| S.No | Project Name | Description | Official Repo | Tech Stack |
|---|---|---|---|---|
| 1 | Multi-PDFs 📚ChatApp AI Agent 🤖 | Chat seamlessly with Multiple PDFs using Langchain, Google Gemini Pro & FAISS Vector DB with Seamless Streamlit Deployment. Get instant, accurate responses from Awesome Google Gemini OpenSource language Model. 📚💬 Transform your PDF experience now! 🔥✨ |  |
F/w: Langchain Model: Google Gemini Pro, Vector DB: FAISS Deployment: Streamlit |
| 2 | 🖼️Image to Speech GenAI Tool Using LLM 🌟♨️ | AI tool that generates an Audio short story based on the context of an uploaded image by prompting a GenAI LLM model. | |
F/w: Langchain Model: HuggingFace Models, OpenAI GPT-3.5, Vector Deployment: Streamlit, Hugging Spaces |
| 3 | Youtube Video Transcribe Summarizer LLM App | End To End Youtube Video Transcribe Summarizer LLM App With Google Gemini Pro providing detailed notes based on YouTube video transcripts. With the power of AI, you can now convert video transcripts into comprehensive study materials. | |
Google Gemini Pro |
| 4 | End to end RAG LLM App | Step-by-Step Guide to Building a RAG LLM App with LLamA2 and LLaMAindex | |
LLamA2 and LLaMAindex |
| 5 | Resume ATS Tracking LLM Project | This is a project aiming to optimize the recruitment process. It integrates an advanced Applicant Tracking System with Google Gemini Pro, streamlining resume parsing, keyword matching, and candidate evaluation for an efficient end-to-end solution in talent acquisition. | |
Google Gemini Pro |
| 6 | End To End Text To SQL LLM App Along With Querying SQL Database | The "Text to SQL LLM App with Google Gemini Pro" is a software application that facilitates the conversion of natural language queries into SQL commands. It also enables querying SQL databases directly using the generated SQL commands. | |
Using Google Gemini Pro |
| 7 | End To End Multi Language Invoice Extractor Project | MultiLanguage Invoice Extractor 💼✨ Discover the power of MultiLanguage Invoice Extractor! This Streamlit app, powered by Google Gemini Pro Vision AI, makes extracting information from invoice images a breeze. Upload images, add prompts, and get detailed responses effortlessly. With multi-language support. | |
Using Google Gemini Pro |
| 8 | PDF Document Question Answering LLM System | |
Langchain,Cassandra,Astra DB,Vector Database | |
| 9 | Fine Tune LLAMA 2 With Custom Dataset | |
Using LoRA And QLoRA Techniques |
|
| 10 | End to End RAG LLM App: Indexing & Querying Multiple Pdf's | |
Using Llamaindex and OpenAI | |
| 11 | Real Time Financial Stock Analysis | |
Using CrewAI, Groq, LangChain & some other APIs like browserless, Serper and SEC EDGAR API |
|
| 12 | Medical ChatBot | The Llama2 Medical Bot is a powerful tool designed to provide medical information by answering user queries using state-of-the-art language models and vector stores. The bot runs on a decent CPU machine with a minimum of 16GB of RAM. | |
Using Llama2 and Sentence Transformers. Powered by Langchain and Chainlit |
| 13 | Medical Mixture-of Experts LLM | Medical Mixture of Experts LLM using Mergekit. | |
MergeKit |
| 14 | Haystack and Mistral 7B RAG Implementation | Haystack and Mistral 7B RAG Implementation. It is based on completely open-source stack. | |
Haystack-and-Mistral-7B-RAG |
| 15 | Power QnA Chatbot | Question Answer Generation App using Mistral 7B, Langchain, and FastAPI. | |
Mistral 7B, Langchain, and FastAPI. |
| 16 | RAG | Gemma-7B-RAG-using-Ollama | |
Gemma-7B-RAG-using-Ollama |
| 17 | On-device LLM Inference | On-device LLM Inference using Mediapipe LLM Inference API. | |
Using Mediapipe LLM Inference API. |
| 18 | Personal Voice Assistant using OpenAI | |
||
| 19 | Fast Fine Tuning and DPO Training of LLMs using Unsloth | |
||
| 20 | Groq Chat App | Groq Chat App built using Groq API and Streamlit. | |
Groq API and Streamlit. |
| 21 | Medical RAG using Bio-Mistral-7B | This is a RAG implementation using Open Source stack. BioMistral 7B has been used to build this app along with PubMedBert as an embedding model, Qdrant as a self hosted Vector DB, and Langchain & Llama CPP as an orchestration frameworks | |
RAG implementation, BioMistral 7B, PubMedBert, Qdrant, Langchain & Llama CPP |
| 22 | End-to-End RAG Implementation-using Amazon Bedrock | |
Amazon Bedrock | |
| 23 | Faster Stable Diffusion using SSD-1B | Faster Stable Diffusion using SSD-1B. A gradio app inside for demo. | |
Stable Diffusion using SSD-1B, Gradio |
| 24 | Phi-2 Fine-Tuning | Phi-2 Fine Tuning to build a mental health GPT. | |
Phi-2-Fine-Tuning |
| 25 | Medical RAG Using Meditron-7B-LLM | Medical RAG QA App using Meditron 7B LLM, Qdrant Vector Database, and PubMedBERT Embedding Model. | |
Meditron 7B LLM, Qdrant, PubMedBERT |
| 26 | Fastest Image Generation using LCM LoRA. | |
LoRA | |
| 27 | HyDE based RAG using NVIDIA NIM | |
HyDE based RAG, NVIDIA NIM | |
| 28 | Building Intelligent Systems Using Visdum-AI | |
Visdum-AI | |
| 29 | Zephyr 7B beta RAG Demo inside a Gradio App | Zephyr 7B beta RAG Demo inside a Gradio app powered by BGE Embeddings, ChromaDB, and Zephyr 7B Beta. | |
Zephyr 7B beta, RAG, Gradio, BGE Embeddings, ChromaDB |
| 30 | LangChain Expression Language | Intro to LangChain Expression Language. | |
LEL |
| 31 | Fine Tuning Multimodal LLM | Fine Tuning Multimodal LLM "Idefics 9B" on Pokemon Go Dataset available on Hugging Face. | |
Multimodal LLM "Idefics 9B" |
| 32 | RAG Tool using Haystack, Mistral and Chainlit | RAG Tool using Haystack, Mistral, and Chainlit. All open source stack on CPU. | |
RAG, Haystack, Mistral, Chainlit |
| 33 | Prompt Compression Using LLMLingua | Prompt Compression using LLMLingua. It helps with token's cost and latency. | |
Prompt Compression, LLMLingua |
| 34 | Stream Diffusion in Colab | |
||
| 35 | Multimodal-RAG Using Langchain | Multimodal-RAG-using-Langchain | |
RAG, Langchain |
| 36 | Secure-AI-LLM Chatbots Using Prompt Injection Prevention Techniques | Prompt Injection & Prevention techniques. Secure your AI Chatbots built using LLMs. | |
Prompt Injection, LLMs |
| 37 | GGUF Quantization Of any LLM | GGUF-Quantization-of-any-LLM | |
GGUF-Quantization |
| 38 | Deltamon Anime Using LoRA | Deltamon-Anime-using-LoRA | |
LoRA |
| 39 | Evaluation of LLMs and RAGs | Evaluation-of-LLMs-and-RAGs. A complete guide to evaluate LLMs and RAGs covering theory and code based approaches. | |
LLMs, RAGs |
| 40 | Unsloth Fine-Tuning | Unsloth-Fine-Tuning | |
Unsloth |
| 41 | SLIM Models by LLMWare | SLIM Models by LLMWare. A streamlit app showing the capabilities for AI Agents and Function Calls. | |
SLIM Models, LLMWare, AI Agents, Function Calls, Streamlit App |
| 42 | Small Multimodal Vision Model | Small Multimodal Vision Model "Imp-v1-3b" trained using Phi-2 and Siglip. | |
Small Multimodal Vision Model "Imp-v1-3b", Phi-2, Siglip |
| 43 | Langsmith Implementation | Langsmith-Implementation | |
Langsmith |
| 44 | Langserve Implementation | Langserve-Implementation | |
Langserve |
| 45 | Multimodal AI App using Llava 7B and Gradio | Multimodal AI App using Llava 7B and Gradio | |
Llava 7B, Gradio |
| 46 | Perplexity Lite | Perplexity Lite using Langgraph, Tavily, and GPT-4. | |
LangGraph, Tavily and GPT-4. |
| 47 | Generative-AI-LLM-Projects | Gen AI End To End Large Language Model Projects | |
30+ Gen AI End To End Large Language Model Projects With Latest OpenSource Models, Fine Tuning |
| 48 | MusicAI | Custom Music Generation with Transformers and PyTorch | |
Transformers, PyTorch |
| 49 | Audio Summarization App using Gemini LLM | Audio Summarization App using Gemini LLM | |
Gemini 1.5, LLM |
| 50 | Fine Tune Multimodal LLM "Idefics 2" using QLoRA | Fine Tune Multimodal LLM "Idefics 2" using QLoRA. | |
Multimodal LLM "Idefics 2", QLoRA |
| 51 | Llama 3 ORPO FineTuning | Llama 3 ORPO Fine Tuning on A100 in Colab Pro. | |
Llama 3 ORPO |
| 52 | RAG using Llama3, Langchain and ChromaDB | This project utilizes Llama3 Langchain and ChromaDB to establish a Retrieval Augmented Generation (RAG) system. This system empowers you to ask questions about your documents, even if the information wasn't included in the training data for the Large Language Model (LLM). Retrieval Augmented Generation works by first performing a retrieval step when presented with a question. This step fetches relevant documents from a special vector database, where the documents have been indexed. | |
RAG using Llama3, Langchain and ChromaDB |
| 53 | LLAMA-3 70B LLM with NVIDIA | Meet LLAMA3 Chat AI App! 🚀 Meta Unveils Llama 3, the Most Powerful Open Source Model Yet. Chat seamlessly with LLAMA3 Chatbot. Get instant, Accurate responses from Awesome Llama3 OpenSource language Model📚💬 |
|
LLAMA-3 70B LLM with NVIDIA, Streamlit UI |
| 54 | Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora | Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora | |
Llama 3 with PyTorch FSDP and Q-Lora, Fine Tuning |
| 55 | 🌟META LLAMA3 GENAI Real World UseCases End To End Implementation Guides📚 | LLAMA3 GENAI UseCases | |
Llama3, FineTuning, Deployment, RAG, Langchain |
| 56 | ⭐Meta's LLaMA3-Quantization🦌💎💫 | LLaMA3-Quantization is the official implementation of paper "How Good Are Low-bit Quantized LLAMA3 Models?". Here evaluation is done on the 10 existing post-training quantization and LoRA-finetuning methods of LLaMa3 on 1-8 bits and diverse datasets to comprehensively reveal LLaMa3's low-bit quantization performance. | |
Quantization, GenerativeAI, llama3-meta-ai |
| 57 | Ollama-UseCases🌟 | This repo brings numerous use cases from the Open Source Ollama | |
Ollama |
| 58 | AI Agents💫 | Design Patterns for Multi Agents Frameworks Like Autogen, Langraph, Taskweaver, Crewai,etc | |
Multi Agents Frameworks Like Autogen, Langraph, Taskweaver, Crewai |
| 59 | RAG with LlamaIndex and NVIDIA | RAG with LlamaIndex and NVIDIA | |
RAG with LlamaIndex and NVIDIA |
| 60 | Quantize LLM using AWQ | Quantize LLM using AWQ | |
Quantize LLM using AWQ |
| 61 | LLMs Inference and Fine Tuning | Estimate Memory Consumption of LLMs Inference and Fine Tuning | |
LLMs Inference and Fine Tuning |
| 62 | Phi-3 LLM by Microsoft | Phi-3 LLM by Microsoft Implementation | |
Phi-3 LLM |
| 63 | 🔥Advanced RAG💫🌟 | Advanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the Langchain, OpenAI GPTs ,META LLAMA3 , Agents. | |
Advanced Retrieval-Augmented Generation (RAG), Langchain, OpenAI GPTs ,META LLAMA3 , Agents. |
| 64 | RAG-using-AWS-Bedrock-and-Azure-OpenAI | RAG-using-AWS-Bedrock-and-Azure-OpenAI | |
RAG, AWS-Bedrock, Azure-OpenAI, Generative AI |
| 65 | LLM SECURITY 2024 | Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024 | |
OWASP, LLM Security, Vulnerability's, Data Security, Cyber Security, Generative AI, LLM Security |
| 66 | GPT4o-API-Implementation-GPT4-RAG | Getting Started with GPT4 API, GPT4 RAG, OpenAI GPT4 Assistant, OpenAI Models | |
openai-api, gpt-4, large-language-models, generative-ai, gpt4-api, gpt4o |
| 67 | PaliGemma Inference and Fine Tuning | PaliGemma Inference and Fine Tuning | |
PaliGemma, Inference, Fine Tuning, Generative-AI |
| 68 | LLMs Evaluation | LLMs Evaluation | |
LLMs Evaluation, Generative AI |
| 69 | Building RAG With OpenAI GPT-4o(omni) Model Using Objectbox Vector Database | Building RAG With OpenAI GPT-4o(omni) Model Using Objectbox Vector Database | |
RAG, OpenAI GPT-4o(omni) Model,MObjectbox Vector Database |
| 70 | PaliGemma FineTuning | PaliGemma FineTuning | |
PaliGemma, FineTuning |
| 71 | RAG Evaluator | A library for evaluating Retrieval-Augmented Generation (RAG) systems | |
RAG Evaluator, Metrics: BLEU, ROUGE, BERT, Perplexity,Diversity, Racial Bias |
| More Projects list is coming...!!! |
Distributed under the MIT License. See LICENSE for more information.
