🚀 Experience: Proven background in designing and developing state-of-the-art cloud-native technical solutions tailored to meet business needs.
💡 Innovation: Hold patents in field of Software Engineering and Artificial Intelligence, you can read about them here and here
🌐 Current Focus: Currently dedicated to building AI Powered Engineering Platforms for practical usage.
🔧 Technical Expertise: Key strengths include crafting technology roadmaps, designing platforms, and implementing automation solutions for intricate business workflows, resulting in cost savings and streamlined operations.
💼 Versatile Experience: Worked across diverse domains, from finance (capital markets) to knowledge management and material management.
🏗️ Architectural Mastery: Created and managed the architecture of complex Web, SOA, and MOM-based applications.
🔄 Cloud Migration: Played a pivotal role in migrating monolith applications to microservices and cloud-based architecture, employing microservices decomposition design patterns.
- How to build AI Action Processor: Execute actions based on prompt (OpenAI, Gemini, Anthropic) here
- Process images with Image Processor: Trigger actions based on images here
- Build AI Autonomous Agent: Execute tasks based on scripts here
- Convert Image to Text: Convert images to text here
- Covert Image to Pojo and integrate in your Java application: Convert images to Pojo here
- Convert Image to Json and make a rest call: Convert images to Json here
- Convert Image to XML for SOAP Call: Convert images to XML here
- Integrate AI with Selenium and call Actions Automatically: Execute actions based on Selenium script here
- AI and Spring Integration: Integrate with Spring Boot here
- AI based Script Processor: Execute tasks based on scripts here
- Integrate AI with Http Rest calls: Execute actions based on HTTP requests here
- Adanced Prompt Processor with AI: Execute tasks based on prompts here
- Convert Promots to Java objects with Prompt Transformer: Convert prompts into various formats ( Java , Json , XML) here
- Use AI based Custom GSON: Convert special values in prompts here
- Provide Subprompt Processing: Break prompts into multiple subprompts here
- Human In Loop Validationhere
- Explainablityhere
- Kubernets Integration [here]( here
- Multi Command Processorhere
- Hallucination Detectorhere
- Bias Detectorhere
| Example Name | Level | Description | Link |
|---|---|---|---|
| TinyLama.ipynb | Beginner | Load open source TinyLlama-1.1B-Chat-v0.6 for Text completion | My First LLM Experiment |
| Vector_Example.ipynb | Beginner | Vector Basic | Vector Databases |
| Chroma_Example_1.ipynb | Beginner | How to use ChromaDB | Vector Databses |
| Chroma_Example_2.ipynb | Beginner | How to Use ChromaDB advanced | Vector Databases |
| AlBert.ipynb | Intermediate | Implementaiton of Bert Model | LLM Models Encyclopedia |
| Cerebras.ipynb | Beginner | facilitate research into LLM scaling laws using open architectures and data set | LLM Models Encyclopedia |
| cookGPT.ipynb | Intermediate | calling custom fine tuned model on open ai | |
| cookGPT_NewRecipe.ipynb | Advanced | asking to create new recipe ( prompting) | |
| CookGPT_SQL.ipynb | Intermediate | LLM for SQL queries | Ai for SQL |
| dataset_experiment.ipynb | Beginner | Play around with open source data set from hugging face or kaggle | |
| distilbert.ipynb | Beginner | Another variation of bERT | LLM Models Encyclopedia |
| Examples_BERT.ipynb | Beginner | bERt examples | LLM Models Encyclopedia |
| Flan_T5.ipynb | Beginner | Google T Flan | LLM Models Encyclopedia |
| Llama_CookGPT_AutoTrain_LLM.ipynb | Intermediate | Fine Tuning using Hugging Face Autotrain Advaned | |
| MovieReview.ipynb | Beginner | Basic Open AI example | |
| NLLB.ipynb | Intermediate | Indic Languages Translation | LLM for Indic Languages |
| PredictionImage.ipynb | Beginner | Prediction based on image data using google deplot | LLM Models Encyclopedia |
| Quantized_CookGPT.ipynb | Beginner | Quantized models for 8 Bit loading | Quantize a model |
| TrainCustom.ipynb | Intermediate | Fine Tune using Trainer ApI from Hugging Face | |
| Using_CookGPT_AutoTrain_LLM.ipynb | Intermediate | Fine tune large model | Auto Train Advanced |
| finetuning.ipynb | Intermediate | Fine Tune on Open AI using Colab | |
| phi_2.ipynb | Beginner | Microsoft Phi LLM example | LLM Models Encyclopedia |
| CookGPT_SQL_Langchain.ipynb | Intermediate | SQL , LLM Model and Langchain example | Ai for SQL |
| Generate_Free_video.ipynb | Intermediate | Video generation using AnimateDiff | Free Images in Code |
| Generate_Image_Free.ipynb | Intermediate | Image generation using openjourney - stable diff | Free Images in Code |
| Stable_Diff.ipynb | Intermediate | Image Generation using Stable Diff | Free Images in Code |
| Generate_Data.ipynb | Beginner | Generate Synthetic Data using Open Ai | |
| Face_ID.ipynb | Intermediate | Face Id recognization using InsightFace | Free Images in Code |
| Gradio.ipynb | Intermediate | Webapp using Gradio and LLM on Colab | Use Gradio and LLM |
| embeddings.ipynb | Intermediate | Embeddings and Quantizaton | Model Quantization |
| gradio_advanced.ipynb | Intermediate | How to Quantize a model | Use Gradio and Quantized model |
| image_QA.ipynb | Intermediate | Recognize objects in image | Detect Objects in Images |
| face_recognize.ipynb | Intermediate | Face Detection and Recognization | Face Detection and Recognization |
Integrade examples with LLM using Langchain, Huggingface pipeline, LamaIndex, or Haystack
| Example Name | Library | Description | Link |
|---|---|---|---|
| TinyLama.ipynb | Langchain | Load open source TinyLlama-1.1B-Chat-v0.6 for Text completion | My First LLM Experiment |
| Vector_Example.ipynb | Pipeline | Vector Basic | Vector Databases |