effectz-ai/effectz-gpt

TypeScript

213 commits

updated Jun 26, 2026

See the code

README

EffectzGPT by Effectz.AI

Welcome to EffectzGPT

EffectzGPT => Easy Workflow Automations with LLMs

EffectzGPT helps you quickly develop Enterprise Workflow Automation Applications powered by Large Language Models (LLMs). It is specially designed for building scalable apps that require advanced reasoning over data. It has been used in both real-world business applications and cutting-edge research. EffectzGPT makes developing powerful AI-driven workflow automation applications simple, even if you're not an AI expert. EffectzGPT has been developed using LlamaIndex.

Watch the Youtube demo of EffectzGPT ChatBot

✨ Feature List
💾 Getting Started
🚀 Deploying With Docker Compose
💖 Trusted By Our Clients
🚩 Used In Cutting Edge Research

Feature List

🤖 Model Support	Implemented	Description
OpenAI (e.g. GPT4)	✅	Embedding and Generation Models by OpenAI
Ollama (e.g. Llama3)	✅	Local Embedding and Generation Models powered by Ollama
Anthrophic (e.g. Claude Sonnet)	✅	Embedding and Generation Models by Anthrophic

🤖 Embedding Support	Implemented	Description
OpenAI	✅	Embedding Models by OpenAI
Ollama	✅	Local Embedding Models powered by Ollama

📁 Data Support	Implemented	Description
Document Ingestion	✅	Ingest documents into EffectzGPT
URL Scraping	✅	Ingest data from urls into EffectzGPT

👨‍💻 Agent Features	Implemented	Description
Agent with memory	✅	Agent with user specific memeory
Agent workflow	✅	Agent with multistep workflow with access to tools
Agent memory management	planned ⏱️	Auto move memory between program memory and disk based on importance

✨ RAG Features	Implemented	Description	Reference
Reranking	✅	Rerank results based on context for improved results
Sentence window retrieval	✅	Sentence window retrieval	Production Ready Advanced RAG Optimization with Llama-Index and Qdrant Vector Database
RAPTOR	✅	Raptor ingestion	RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Supervised ICL	✅	Supervised In-Context Learning	Many-Shot In-Context Learning
Unsupervised ICL	✅	Unsupervised In-Context Learning	Many-Shot In-Context Learning
Query Optimization	✅	Optimization by PROmpting (OPRO)	Large Language Models as Optimizers
Support for Hybrid RAG	planned ⏱️	Integrating Knowledge Graphs and Vector RAG	HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
LlamaIndex Workflows Support	✅	Event-driven abstraction used to chain together several events
Self-Route	✅	Hybrid approach (RAG / LC LLM)	Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
Secure ICL	planned ⏱️	Secure ICL implementation for security sensitive applications	Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Dense-X-Retrieval	planned ⏱️	Retrieval based on propoistions extracted from each node	Dense X Retrieval: What Retrieval Granularity Should We Use?
Corrective RAG	planned ⏱️	Incorporating a self-correction mechanism that evaluates and refines retrieved knowledge	Corrective Retrieval Augmented Generation

🗡️ Chunking Techniques	Implemented	Description
Sentence	✅	Chunk by Sentence

🆒 Cool Bonus	Implemented	Description
Docker Support	✅	EffectzGPT is deployable via Docker
Inbuilt ChatBot	✅	A Next.js based ChatBot is available
Inbuilt Admin Panel	✅	A Next.js based Admin Panel is available
Whatsapp Intergration	✅	Whatsapp business API is supported
Messenger Intergration	✅	Facebook messenger API is supported
Streaming API	✅	For Applications like chatbots
Non-Streaming API	✅	For Non-streaming RAG applications

🤝 RAG Libraries	Implemented	Description
LlamaIndex	✅	Implement LlamaIndex RAG pipelines

🗄️ Vector DB Support	Implemented	Description
Chroma	✅	AI-native open-source vector database
Qdrant	✅	Open-source vector database and vector search engine
Weaviate	planned ⏱️	Open-source vectore database

Getting Started

To run EffectzGPT, you have to build a Docker image from the Dockerfile and start a docker container with that image.

Prerequisites

Make sure you have the following installed on your system:

node
python 3.11
Docker
Docker Compose

Environment Variables

Environment Variable	Example Values	Description	Scope	IsRequired
NEXT_PUBLIC_CHAT_API_BASE_URL	http://localhost:5000	Set backend API end point	UI	Y
APP_PORT	5000	Set port to start the backend app	BACKEND	Y
TOP_K	10	Set number of similar embeddings to return	BACKEND	Y
VECTOR_STORE_PROVIDER	chroma	Set vector store provider	BACKEND	Y
MODEL_PROVIDER	openai	Set LLM provider	BACKEND	Y
MODEL	gpt-3.5-turbo	Set LLM	BACKEND	Y
EMBEDDING_MODEL	text-embedding-3-large	Set embedding model	BACKEND	Y
OPENAI_API_KEY	Your OpenAI API key	Set OpenAI API key	BACKEND	Y
SYSTEM_PROMPT	Your system prompt	Set system prompt	BACKEND	Y
COHERE_API_KEY	Your Cohere API key	Set Cohere API key	BACKEND	Y
STREAM_TIMEOUT	60000	Time out in ms for streaming a	BACKEND	N
CHROMA_COLLECTION	./default	chroma collection name	BACKEND	N
CHROMA_PATH	./chromadb	path to chroma file storage	BACKEND	N
CHROMA_HOST	localhost	chroma DB url ( if this value is defined CHROMA_PATH will be ignore )	BACKEND	N
CHROMA_PORT	8000	Chroma DB access port ( if this value is defined CHROMA_PATH will be ignore )	BACKEND	N
EMBEDDING_DIM	1024	embedding size	BACKEND	N
LLAMA_CLOUD_API_KEY	Your LLAMA cloud API key	LLAMA cloud key	BACKEND	N
COHERE_API_KEY	Your Cohere cloud API key	Cohere key	BACKEND	N

Endpoints

The docker container exposes the following endpoints.

Admin Panel: http://localhost:3000/admin
Chat UI: http://localhost:3000
Docs UI: http://localhost:3000/docs

Deploying With Docker Compose

You can easily deploy EffectzGPT to your own infrastructure with Docker Compose.

Prerequisites

Make sure you have the following installed on your system:

Docker
Docker Compose

Steps

Clone the repository.

git clone https://github.com/effectz-ai/effectz-gpt.git

# navigate to backend folder and build docker image
cd effectz-gpt/backend
docker build -t effectzai/effectzgpt_b .

# navigate to frontend folder and build docker image
cd effectz-gpt/frontend
docker build -t effectzai/effectzgpt_f .

Start frontend and backend services defined in the docker-compose.yml file.

docker-compose up -d effectzgpt_ui

Or start a specific service (detached mode).

docker-compose up -d <service_name>

Notes

If you make changes to the code or Dockerfile, you may need to rebuild the images.

docker-compose up --build

The docker-compose.yml file uses environment variables. To set environment variables, you can follow one of the following methods.

Using a .env file (create a .env file and define the environment variables).

VAR_NAME1=value1

Exporting environment variables directly.

export VAR_NAME1=value1

Required and optional environment variable can be found above in Environment Variables

Trusted By Our Clients

Logo of University of Florida Logo of Chitra Logo of Cleolinks AB

Used In Cutting Edge Research

Name	Reference
RMF-GPT	RMF-GPT — OpenAI GPT-3.5 LLM, Blockchain, NFT, Model Cards and OpenScap Enabled Intelligent RMF Automation System
SliceGPT	SliceGPT – OpenAI GPT-3.5 LLM, Blockchain and Non-Fungible Token Enabled Intelligent 5G/6G Network Slice Broker and Marketplace
DevSec-GPT	DevSec-GPT — Generative-AI (with Custom-Trained Meta's Llama2 LLM), Blockchain, NFT and PBOM Enabled Cloud Native Container Vulnerability Management and Pipeline Verification Platform

Similar repos

labring/FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of…

29,856

langchain-ai/opengpts

6,709

sabeeralikp/llama_flow

langgenius/dify

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative…

158,871

khulnasoft/GPT-DB

KavinKumar22K/db-gpt

d0ublecl1ck/DB-GPT

gengwanli/DB-dev

download on Mar 15 2025

effectz-ai/effectz-gpt

TypeScript

213 commits

updated Jun 26, 2026

See the code

README

EffectzGPT by Effectz.AI

Welcome to EffectzGPT

EffectzGPT => Easy Workflow Automations with LLMs

✨ Feature List
💾 Getting Started
🚀 Deploying With Docker Compose
💖 Trusted By Our Clients
🚩 Used In Cutting Edge Research

Feature List

🤖 Model Support	Implemented	Description
OpenAI (e.g. GPT4)	✅	Embedding and Generation Models by OpenAI
Ollama (e.g. Llama3)	✅	Local Embedding and Generation Models powered by Ollama
Anthrophic (e.g. Claude Sonnet)	✅	Embedding and Generation Models by Anthrophic

🤖 Embedding Support	Implemented	Description
OpenAI	✅	Embedding Models by OpenAI
Ollama	✅	Local Embedding Models powered by Ollama

📁 Data Support	Implemented	Description
Document Ingestion	✅	Ingest documents into EffectzGPT
URL Scraping	✅	Ingest data from urls into EffectzGPT

👨‍💻 Agent Features	Implemented	Description
Agent with memory	✅	Agent with user specific memeory
Agent workflow	✅	Agent with multistep workflow with access to tools
Agent memory management	planned ⏱️	Auto move memory between program memory and disk based on importance

✨ RAG Features	Implemented	Description	Reference
Reranking	✅	Rerank results based on context for improved results
Sentence window retrieval	✅	Sentence window retrieval	Production Ready Advanced RAG Optimization with Llama-Index and Qdrant Vector Database
RAPTOR	✅	Raptor ingestion	RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Supervised ICL	✅	Supervised In-Context Learning	Many-Shot In-Context Learning
Unsupervised ICL	✅	Unsupervised In-Context Learning	Many-Shot In-Context Learning
Query Optimization	✅	Optimization by PROmpting (OPRO)	Large Language Models as Optimizers
Support for Hybrid RAG	planned ⏱️	Integrating Knowledge Graphs and Vector RAG	HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
LlamaIndex Workflows Support	✅	Event-driven abstraction used to chain together several events
Self-Route	✅	Hybrid approach (RAG / LC LLM)	Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
Secure ICL	planned ⏱️	Secure ICL implementation for security sensitive applications	Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Dense-X-Retrieval	planned ⏱️	Retrieval based on propoistions extracted from each node	Dense X Retrieval: What Retrieval Granularity Should We Use?
Corrective RAG	planned ⏱️	Incorporating a self-correction mechanism that evaluates and refines retrieved knowledge	Corrective Retrieval Augmented Generation

🗡️ Chunking Techniques	Implemented	Description
Sentence	✅	Chunk by Sentence

🆒 Cool Bonus	Implemented	Description
Docker Support	✅	EffectzGPT is deployable via Docker
Inbuilt ChatBot	✅	A Next.js based ChatBot is available
Inbuilt Admin Panel	✅	A Next.js based Admin Panel is available
Whatsapp Intergration	✅	Whatsapp business API is supported
Messenger Intergration	✅	Facebook messenger API is supported
Streaming API	✅	For Applications like chatbots
Non-Streaming API	✅	For Non-streaming RAG applications

🤝 RAG Libraries	Implemented	Description
LlamaIndex	✅	Implement LlamaIndex RAG pipelines

🗄️ Vector DB Support	Implemented	Description
Chroma	✅	AI-native open-source vector database
Qdrant	✅	Open-source vector database and vector search engine
Weaviate	planned ⏱️	Open-source vectore database

Getting Started

To run EffectzGPT, you have to build a Docker image from the Dockerfile and start a docker container with that image.

Prerequisites

Make sure you have the following installed on your system:

node
python 3.11
Docker
Docker Compose

Environment Variables

Environment Variable	Example Values	Description	Scope	IsRequired
NEXT_PUBLIC_CHAT_API_BASE_URL	http://localhost:5000	Set backend API end point	UI	Y
APP_PORT	5000	Set port to start the backend app	BACKEND	Y
TOP_K	10	Set number of similar embeddings to return	BACKEND	Y
VECTOR_STORE_PROVIDER	chroma	Set vector store provider	BACKEND	Y
MODEL_PROVIDER	openai	Set LLM provider	BACKEND	Y
MODEL	gpt-3.5-turbo	Set LLM	BACKEND	Y
EMBEDDING_MODEL	text-embedding-3-large	Set embedding model	BACKEND	Y
OPENAI_API_KEY	Your OpenAI API key	Set OpenAI API key	BACKEND	Y
SYSTEM_PROMPT	Your system prompt	Set system prompt	BACKEND	Y
COHERE_API_KEY	Your Cohere API key	Set Cohere API key	BACKEND	Y
STREAM_TIMEOUT	60000	Time out in ms for streaming a	BACKEND	N
CHROMA_COLLECTION	./default	chroma collection name	BACKEND	N
CHROMA_PATH	./chromadb	path to chroma file storage	BACKEND	N
CHROMA_HOST	localhost	chroma DB url ( if this value is defined CHROMA_PATH will be ignore )	BACKEND	N
CHROMA_PORT	8000	Chroma DB access port ( if this value is defined CHROMA_PATH will be ignore )	BACKEND	N
EMBEDDING_DIM	1024	embedding size	BACKEND	N
LLAMA_CLOUD_API_KEY	Your LLAMA cloud API key	LLAMA cloud key	BACKEND	N
COHERE_API_KEY	Your Cohere cloud API key	Cohere key	BACKEND	N

Endpoints

The docker container exposes the following endpoints.

Admin Panel: http://localhost:3000/admin
Chat UI: http://localhost:3000
Docs UI: http://localhost:3000/docs

Deploying With Docker Compose

You can easily deploy EffectzGPT to your own infrastructure with Docker Compose.

Prerequisites

Make sure you have the following installed on your system:

Docker
Docker Compose

Steps

Clone the repository.

git clone https://github.com/effectz-ai/effectz-gpt.git

# navigate to backend folder and build docker image
cd effectz-gpt/backend
docker build -t effectzai/effectzgpt_b .

# navigate to frontend folder and build docker image
cd effectz-gpt/frontend
docker build -t effectzai/effectzgpt_f .

Start frontend and backend services defined in the docker-compose.yml file.

docker-compose up -d effectzgpt_ui

Or start a specific service (detached mode).

docker-compose up -d <service_name>

Notes

If you make changes to the code or Dockerfile, you may need to rebuild the images.

docker-compose up --build

The docker-compose.yml file uses environment variables. To set environment variables, you can follow one of the following methods.

Using a .env file (create a .env file and define the environment variables).

VAR_NAME1=value1

Exporting environment variables directly.

export VAR_NAME1=value1

Required and optional environment variable can be found above in Environment Variables

Trusted By Our Clients

Logo of University of Florida Logo of Chitra Logo of Cleolinks AB

Used In Cutting Edge Research

Name	Reference
RMF-GPT	RMF-GPT — OpenAI GPT-3.5 LLM, Blockchain, NFT, Model Cards and OpenScap Enabled Intelligent RMF Automation System
SliceGPT	SliceGPT – OpenAI GPT-3.5 LLM, Blockchain and Non-Fungible Token Enabled Intelligent 5G/6G Network Slice Broker and Marketplace
DevSec-GPT	DevSec-GPT — Generative-AI (with Custom-Trained Meta's Llama2 LLM), Blockchain, NFT and PBOM Enabled Cloud Native Container Vulnerability Management and Pipeline Verification Platform

Similar repos

labring/FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of…

29,856

langchain-ai/opengpts

6,709

sabeeralikp/llama_flow

langgenius/dify

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative…

158,871

khulnasoft/GPT-DB

KavinKumar22K/db-gpt

d0ublecl1ck/DB-GPT

gengwanli/DB-dev

download on Mar 15 2025