`vendor_fabric.meshy.persistence.vector_store`¶

SQLite vector store for idempotency tracking and RAG embeddings.

This module provides a vector-enabled SQLite database for:

Idempotency tracking - deduplicate asset generation requests
RAG embeddings - semantic search over prompts, species, assets

Uses sqlite-vec for vector similarity search, falling back to standard SQLite if vectors aren’t needed.

Usage: from vendor_fabric.meshy.persistence.vector_store import VectorStore

store = VectorStore("assets.db")

# Track asset generation
store.record_generation(
    spec_hash="abc123",
    prompt="cute otter character",
    task_id="meshy-task-id",
    embedding=get_embedding("cute otter character"),
)

# Find similar prompts (RAG)
similar = store.search_similar("river otter", limit=5)

# Check idempotency
existing = store.get_by_spec_hash("abc123")

Requirements: pip install “vendor-fabric[meshy,vector]”

The vector extra includes:
- sqlite-vec (vector similarity extension)

get_embedding() uses sentence-transformers only when users install it
independently after reviewing its torch dependency tree.

Module Contents¶

Classes¶

`GenerationRecord`	Record of a 3D asset generation.
`SimilarityResult`	Result from similarity search.
`VectorStore`	SQLite vector store for asset generation tracking and RAG.

Functions¶

get_embedding

Get embedding for text using sentence-transformers.

API¶

class vendor_fabric.meshy.persistence.vector_store.GenerationRecord¶

Record of a 3D asset generation.

id: int | None = None¶

spec_hash: str = <Multiline-String>¶

project: str = <Multiline-String>¶

prompt: str = <Multiline-String>¶

art_style: str = 'sculpture'¶

task_id: str | None = None¶

status: str = 'pending'¶

model_url: str | None = None¶

embedding: list[float] | None = None¶

metadata: dict[str, Any] = 'field(...)'¶

created_at: datetime.datetime = 'field(...)'¶

updated_at: datetime.datetime = 'field(...)'¶

class vendor_fabric.meshy.persistence.vector_store.SimilarityResult¶

Result from similarity search.

record: vendor_fabric.meshy.persistence.vector_store.GenerationRecord = None¶

distance: float = None¶

score: float = None¶

class vendor_fabric.meshy.persistence.vector_store.VectorStore(db_path: str | pathlib.Path = 'vendor_fabric.meshy.db', embedding_dim: int = DEFAULT_EMBEDDING_DIM)¶

SQLite vector store for asset generation tracking and RAG.

Features:

Idempotent task tracking by spec_hash
Vector similarity search for RAG
Full-text search fallback when vectors unavailable
Atomic transactions

Args: db_path: Path to SQLite database file embedding_dim: Dimension of embedding vectors (default: 384 for MiniLM)

Initialization

DEFAULT_EMBEDDING_DIM = 384¶

record_generation(spec_hash: str, prompt: str, project: str = 'default', art_style: str = 'sculpture', task_id: str | None = None, embedding: list[float] | None = None, metadata: dict[str, Any] | None = None) → extended_data.containers.ExtendedDict¶

Record a new generation (idempotent by spec_hash).

If a record with the same spec_hash exists, returns existing.

Args: spec_hash: Unique hash of the generation spec prompt: Text prompt for generation project: Project identifier art_style: Art style (realistic, sculpture, etc.) task_id: Meshy task ID if already submitted embedding: Optional embedding vector for RAG metadata: Additional metadata dict

Returns: Extended generation record payload (existing or newly created)

update_status(spec_hash: str, status: str, task_id: str | None = None, model_url: str | None = None) → bool¶

Update generation status.

Args: spec_hash: Generation spec hash status: New status task_id: Optional task ID to update model_url: Optional model URL to update

Returns: True if record was updated, False if not found

get_by_spec_hash(spec_hash: str) → extended_data.containers.ExtendedDict | None¶

Get generation record by spec hash.

Args: spec_hash: Generation spec hash

Returns: Extended generation record payload or None

get_by_task_id(task_id: str) → extended_data.containers.ExtendedDict | None¶

Get generation record by Meshy task ID.

Args: task_id: Meshy task ID

Returns: Extended generation record payload or None

search_similar(query_embedding: list[float], limit: int = 10, project: str | None = None) → extended_data.containers.ExtendedList[extended_data.containers.ExtendedDict]¶

Search for similar generations using vector similarity.

Args: query_embedding: Query embedding vector limit: Maximum results to return project: Optional project filter

Returns: Extended similarity result payloads ordered by similarity (highest first)

search_text(query: str, limit: int = 10, project: str | None = None) → extended_data.containers.ExtendedList[extended_data.containers.ExtendedDict]¶

Full-text search for prompts.

Falls back to this when vector search is unavailable.

Args: query: Search query limit: Maximum results project: Optional project filter

Returns: Extended generation record payloads

list_pending(project: str | None = None) → extended_data.containers.ExtendedList[extended_data.containers.ExtendedDict]¶

List all pending/in-progress generations.

Args: project: Optional project filter

Returns: Extended pending generation record payloads

compute_spec_hash(spec: dict[str, Any]) → str¶

Compute deterministic hash for a generation spec.

Args: spec: Generation specification dict

Returns: SHA256 hex digest

close() → None¶: Close database connection.

vendor_fabric.meshy.persistence.vector_store.get_embedding(text: str, model: str = 'all-MiniLM-L6-v2') → extended_data.containers.ExtendedList[float] | None¶

Get embedding for text using sentence-transformers.

Args: text: Text to embed model: Model name (default: all-MiniLM-L6-v2)

Returns: Extended embedding vector or None if sentence-transformers not available

vendor_fabric.meshy.persistence.vector_store¶

Module Contents¶

Classes¶

Functions¶

API¶

`vendor_fabric.meshy.persistence.vector_store`¶