FLAGSHIP PRODUCT

GiperMEMORY: Customer Vector Search

Production-grade hybrid RAG system with Knowledge Graph. Multi-functional mixed memory for agents. Foundation for any AI service.

API Documentation

System Architecture

Technology Stack v3.0

Frontend

React 18 + TS + Vite + shadcn/ui

Backend

FastAPI + Pydantic v2

Task Queue

Celery + Redis

Database

PostgreSQL 17 + pgvector

OCR

Docling (IBM)

LLM

OpenRouter / OpenAI / Anthropic

Key Features

System Capabilities

Structured OCR

Docling extracts text, tables, heading hierarchy and bbox.

Hybrid Chunking

Smart chunking with semantic boundaries.

LLM Enrichment

MetadataAgent and EntityExtractor enrich each chunk with context.

Knowledge Graph

Entities and relationships are saved in a graph structure.

Vector Search

pgvector for fast semantic search over embeddings.

Async Processing

Celery workers for background processing of documents of any size.

Processing Pipeline

Docling-native Pipeline v3.0

Loading

STEP 01

Document loading, status check and template selection.

Template

STEP 02

LLM provider and chunking parameters configuration.

OCR (Docling)

STEP 03

Structured OCR: text, tables and structure extraction.

LLM Setup

STEP 04

Agents and embedding services initialization.

Summary

STEP 05

Document summary generation for context.

Enrichment

STEP 06

Parallel metadata and entity extraction.

Aggregation

STEP 07

Entity and relation deduplication (Knowledge Graph).

Embedding

STEP 08

Chunk content vectorization.

Saving

STEP 09

Saving chunks and graph to PostgreSQL.

Finalizing

STEP 10

Task completion and status update.

Database Schema

PostgreSQL 17 + pgvector

cvs.chunks
content TEXT
embedding vector(1536)
heading_hierarchy TEXT[]
relevance_tags TEXT[]
bbox JSONB
cvs.kg_nodes & edges
node_type person/company...
name TEXT
embedding vector(1536)
edge_type works_at/part_of...

Integration

REST API Reference

POST/api/documents/upload
{
  "id": "upload-abc123...",
  "filename": "contract.pdf",
  "status": "pending"
}
GET/api/documents/{doc_id}/progress
data: {
  "status": "PROGRESS",
  "step": "enrichment",
  "progress": 65,
  "step_label": "Metadata enrichment"
}

Deployment

Docker Compose & Environment

Services

  • • cvs-backend (FastAPI)
  • • cvs-frontend (React)
  • • cvs-worker (Celery)
  • • cvs-docling (OCR Service)
  • • supabase-db (PostgreSQL)
  • • queue-redis (Redis)

Build Commands

docker compose up -d