TurboVec

Use Docpipe's local vector index option.

TurboVec

TurboVec stores compressed vector indices on local disk. It can suit local, single-node, or air-gapped workloads; it is not a replacement for a managed, multi-replica vector service. Use pgvector for the documented production Postgres path.

Source: Vector-store support and limits Source: TurboVec adapter

Setup

# pip install "docpipe-sdk[turbovec,openai]"   # + your embedding provider
export DOCPIPE_VECTOR_BACKEND=turbovec
export DOCPIPE_TURBVEC_INDEX_DIR=./.docpipe/indices   # default on-disk index root

# Per-request override on ingest / search / RAG API bodies:
# { "vector_backend": "turbovec", "table_name": "my_library", ... }

import docpipe

config = docpipe.IngestionConfig(
    connection_string="postgresql://unused",  # accepted; vectors use local files
    table_name="my_library",                  # index folder name under TURBVEC_INDEX_DIR
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
    vector_backend="turbovec",
)
docpipe.ingest("invoice.pdf", config=config)
# → ./.docpipe/indices/my_library/index.tvim + docstore.json

# TurboVec is local/on-disk; use pgvector or a supported external backend for
# deployments that need shared, multi-replica vector storage.