LLM Tool RAG

v 16.0 Third Party 25

Availability	Odoo Online Odoo.sh On Premise
Odoo Apps Dependencies	Discuss (mail)
Community Apps Dependencies	Show • LLM Assistant • LLM Knowledge • LLM Tool • Easy AI Chat • LLM Integration Base • LLM Prompt Templates • Web JSON Editor • LLM Mail Message Subtypes • LLM Resource • LLM Vector Store Base
Lines of code	13756
Technical Name	`llm_tool_knowledge`
License	LGPL-3
Website	https://github.com/apexive/odoo-llm

You bought this module and need support? Click here!

Availability	Odoo Online Odoo.sh On Premise
Odoo Apps Dependencies	Discuss (mail)
Community Apps Dependencies	Show • LLM Assistant • LLM Knowledge • LLM Tool • Easy AI Chat • LLM Integration Base • LLM Prompt Templates • Web JSON Editor • LLM Mail Message Subtypes • LLM Resource • LLM Vector Store Base
Lines of code	13756
Technical Name	`llm_tool_knowledge`
License	LGPL-3
Website	https://github.com/apexive/odoo-llm

LLM Tool RAG

AI-Powered Tools for Retrieval Augmented Generation in Odoo

About This Module

The LLM Tool RAG module extends the core RAG functionality in Odoo with specialized tools for knowledge retrieval, document search, and more. These tools enable AI assistants to access and utilize your organization's knowledge base for more accurate and context-aware responses.

What are LLM Tools? LLM Tools allow Large Language Models to perform specific actions in Odoo, such as retrieving relevant documents, searching knowledge bases, and executing functions based on user requests.

Key Features

Knowledge Retriever

Retrieve relevant information from your document database using semantic search:

Vector similarity matching
Hybrid search capabilities
Configurable similarity thresholds
Document ranking and prioritization

Document Search

Advanced search capabilities for document chunks:

Semantic search with vector embeddings
Keyword-based filtering
Customizable search parameters
Result grouping by document

Function Calling

Enable AI models to execute specific functions:

Schema-based function definitions
Parameter validation
Structured response formatting
Error handling and reporting

Integration with RAG

Seamless integration with the core RAG module:

Access to document chunks
Embedding model compatibility
Shared search functionality
Consistent result processing

Implementation Details

Tool Definition

Tools are defined as Odoo models that extend the base llm.tool model, with specific implementations for different functions.

Parameter Handling

Tool parameters are defined using Pydantic models, which provide automatic validation and schema generation.

Execution

When a tool is called, its implementation method processes the parameters and executes the requested function.

Result Processing

Results are formatted according to the tool's specification and returned to the calling assistant or interface.

Extensibility

The module is designed to be highly extensible, allowing developers to create custom tools:

Component	Purpose	How to Extend
Tool Implementations	Define new tool functionality	Extend `llm.tool` and implement the required methods
Parameter Models	Define input parameters for tools	Create Pydantic models with appropriate field definitions
Search Functionality	Customize document search behavior	Inherit from `llm.document.search.mixin` and override methods

Module Information

Name: LLM Tool RAG
Version: 16.0.1.0.0
Category: AI
Author: Apexive Solutions LLC
Website: GitHub
License: LGPL-3
Dependencies: base, mail, llm, llm_rag

Installation

Install the base llm and llm_rag modules
Install this module (llm_tool_rag)
Configure your tools in the LLM settings

Get Started

Ready to enhance your Odoo with AI-powered tools? Install now and start leveraging your knowledge base with AI.

Download from GitHub

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.