Skip to Content

LLM Chroma

by
Odoo
v 18.0 Third Party 22
Download for v 18.0 Deploy on Odoo.sh
Availability
Odoo Online
Odoo.sh
On Premise
Odoo Apps Dependencies Discuss (mail)
Community Apps Dependencies
Lines of code 4854
Technical Name llm_chroma
LicenseLGPL-3
Websitehttps://github.com/apexive/odoo-llm
Versions 16.0 18.0
You bought this module and need support? Click here!
Availability
Odoo Online
Odoo.sh
On Premise
Odoo Apps Dependencies Discuss (mail)
Community Apps Dependencies
Lines of code 4854
Technical Name llm_chroma
LicenseLGPL-3
Websitehttps://github.com/apexive/odoo-llm
Versions 16.0 18.0
ChromaDB Integration

LLM Chroma

Vector store integration with Chroma for LLM features.

Connect Odoo to ChromaDB for powerful vector storage and search

HTTP Client
Vector Search
Open Source

What is ChromaDB?

An open-source vector database for AI applications

ChromaDB is a popular open-source embedding database designed specifically for AI applications. This module connects Odoo to a Chroma server via HTTP, enabling vector storage and similarity search capabilities for your knowledge base and AI assistants.

Features

Powerful vector capabilities for Odoo

Chroma Integration

Native integration with ChromaDB for storing and managing vector embeddings.

HTTP Client Connection

Connect to your Chroma server over HTTP for flexible deployment options.

Collection Management

Manage vector collections for organizing different types of embeddings.

Vector Search

Perform similarity searches with various similarity functions supported by Chroma.

Technical Details

Requirements and dependencies

Module Information

Dependencies:

llm, llm_knowledge, llm_store

Python Packages:

chromadb-client, numpy

Category:

Technical

License:

LGPL-3

LLM Chroma

ChromaDB vector store for Odoo

Developed by Apexive Solutions LLC

Licensed under LGPL-3 • © 2025 All rights reserved.

github.com/apexive/odoo-llm
hello@apexive.com

Chroma Provider for Odoo LLM

Development-friendly vector store for prototyping and lightweight use.

Module Type: 🗄️ Vector Store (Development Friendly)

Architecture

┌───────────────────────────────────────────────────────────────┐
│                    Used By (RAG Modules)                      │
│        ┌───────────────┐           ┌───────────────┐         │
│        │ llm_knowledge │           │llm_assistant  │         │
│        │   (RAG)       │           │  (with RAG)   │         │
│        └───────┬───────┘           └───────┬───────┘         │
└────────────────┼───────────────────────────┼─────────────────┘
                 └─────────────┬─────────────┘
                               ▼
              ┌───────────────────────────────────────────┐
              │             llm_store                     │
              │        (Vector Store API)                 │
              └─────────────────────┬─────────────────────┘
                                    │
                                    ▼
              ┌───────────────────────────────────────────┐
              │       ★ llm_chroma (This Module) ★        │
              │          Chroma Implementation            │
              │  🌈 Easy Setup │ HTTP API │ Development   │
              └─────────────────────┬─────────────────────┘
                                    │
                                    ▼
              ┌───────────────────────────────────────────┐
              │              Chroma Server                │
              │           (localhost:8000)                │
              └───────────────────────────────────────────┘

Installation

What to Install

For development RAG:

# 1. Start Chroma server
docker run -p 8000:8000 chromadb/chroma:1.0.0

# 2. Install Python dependencies
pip install chromadb-client numpy

# 3. Install the Odoo module
odoo-bin -d your_db -i llm_knowledge,llm_chroma

Auto-Installed Dependencies

  • llm (core infrastructure)
  • llm_store (vector store abstraction)

Why Choose Chroma?

Feature Chroma
Setup 🚀 Very easy
Development 🛠️ Great for prototyping
API 📡 Simple HTTP API
Cost 💰 Free & open source

Vector Store Comparison

Feature llm_pgvector llm_qdrant llm_chroma
Server 🐘 PostgreSQL 🔷 Qdrant 🌈 Chroma
Setup Easy Moderate Easy
Scale Medium High Medium
Best For Simple RAG Large scale Development

Common Setups

I want to... Install
Development RAG llm_knowledge + llm_chroma
Chat + RAG (dev) llm_assistant + llm_openai + llm_knowledge + llm_chroma

Features

  • Chroma HTTP Client: Connect to a Chroma server with optional SSL and API key support
  • Collection Management: Create, list, delete, and verify collections directly from Odoo
  • Vector Operations: Insert, delete, and search vectors with metadata
  • Filter Conversion: Translate Odoo filter formats into Chroma where conditions

Configuration

  1. In LLM > Configuration > Vector Stores, create or edit a store:

    • Service: chroma
    • Connection URI: e.g., http://localhost:8000
    • API Key (optional)

  2. Ensure your Chroma Docker image matches the client version:

    image: chromadb/chroma:1.0.0

Usage

Once configured, use the llm.store methods:

# Create a new collection
store.chroma_create_collection(collection_id)

# Insert embeddings
store.chroma_insert_vectors(collection_id, vectors, metadata=list_of_dicts, ids=list_of_ids)

# Query by embedding or text
results = store.chroma_search_vectors(collection_id, query_vector, limit=10)

Troubleshooting

KeyError: '_type'

Symptom: A KeyError: '_type' when calling client.create_collection(...).

Cause: Chroma server expects a _type discriminator in the JSON configuration payload but didn't receive one, often due to a client/server version mismatch.

Solutions:

  1. Pin matching versions:

    pip install chromadb-client==1.0.0
docker pull chromadb/chroma:1.0.0

  2. Explicitly supply configuration in code.

Technical Specifications

  • Version: 18.0.1.0.0
  • License: LGPL-3
  • Dependencies: llm, llm_store
  • Python Packages: chromadb-client, numpy

License

LGPL-3

© 2025 Apexive Solutions LLC

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.
Please choose a rating from 1 to 5 for this module.