Create & Ingest

memvid create my-knowledge.mv2

# Create a basic memory file
memvid create research.mv2

# Create without lexical index
memvid create notes.mv2 --no-lex

# Create a smaller memory (capacity override)
memvid create small.mv2 --size 512MB

memvid create my-memory.mv2 --json

{
  "path": "my-memory.mv2",
  "size_limit_bytes": 536870912,
  "lex_enabled": true,
  "vec_enabled": true,
  "created_at": "2024-01-15T10:30:00Z"
}

memvid open <FILE> [OPTIONS]

# Inspect a memory file
memvid open my-memory.mv2

# Get JSON output for scripting
memvid open my-memory.mv2 --json

Memory File: my-memory.mv2
  Version: 2.1.0
  Created: 2024-01-15T10:30:00Z
  Frames: 1,234
  Size: 45.2 MB / 512 MB (8.8%)

Indexes:
  Lexical: enabled (12,456 terms)
  Vector: enabled (1,234 vectors, 384d)
  Time: enabled (1,234 entries)

Tracks:
  default: 890 frames
  meetings: 234 frames
  emails: 110 frames

Memory Binding:
  Memory ID: mem_abc123
  Bound at: 2024-01-15T10:30:00Z

{
  "path": "my-memory.mv2",
  "version": "2.1.0",
  "created_at": "2024-01-15T10:30:00Z",
  "frame_count": 1234,
  "size_bytes": 47395430,
  "size_limit_bytes": 536870912,
  "indexes": {
    "lex": { "enabled": true, "term_count": 12456 },
    "vec": { "enabled": true, "vector_count": 1234, "dimension": 384 },
    "time": { "enabled": true, "entry_count": 1234 }
  },
  "tracks": {
    "default": 890,
    "meetings": 234,
    "emails": 110
  },
  "binding": {
    "memory_id": "mem_abc123",
    "bound_at": "2024-01-15T10:30:00Z"
  }
}

# Ingest a single file (text-only)
memvid put my-knowledge.mv2 --input document.pdf

# Ingest a directory
memvid put my-knowledge.mv2 --input ./documents/

# Ingest with semantic embeddings (+16x PQ compression)
memvid put my-knowledge.mv2 --input document.pdf --embedding --vector-compression

# Ingest from stdin (text-only by default)
echo "Some text content" | memvid put my-knowledge.mv2

memvid models install --clip mobileclip-s2
memvid models install --ner distilbert-ner

# Use built-in BGE (default, no API key needed)
memvid put knowledge.mv2 --input docs/ --embedding

# Use OpenAI embeddings
export OPENAI_API_KEY=sk-...
memvid put knowledge.mv2 --input docs/ --embedding -m openai-small

# Use OpenAI large model for higher quality
memvid put knowledge.mv2 --input docs/ --embedding -m openai-large

# Add to a specific track
memvid put knowledge.mv2 --input meeting-notes.md --vector-compression --track "meetings"

# Add metadata tags
memvid put knowledge.mv2 --input api-docs.md --vector-compression \
  --tag "category=documentation" \
  --tag "version=2.0" \
  --tag "author=team"

# Add labels
memvid put knowledge.mv2 --input report.pdf --vector-compression \
  --label "quarterly" \
  --label "finance"

# Set custom timestamp
memvid put knowledge.mv2 --input old-report.pdf --vector-compression \
  --timestamp 1686819000

# Combine options
memvid put knowledge.mv2 --input quarterly-report.pdf --vector-compression \
  --track "reports" \
  --title "Q3 2024 Report" \
  --tag "quarter=Q3" \
  --tag "year=2024"

# Enable parallel ingestion
memvid put knowledge.mv2 --input ./large-dataset/ --vector-compression \
  --parallel-segments \
  --parallel-threads 8

# Fine-tune parallel settings
memvid put knowledge.mv2 --input ./corpus/ --vector-compression \
  --parallel-segments \
  --parallel-seg-tokens 4000 \
  --parallel-threads 4 \
  --parallel-queue-depth 16

# Pipe text content
echo "Important note to remember" | memvid put knowledge.mv2 --vector-compression

# Pipe from curl
curl -s https://api.example.com/data | memvid put knowledge.mv2 --vector-compression --title "API Response"

# Pipe from another command
cat log.txt | grep "ERROR" | memvid put knowledge.mv2 --vector-compression --track "errors"

# Extract tables from a PDF
memvid put knowledge.mv2 --input invoice.pdf --tables --vector-compression

# Extract tables and embed individual rows for semantic search
memvid put knowledge.mv2 --input financial-report.pdf --tables --embed-rows --vector-compression

# List all tables in a memory
memvid tables list knowledge.mv2

# Output:
# Found 3 tables:
#   - pdf_table_1_page1: 5 rows x 4 cols (LineBased)
#   - pdf_table_2_page1: 12 rows x 3 cols (Stream)
#   - pdf_table_3_page2: 8 rows x 5 cols (Lattice)

# View a specific table
memvid tables view knowledge.mv2 --table-id pdf_table_1_page1

# Export to CSV
memvid tables export knowledge.mv2 --table-id pdf_table_1_page1 --format csv > data.csv

# Export to JSON
memvid tables export knowledge.mv2 --table-id pdf_table_1_page1 --format json

# Create memory for invoices
memvid create invoices.mv2

# Ingest invoice with table extraction
memvid put invoices.mv2 --input amazon-invoice.pdf --tables --vector-compression

# Search for specific items
memvid find invoices.mv2 --query "total" --json

# List extracted tables
memvid tables list invoices.mv2

# Export line items to CSV
memvid tables export invoices.mv2 --table-id pdf_table_1_page1 --format csv

memvid update <FILE> [OPTIONS]

# Update title
memvid update project.mv2 --frame-id 1234 --title "Updated Title"

# Update content and recompute embeddings
memvid update project.mv2 --uri "file:///doc.txt" \
  --input updated-doc.txt \
  --embeddings

# Add new tags
memvid update project.mv2 --frame-id 1234 \
  --tag "status=reviewed" \
  --label approved

Updated frame 1234 in project.mv2
  Title: Updated Title
  Tags added: status=reviewed
  Labels added: approved
  Embeddings: recomputed

memvid delete <FILE> [OPTIONS]

# Delete by frame ID
memvid delete project.mv2 --frame-id 1234

# Delete by URI (skip confirmation)
memvid delete project.mv2 --uri "file:///old-doc.txt" --yes

Deleted frame 1234 from project.mv2
  URI: file:///old-doc.txt
  Title: Old Document

memvid api-fetch <FILE> <CONFIG> [OPTIONS]

{
  "url": "https://api.example.com/documents",
  "method": "GET",
  "headers": {
    "Authorization": "Bearer ${API_TOKEN}"
  },
  "pagination": {
    "type": "cursor",
    "cursor_param": "after",
    "cursor_path": "$.meta.next_cursor"
  },
  "items_path": "$.data",
  "mapping": {
    "title": "$.name",
    "text": "$.content",
    "uri": "$.id"
  }
}

# Fetch from API
memvid api-fetch project.mv2 ./fetch-config.json

# Dry run to preview
memvid api-fetch project.mv2 ./fetch-config.json --dry-run

# Create the memory
memvid create docs.mv2

# Ingest documentation with embeddings
memvid put docs.mv2 --input ./docs/ --vector-compression --track "documentation"

# Add API reference
memvid put docs.mv2 --input ./api-reference/ --vector-compression \
  --track "api" \
  --tag "type=reference"

# Create the memory
memvid create papers.mv2

# Ingest papers with metadata
for paper in ./papers/*.pdf; do
  memvid put papers.mv2 --input "$paper" --vector-compression \
    --track "research" \
    --tag "source=arxiv"
done

# Create memory for codebase
memvid create codebase.mv2

# Ingest with parallel processing
memvid put codebase.mv2 --input ./src/ --vector-compression \
  --parallel-segments \
  --track "source"

# Add tests and docs
memvid put codebase.mv2 --input ./tests/ --vector-compression --track "tests"
memvid put codebase.mv2 --input ./docs/ --vector-compression --track "docs"

Error: File is locked by another process

# Check who holds the lock
memvid who knowledge.mv2

# Request release
memvid nudge knowledge.mv2

# Find process on macOS/Linux
lsof knowledge.mv2

# Wait longer for lock
memvid put knowledge.mv2 --input doc.pdf --lock-timeout 5000

# Force takeover (only if previous writer crashed)
memvid put knowledge.mv2 --input doc.pdf --force

Error: CapacityExceeded

# Check current usage
memvid stats knowledge.mv2

# Delete unused frames
memvid delete knowledge.mv2 --frame-id 42 --yes

# Compact the file
memvid doctor knowledge.mv2 --vacuum

Error: Failed to load embedding model

# Set model directory
export MEMVID_MODELS_DIR=~/.memvid/models

# Or use offline mode with pre-cached models
export MEMVID_OFFLINE=1