding.len(), 384);

// Use different model
let config = TextEmbedConfig::bge_base();
let embedder = LocalTextEmbedder::new(config)?;

// Bind the index to a specific model.
// If the index was previously created with a different model, this will return an error.
mem.set_vec_model("bge-small-en-v1.5")?;

export OPENAI_API_KEY="sk-..."

use memvid_core::api_embed::{OpenAIConfig, OpenAIEmbedder};
use memvid_core::types::embedding::EmbeddingProvider;

// Use default model (text-embedding-3-small)
let config = OpenAIConfig::default();
let embedder = OpenAIEmbedder::new(config)?;

let embedding = embedder.embed_text("hello world")?;
assert_eq!(embedding.len(), 1536);

// Use higher quality model
let config = OpenAIConfig::large();  // text-embedding-3-large (3072 dims)
let embedder = OpenAIEmbedder::new(config)?;

┌────────────────────────────┐
│ Header (4KB)               │  Magic, version, capacity
├────────────────────────────┤
│ Embedded WAL (1-64MB)      │  Crash recovery
├────────────────────────────┤
│ Data Segments              │  Compressed frames
├────────────────────────────┤
│ Lex Index                  │  Tantivy full-text
├────────────────────────────┤
│ Vec Index                  │  HNSW vectors
├────────────────────────────┤
│ Time Index                 │  Chronological ordering
├────────────────────────────┤
│ TOC (Footer)               │  Segment offsets
└────────────────────────────┘