You will get robust english to relevant data fetching pipeline


Project details
You will get a robust english to sql to relevant data (from your dataset provided) pipeline which let's you access the relevant data using plain english. It can be used to generate timely reports and required plots as well.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
AI Chatbot, Natural Language UnderstandingAI Development Language
PythonAI Tools
Hugging Face, PyTorch, StreamlitAI Models
BERT, ChatGPT, LLaMAWhat's included $50
These options are included with the project scope.
$50
- Delivery Time 14 days
- AI Model Integration
- Database Integration
- Detailed Code Comments
- Model Deployment
- Model Documentation
- Model Testing & Optimization
- Model Tuning
- Natural Language Processing
- Prompt Engineering
- Setup File
- Source Code
About Sarath
Data Scientist | Machine Learning | LLMs | Python | SQL
Bengaluru, India - 2:32 pm local time
I have a deep command of traditional supervised and unsupervised approaches, including linear and logistic regression, decision trees, ensemble methods (random forests, gradient boosting machines, XGBoost, LightGBM, CatBoost), and clustering algorithms. Beyond these, I’ve leveraged advanced frameworks such as MLflow to manage experiment tracking and model versioning, ensuring reproducibility and rapid iteration. I have also spent quite some time in extracting raw data (form APIs, html webpages etc) and generating training datasets for ML models.
More recently, I’ve extended my skill set to the cutting edge of natural-language processing and large-language models (LLMs). I designed and implemented a Natural-Language-to-SQL (NL2SQL) pipeline that translates plain-English queries into optimized SQL statements—streamlining data exploration for nontechnical stakeholders and reducing analysis turnaround times.
My technical toolkit includes:
* **Programming & Scripting:** Python (pandas, NumPy, scikit-learn, PyTorch), SQL (PostgreSQL, BigQuery, ClickHouse)
* **Workflow Orchestration & Cloud Platforms:** Apache Airflow, AWS (Lambda, S3, EC2), GCP (BigQuery, AI Platform)
* **Model Management & Deployment:** MLflow for experiment tracking; Sagemaker for LLM deployment, containerized deployments using Docker;
* **Data Storage & Analytics:** Relational and columnar databases (PostgreSQL, ClickHouse), data warehouses (BigQuery)
Steps for completing your project
After purchasing the project, send requirements so Sarath can start the project.
Delivery time starts when Sarath receives requirements from you.
Sarath works on your project following the steps below.
Revisions may occur after the delivery date.
Ingest the relevant data into a database
Develop a natural language to sql query generation pipeline
Creates a sql query for each question asked by the user
