Freelancers using LangChain in New DelhiFreelancers using LangChain in New Delhi
ProjectsPeople
Suyash Dubey's avatar
Suyash Dubey
Delhi, India
I build production AI agents that automate real workflows
I build production AI agents that automate real workflows
Cover image for Built an LLM-powered question-answering application
Built an LLM-powered question-answering application that lets users ask natural-language questions over large document corpora and get accurate, grounded answers, instead of manually searching through documents for the right section. Designed and built the full RAG pipeline independently, from document ingestion through to answer generation, as a technical demonstration of production-grade retrieval-augmented generation using AWS-native tooling. Key Challenges: Documents exceeding token limits: Large source documents couldn't be fed directly into the LLM's context window, so they had to be broken down without losing meaning or context across chunks. Finding the right context: With a large corpus, the system needed to reliably surface the specific chunks relevant to a given question, not just the most textually similar ones. Grounded, accurate answers: Answers had to be based on the actual retrieved content, not the model's general knowledge, to avoid confidently wrong responses. Working within a managed AWS ecosystem: Embeddings, storage, and generation all needed to work together cleanly using Bedrock-native models rather than a patchwork of external services. Approach: Document loading and chunking Processed large documents into manageable chunks sized to stay within model token limits while preserving enough context for coherent retrieval. Vector embeddings with Amazon Titan Generated vector embeddings for each document chunk using Amazon Titan, capturing semantic meaning rather than just keyword overlap. Vector storage and retrieval Stored the embeddings in a vector database, enabling fast similarity search to pull the most relevant chunks for any given question. RAG-based answer generation with Claude on Bedrock When a question comes in, the system retrieves the relevant chunks and passes them as context to Anthropic Claude via Amazon Bedrock, which generates an answer grounded in the retrieved content rather than relying on parametric memory alone. Results & Impact: Accurate, source-grounded answers over document corpora too large to fit in a single context window. A scalable retrieval architecture that separates document processing, embedding, and generation, so any of the three can be swapped or scaled independently. A fully AWS-native RAG pipeline, demonstrating fluency with Bedrock's embedding and generation models working together in production patterns. Tech Stack Python · LangChain · AWS Bedrock · Amazon Titan · Anthropic Claude · FAISS DB
1
82
Cover image for Built and maintained a HIPAA
Built and maintained a HIPAA compliant production medical AI scribe system that uses multi-step LLM agents to extract clinical entities directly from physician-patient conversations and turn them into structured medical notes, cutting down the manual transcription work clinicians used to do after every visit. Multi-stage clinical workflow: Documentation, coding, and review each have different logic and conditional paths, and the system needed to branch correctly between them without losing context. Clinical accuracy: Generated notes had to be grounded in real patient history and clinical guidelines, not just plausible-sounding text. Production reliability: As a live system handling real conversations, every agent run needed to be observable, debuggable, and monitored for cost and latency in real time. Non-technical requirements gathering: Clinical needs had to be captured accurately from stakeholders without a technical background and translated into precise agent logic. Approach: Stateful agent orchestration with LangGraph Designed LangGraph-based agent workflows with conditional branching, allowing the system to move correctly across documentation, coding, and review stages based on conversation content. Context-grounded note generation with RAG Built a RAG pipeline on AWS Bedrock with embeddings, so every generated note is grounded in the patient's actual history and relevant clinical guidelines rather than generic output. Full production observability Integrated Langfuse across all agent runs to track token usage, latency, and model KPIs, giving the team visibility into system health and cost in production, not just at build time. Clinical stakeholder collaboration Ran requirements sessions directly with clinical staff, converting their documentation needs into concrete agent behavior specs and validation criteria. Results & Impact: ~40% reduction in manual transcription time for clinicians using the system. Clinically grounded output, with notes tied to real patient history and guidelines instead of unsupported generation. Full production observability, with token usage, latency, and model performance tracked continuously. A workflow clinicians could trust, built through direct collaboration rather than a black-box handoff. Provided Services & Solutions: 📌 AI Agent Development (LangGraph) 📌 RAG Pipeline Development (AWS Bedrock) 📌 LLM Observability (Langfuse) 📌 Cloud Infrastructure (AWS Lambda, S3, DynamoDB) 📌 Stakeholder Requirements Translation 📌 Production ML Systems Tech Stack Python · LangChain · LangGraph · AWS (Bedrock, Lambda, S3, DynamoDB) · Langfuse · TypeScript · REST APIs
2
81
Cover image for Overview 📖 Built an end-to-end agentic
Overview 📖 Built an end-to-end agentic content creation pipeline for a fast-growing AI-powered SEO platform. The system chains multiple LLM agents together to research, draft, and optimize content automatically, replacing what used to be a manual, multi-step editorial process with a single automated workflow. Collaboration 🤝 Partnered directly with the platform's engineering team to design and ship the automation layer that now sits at the core of their content operations, turning a bottlenecked manual process into a scalable, always-on pipeline. Key Challenges 🤔 Multi-step content logic: Research, drafting, and optimization each require different context and tone, but had to feel like one coherent pipeline, not three disconnected tools. Consistency at scale: Every piece of generated content had to match brand voice and pass compliance checks, without a human reviewing each one manually. Orchestration complexity: Content jobs needed to trigger reliably from webhooks and third-party APIs, run through multiple agents in sequence, and fail gracefully without stalling the whole pipeline. Performance under load: The backend had to stay fast and stable as content throughput scaled up. Approach 🔍 Agentic content pipeline design Designed a multi-step LangChain agent chain with tool-calling, where each agent (research, drafting, optimization) has a clearly scoped role and hands off structured output to the next. Workflow orchestration with n8n Built n8n automation workflows to handle webhook triggers, third-party API integrations, and job routing, removing the need for manual intervention at almost every stage. Brand voice & compliance enforcement Layered in structured prompting and validation steps so generated content stays on-brand and passes compliance checks automatically, at scale. Backend performance tuning Optimized FastAPI endpoints and managed Azure-hosted PostgreSQL databases to keep latency low under high content-throughput conditions. Results & Impact ✨ ~60% reduction in manual intervention across the content pipeline, freeing the team to focus on strategy instead of babysitting workflows. Consistent brand voice at scale, with compliance checks running automatically instead of manually. Reliable, low-latency infrastructure validated under real content-throughput loads. A reusable agentic architecture the platform can extend to new content types without rebuilding the pipeline. Provided Services & Solutions ✅ 📌 AI Agent Development (LangChain) 📌 Workflow Automation (n8n) 📌 LLM Integration (GPT-4, Claude) 📌 API Development (FastAPI) 📌 Cloud Database Management (Azure, PostgreSQL) 📌 Architecture Design & Consulting Tech Stack Python · FastAPI · LangChain · n8n · GPT-4 · Claude · Azure · PostgreSQL
2
86
Cover image for My submission for replitbuildathon. Features
My submission for replitbuildathon. Features an AI agent that answers inbound leads in seconds, qualifies them against your rules, and books the appointment — rebrandable for a new client in about a minute. Most small businesses lose leads to silence. Someone lands on the site at 9pm, fills nothing in, and leaves. Frontdesk is the agent that catches them. It greets the visitor, works through the qualifying questions you defined, scores what it hears out of 100, books the appointment, and hands the team a lead with the transcript and a follow-up email already drafted. The reason it's a template and not a product: it's built to be rebranded. Set a logo and two colours in Brand Studio and the entire app, the chat widget, and the design system documentation retint together, because they all read the same tokens. Agencies fork it once per client. Applying a preset doesn't recolour the same install: it opens a different one, with its own agency name, business name and greeting. Checkout the app here: https://frontdeskzip--SuyashDubey3.replit.app
2
90
LangChain(3)
Trashu Vashisth's avatar
Trashu Vashisth
Delhi, India
Building Production-Grade AI Agents & RAG Systems
14
Followers
Building Production-Grade AI Agents & RAG Systems
Cover image for The Problem: Sales teams waste 60%
The Problem: Sales teams waste 60% of their time researching leads instead of closing them. The Solution: I built a custom Agentic AI Pipeline that automates deep-dive business intelligence and lead scoring. Key Technical Highlights: Multi-Agent Architecture: Built using CrewAI, featuring a 'Business Intelligence Specialist' (for real-time research) and a 'Senior Sales Director' (for strategic scoring). High-Speed Intelligence: Powered by Llama 3.3-70B  for near-instant reasoning and decision-making. Real-time Web Scoping: Integrated Tavily AI to fetch live revenue data, employee counts, and market positioning. Enterprise Storage: A robust SQLite backend to manage lead pipelines with a sleek Streamlit dashboard. Smart Throttling: Engineered custom rate-limiting and token-trimming logic to ensure 99.9% uptime even under heavy API constraints. How it works: Simply enter a company name and URL. The AI agents scour the web, analyze the company's "AI potential," calculate a priority score (0-100), and even write a personalized sales pitch—all in under 30 seconds.
0
87
Cover image for Developed a production-grade Retrieval-Augmented Generation
Developed a production-grade Retrieval-Augmented Generation (RAG) system specifically designed to automate the analysis of complex Environmental, Social, and Governance (ESG) reports. This tool bridges the gap between static LLMs and the dynamic, data-heavy requirements of legal and sustainability compliance. [1 (https://www.youtube.com/watch?v=wkYPcMtwlN8)] Key Features & Capabilities Intelligent Document Processing: Automatically handles large, unstructured PDF/Word ESG reports, extracting critical clauses and metrics in seconds. Fact-Grounded Q&A: Uses a RAG architecture to ensure all answers are strictly based on the uploaded documents, virtually eliminating AI hallucinations. Compliance Mapping: Cross-references internal company data with global frameworks like CSRD, GRI, and TCFD to identify gaps or inconsistencies. Audit-Ready Traceability: Every insight generated includes direct citations and excerpts from the source files, providing a clear "paper trail" for legal teams. Automated Drafting: Capability to draft legal summaries, notices, or internal policy updates based on analyzed ESG risks Note: The 'Slaughter and May' branding in the sidebar is for UI/UX demonstration purposes only, showcasing how the tool integrates into a top-tier law firm's environment. #AI #RAG #LegalTech #ESG #Python #LangChain
1
173
Cover image for Developed a full-stack RAG-based E- Commerce
Developed a full-stack RAG-based E- Commerce AI chatbot using React.js and Tailwind CSS that suggests the perfect laptop from a live catalog. Integrated ChromaDB with BGE Embedding models to provide highly accurate, context-aware product recommendations and instant technical support." Key Highlights: Smart Laptop Recommendations: Uses Semantic Search to match user needs (gaming, coding, etc.) with real-time specs. Advanced Tech Stack: Powered by LangChain for orchestration and BGE models for superior data retrieval. Modern UI/UX: Built a responsive, clean interface using React.js and Tailwind CSS. Zero Hallucination: Ensures all suggestions are strictly grounded in the available product inventory.
2
1
254
Cover image for Built a highly scalable Retrieval-Augmented Generation
Built a highly scalable Retrieval-Augmented Generation (RAG) chatbot designed to interact with private datasets/PDFs. Unlike standard LLMs, this system minimizes hallucinations by retrieving real-time context from a local knowledge base before generating responses. Key Features: Semantic Search: Implemented Vector Embeddings to perform high-speed similarity searches across thousands of document chunks. Smart Retrieval: Integrated a retrieval pipeline using LangChain to fetch the most relevant context for user queries. Source Citation: Configured the bot to provide source references from documents, ensuring data transparency and accuracy. Optimized Performance: Used FAISS/Chromadb for efficient vector storage and retrieval.
4
303
LangChain(5)
Wahid Ali's avatar
Wahid Ali
proGhaziabad, India
Full Stack Developer | MVPs, SaaS & Dashboards for Startups
$10k+
Earned
5x
Hired
4.9
Rating
24
Followers
Full Stack Developer | MVPs, SaaS & Dashboards for Startups
Cover image for AI Search Optimization Platform
AI Search Optimization Platform
1
32
Cover image for Flight Booking Platform
Flight Booking Platform
1
30
Cover image for Innovation Intelligence Platform
Innovation Intelligence Platform
1
36
Cover image for Digital Business Card Platform
Digital Business Card Platform
1
32
LangChain(1)
Sparsh Gupta's avatar
Sparsh Gupta
Noida, India
Full-Stack & AI Developer building scalable SaaS products
New to Contra
Full-Stack & AI Developer building scalable SaaS products
Cover image for Grantiv – AI-Powered Grant Discovery Platform
Grantiv – AI-Powered Grant Discovery Platform
0
4
Cover image for Skej — Conversational AI Scheduling Platform
Skej — Conversational AI Scheduling Platform
0
4
Cover image for CaratIQ — Jewelry Retail Cloud Platform
CaratIQ — Jewelry Retail Cloud Platform
0
3
Cover image for ShopHunter — Shopify Sales Spy & Product Research Tool
ShopHunter — Shopify Sales Spy & Product Research Tool
0
2
LangChain(1)
Abhijeet Jha's avatar
Abhijeet Jha
New Delhi, India
AI/ML Engineer | Building LLM, Agentic AI & ML System
AI/ML Engineer | Building LLM, Agentic AI & ML System
Cover image for SuperAgent is a multi-agent orchestration
SuperAgent is a multi-agent orchestration system built to automate complex, multi-step workflows across research, planning, coding, and general problem-solving tasks. The platform uses a hierarchical Hub-and-Spoke architecture powered by LangGraph and Google Gemini. A central Supervisor agent interprets the user’s goal, breaks the task into smaller steps, and routes work to specialized agents based on capability. The system includes a Coder Agent with isolated local code execution, a Generalist Agent for research and ideation, and persistent shared state to maintain context across agent handoffs. A React-based management dashboard provides visibility into agent activity, workflow progress, and approval-required actions. Safety is a core part of the design. SuperAgent applies iteration limits to control runaway execution and requires human approval before sensitive code execution steps proceed. The code-execution workspace is isolated through Docker-based containerization. I designed and developed the agent architecture, orchestration flow, safety model, code-execution environment, persistent context layer, backend services, and management dashboard.
0
36
Cover image for The Great AI ROI Lie Nobody in wants to Say Out Loud
The Great AI ROI Lie Nobody in wants to Say Out Loud
0
1
Cover image for Jarvis CLI is a Python-based
Jarvis CLI is a Python-based voice assistant for Windows that enables hands-free desktop interaction through voice commands and an animated graphical interface. The assistant listens for a wake word, interprets spoken requests, and performs practical actions such as launching local applications, opening websites, searching Google or YouTube, playing media, retrieving the current time, and handling basic system commands. The project uses a modular architecture that separates speech processing, text-to-speech, command routing, desktop actions, and the GUI layer. It includes an animated orb interface that visually represents assistant states such as idle, listening, speaking, and code-generation activity. The voice and conversational pipeline was further explored with Google Gemini integration for transcription and AI-generated responses, while the project also contains local speech-recognition work based on Vosk. I designed and developed the assistant’s voice-command workflow, desktop automation capabilities, modular Python architecture, animated GUI, speech-processing integration, command normalization logic, and Gemini-powered conversational enhancements. The project demonstrates practical work in voice interfaces, AI assistant design, desktop automation, and human-friendly interaction flows.
0
10
Cover image for A modern AI infrastructure tool
A modern AI infrastructure tool that estimates GPU VRAM requirements for LLM inference, fine-tuning, and quantization. It helps ML engineers configure a model workload, understand where memory is consumed, and identify suitable GPU hardware before deployment.
0
47
LangChain(1)
Khushi Mehta's avatar
Khushi Mehta
Delhi, India
Data Scientist & AI Content Specialist | Dashboards • ML App
Data Scientist & AI Content Specialist | Dashboards • ML App
Cover image for BizBot: AI-Powered Business Data Chatbot Development
BizBot: AI-Powered Business Data Chatbot Development
0
4
Cover image for Cyber Crime Analysis using Machine Learning
Cyber Crime Analysis using Machine Learning
0
3
Cover image for Customer and Sales Insights Dashboard
Customer and Sales Insights Dashboard
0
5
Placeholder project card media
View more →
LangChain(1)
Aparna Soneja's avatar
Aparna Soneja
Delhi, India
Full Stack AI & Machine Learning Engineer
$5k+
Earned
1x
Hired
46
Followers
BOLT_EXPERT

Expert

BOLT_MENTOR_EXPERT

Mentor

Full Stack AI & Machine Learning Engineer
Cover image for AI Agent that transforms Trello sprint data into a report
AI Agent that transforms Trello sprint data into a report
0
9
Cover image for AI agent for project planning, estimation & resourcing
AI agent for project planning, estimation & resourcing
0
15
Cover image for It's finally here 🎬✨ Introducing Sniplyx
It's finally here 🎬✨ Introducing Sniplyx AI — your full AI video editor, not just another clipper. Upload your raw footage and let AI do the heavy lifting: ✂️ Auto viral clips 🎞️ AI B-roll 🎵 AI music & SFX 📝 Auto transcription 🌐 100% browser-based, nothing to install Built this because manual video editing was something I had to do myself but never really knew how to do well, and it took forever. So I built a tool that does the heavy lifting for me. Now it's all in one place, starting at just $2 🙌 Try it out here: https://www.sniplyxai.com
0
109
Cover image for Mentors program. Week 5-7
Mentors program. Week 5-7
1
2
29
LangChain(2)