LLM RAG

v 16.0 Third Party 9

Availability	Odoo Online Odoo.sh On Premise
Odoo Apps Dependencies	Discuss (mail)
Community Apps Dependencies	Show • LLM Integration Base • LLM PgVector • LLM Knowledge • LLM Vector Store Base • LLM Resource
Lines of code	6766
Technical Name	`llm_rag`
License	LGPL-3
Website	https://github.com/apexive/odoo-llm

You bought this module and need support? Click here!

What is RAG? Retrieval Augmented Generation (RAG) enhances Large Language Models by retrieving relevant information from a knowledge base before generating responses, improving accuracy and providing up-to-date information.

Key Features

Document Management

Complete system for organizing, tracking, and processing documents for RAG:

Document status tracking
Document versioning
Attachment handling
Activity logging

Vector Search

Advanced semantic search capabilities:

Integration with PostgreSQL pgvector
Cosine similarity matching
Optimized vector indices
Hybrid search capabilities

User Interface

Intuitive interfaces for managing the RAG process:

Document creation wizard
RAG search interface
Document processing dashboard
Results visualization

Complete RAG Pipeline

The module implements a full end-to-end pipeline for processing documents:

Retrieve

Extract document content from source records

Parse

Convert to standardized format (markdown)

Chunk

Split into semantic segments

Embed

Create vector representations

Extensible Architecture

The module is designed to be highly extensible, allowing developers to customize each step of the RAG pipeline:

Component	Purpose	How to Extend
Retrievers	Extract content from different record types	Extend `_get_available_retrievers` method and implement a custom retriever method
Parsers	Process different file formats (PDF, text, etc.)	Extend `_get_available_parsers` method and implement a custom parser method
Chunkers	Implement different document segmentation algorithms	Extend `_get_available_chunkers` method and implement a custom chunker method
Embedders	Integrate with different embedding models	Configure via the embedding model selection

Integration Points

The module can be integrated with other Odoo models through:

Server Actions: Pre-configured actions for creating RAG documents from any record
Model Extensions: Add RAG capabilities to any model by implementing the rag_retrieve method
API Access: Programmatic access to the RAG pipeline through the Odoo API

PDF Processing: The module includes advanced PDF handling capabilities through PyMuPDF, including text extraction and image handling.

Getting Started

Installation

Install the module and its dependencies:

Install the base llm and llm_pgvector modules
Install Python dependencies: PyMuPDF and numpy
Install the llm_rag module

Configuration

Set up your embedding models and configure the RAG pipeline:

Configure embedding models in the LLM settings
Select default parsers, chunkers, and other pipeline options
Create your first RAG documents

Please log in to comment on this module

The author can leave a single reply to each comment.
This section is meant to ask simple questions or leave a rating. Every report of a problem experienced while using the module should be addressed to the author directly (refer to the following point).
If you want to start a discussion with the author, please use the developer contact information. They can usually be found in the description.