LLM Knowledge

v 16.0 Third Party 11

Availability	Odoo Online Odoo.sh On Premise
Odoo Apps Dependencies	Discuss (mail)
Community Apps Dependencies	Show • LLM Integration Base • LLM Resource • LLM Vector Store Base
Lines of code	4657
Technical Name	`llm_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 Integration Base • LLM Resource • LLM Vector Store Base
Lines of code	4657
Technical Name	`llm_knowledge`
License	LGPL-3
Website	https://github.com/apexive/odoo-llm

Retrieval Augmented Generation for LLM with Vector Search

Key Features

Organize resources into collections for targeted knowledge retrieval

Split documents into manageable chunks for more precise retrieval

Generate embeddings for semantic search capabilities

Seamless integration with multiple vector database options:

Native PostgreSQL vector storage and search with high performance

Integration with Chroma vector database for flexible deployment

Support for Qdrant vector search engine with advanced filtering

Access and manage knowledge collections through a simple, intuitive interface:

Access Collections: Navigate to LLM > Knowledge > Collections to view and manage all collections
View Resources: Access LLM > Knowledge > Resources to manage document resources
Explore Chunks: Browse LLM > Knowledge > Chunks to see individual document chunks
Upload Documents: Use the "Upload Resource" wizard to easily add new documents

Create and manage knowledge collections with a streamlined workflow:

Create Collection: Click "Create" button to add a new collection, specifying the embedding model
Add Resources: Add resources manually or configure domain filters for automatic inclusion
Process Resources: Click "Process Resources" to retrieve, parse, chunk, and embed documents
Configure RAG: Enable the collection for use in LLM threads for knowledge retrieval
Manage Chunks: View and manage individual chunks through the Chunks menu

Documents are retrieved, parsed, and split into manageable chunks

Chunks are converted to vector embeddings using the specified model

LLM queries retrieve the most relevant chunks for enhanced responses

For more information, visit our GitHub repository

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.