Sachin Khandewal's repositories
DSPy-Chain-of-Thought-RAG
Building a Chain of Thought RAG Model with DSPy, Qdrant and Ollama
intelligentgallery
Intelligent Image Gallery with Uploads, Deduplication, and Text-Based Search Using Vector DB Qdrant
Financial-RAG-GPU-less-Mistral-Langchain
All CPU efficient GPU-less Financial Analysis RAG Model with Qdrant, Langchain and GPT4All x Mistral-7B, run RAG without any GPU support!
Finetuning-Mistral-7B-Chat-Doctor-Huggingface-LoRA-PEFT
Finetuning Mistral-7B into a Medical Chat Doctor using Huggingface 🤗+ QLoRA + PEFT.
AI-Assistant-Clinics-Medical-Data-Qdrant-Dspy-Groq
Building Private Healthcare AI Assistant for Clinics Using Qdrant Hybrid Cloud, DSPy and Groq - Llama3
Knowledge-graphs-RAG-DAGWorks-Hamilton-FalkorDB-OpenAI
Creating Knowledge Graphs and Productionalizing your RAG model with using Dagworks, FalkorDB, Langchain and OpenAI
Firewall-action-using-decision-tree
Firewall actions (Allow, Deny, Drop and reset-both) will be predicted based on 11 parameters. Algorithms used: Decision Tree, Random forest, Gradient Boosting
Forest-cover-type-using-deep-learning
Predicting forest cover type from cartographic variables only (no remotely sensed data). The actual forest cover type for a given observation (30 x 30 meter cell) was determined from US Forest Service (USFS) Region 2 Resource Information System (RIS) data. Independent variables were derived from data originally obtained from US Geological Survey (USGS) and USFS data. Data is in raw form (not scaled) and contains binary (0 or 1) columns of data for qualitative independent variables (wilderness areas and soil types). This study area includes four wilderness areas located in the Roosevelt National Forest of northern Colorado. These areas represent forests with minimal human-caused disturbances, so that existing forest cover types are more a result of ecological processes rather than forest management practices. Some background information for these four wilderness areas: Neota (area 2) probably has the highest mean elevational value of the 4 wilderness areas. Rawah (area 1) and Comanche Peak (area 3) would have a lower mean elevational value, while Cache la Poudre (area 4) would have the lowest mean elevational value. As for primary major tree species in these areas, Neota would have spruce/fir (type 1), while Rawah and Comanche Peak would probably have lodgepole pine (type 2) as their primary species, followed by spruce/fir and aspen (type 5). Cache la Poudre would tend to have Ponderosa pine (type 3), Douglas-fir (type 6), and cottonwood/willow (type 4). The Rawah and Comanche Peak areas would tend to be more typical of the overall dataset than either the Neota or Cache la Poudre, due to their assortment of tree species and range of predictive variable values (elevation, etc.) Cache la Poudre would probably be more unique than the others, due to its relatively low elevation range and species composition.
Human-characters-detection-from-a-video-The-Office-S06E01-Computer-vision-and-Facenet
This is a self mini project that I undertook for my learning process. I have taken an episode from my favourite TV series called The Office (US) S06E01. Using this episode I have extracted images & using those images I have classified 17 characters using CV2 and Facenet Model.
Brain-MRI-Images-for-Brain-Tumor-Detection
Brain MRI Images for Brain Tumor Detection using convolutional neural networks.
Breast-cancer-benign-or-malignant-using-ensemble-algorithms
Classification problem where based on 31 parameters we have to classify diagnosis as either "Benign" or "malignant".
Classification-Algorithms
Here i will upload all the Classification algorithms performed on a College admit dataset which has 4 attributes admit (0 or1), gpa, gre score and rank in the school
Classifying-10-monkey-species-using-InceptionV3-model
This is an image classification problem, where there are 10 classes or species of monkeys and based on the their images we have to predict their species. I have used transfer learning here using InceptionV3 model.
Co2-emissions-prediction-using-gradient-boosting-ensemble-algorithm
Based on 11 parameters of a vehicle, Co2 emissions are to be predicted, test_size=12.5% and train_size=87.5%, algorithm used is Gradient boosting. In this exercise I've also used One hot encoding on one of the parameter to incorporate it into the train set.
Customer-attrition-prediction-using-bank-dataset
Based on bank dataset collected over a European area, we have to predict if the customer will leave the bank or stay with the bank (Customer attrition).
Regression-Algorithms
This is my college practice work, where i try to learn and cover all the regression algorithms (preferably in python)
Tree-Based-Regression-Algorithms
This is my college practice work, where i try to learn and cover all the tree based regression algorithms (preferably in python).