|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
- generated_from_trainer |
|
- dataset_size:16 |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
base_model: BAAI/bge-base-en-v1.5 |
|
widget: |
|
- source_sentence: what is your company's mission ? |
|
sentences: |
|
- 'About the Company |
|
|
|
|
|
The company is a global digital transformation agency helping businesses thrive |
|
in the digital world. Headquartered in Noida, India, with a strong presence in |
|
the USA, UK, Middle East, and India, the company delivers cutting-edge solutions |
|
to drive business growth and customer engagement. |
|
|
|
|
|
Specializing in cloud transformation, AI technologies, and omnichannel experiences, |
|
the company optimizes operations, enhances brand presence, and automates processes. |
|
It serves industries including finance, automotive, e-commerce, retail, healthcare, |
|
technology, and oil and gas. |
|
|
|
|
|
Mission, Vision & Values |
|
|
|
|
|
Vision: To be a partner in enterprise transformation and future-readiness by leveraging |
|
AI, ML, Data Science, and emerging technologies for swift impact. |
|
|
|
|
|
Mission: To decode data, infuse intelligence into products, and develop systems |
|
that redefine experiences and drive growth. |
|
|
|
|
|
Values: |
|
|
|
|
|
Customer-Centric: Prioritizing client needs. |
|
|
|
|
|
People-First: Empowering employees in a supportive environment. |
|
|
|
|
|
Community Spirit: Fostering collaboration for collective progress. |
|
|
|
|
|
Ownership & Teamwork: Ensuring accountability and shared success. |
|
|
|
|
|
Attracting Talent: Building communities that value skill-sharing and innovation.Our |
|
History |
|
|
|
|
|
2017 - Digital Transformation Begins |
|
|
|
The company entered global markets in Europe, Australia, and Africa with an advanced |
|
car accelerator app, marking a significant turning point. It successfully delivered |
|
10+ technology training programs to over 500 individuals in the USA and India. |
|
|
|
|
|
2018 - Strategic Alliances & Expansion |
|
|
|
Building a reputation as a trusted partner, the company formed alliances with |
|
top automotive brands and financial institutions. Expanding globally, it partnered |
|
with digital agencies and system integrators, gaining access to enterprise accounts |
|
while focusing on CMS, Commerce, Microservices, and Custom Dashboards. |
|
|
|
|
|
2019 - Growth & Development |
|
|
|
With a new office in Pune and an upgraded Delhi headquarters, the company expanded |
|
its reach, growing its team to over 50 professionals. This strategic growth attracted |
|
more SME and enterprise clients, reinforcing its position as a tech innovator. |
|
|
|
|
|
2020 - Resilience & Innovation |
|
|
|
Despite the pandemic’s challenges, the company retained its workforce, explored |
|
new product ideas, and sought grants. This period strengthened resilience and |
|
adaptability, driving continued digital transformation efforts. |
|
|
|
|
|
2021 - Automation & Training |
|
|
|
Navigating rapid growth and a talent shortage, the company expanded its workforce |
|
and embraced remote work. It launched comprehensive training programs to manage |
|
operational demands efficiently. |
|
|
|
|
|
2022 - Innovation & Employee Development |
|
|
|
Amid the ‘Great Resignation,’ the company implemented strategic retention strategies |
|
and workforce assessments. A rise in revenue growth and employee engagement further |
|
solidified its competitive edge in the tech industry. |
|
|
|
|
|
2023 - Strategic Adaptation |
|
|
|
Rebranding as TechChefz Digital, the company adapted to recession and geopolitical |
|
turmoil by focusing on consulting, platform selection, and client roadmaps. This |
|
shift strengthened its role in digital transformation. |
|
|
|
|
|
2024 - Expansion & Collaboration |
|
|
|
Celebrating a milestone with its new Noida office, the company expanded its expertise |
|
in Data Science, AI/ML, and LLMs. Expanding into the US, UK, EU, and the Middle |
|
East, it leverages GenAI and RPA to enhance efficiency and refine its market strategy. |
|
|
|
|
|
' |
|
- "Mayank Maggon – Founder, CEO & CTO\nMayank Maggon is the visionary leader of\ |
|
\ TechChefz Digital, responsible for driving the company's strategic direction.\ |
|
\ With over 15 years of experience in entrepreneurship and technology, Mayank\ |
|
\ has a deep understanding of AI, cloud technologies, and digital transformation.\ |
|
\ His leadership is centered on building a culture of innovation, operational\ |
|
\ excellence, and customer-first solutions.\nMayank holds a postgraduate certificate\ |
|
\ in Technology Leadership & Innovation from MIT and a postgraduate diploma in\ |
|
\ Sales & Marketing Communication from MICA, making him uniquely equipped to lead\ |
|
\ the company's growth in an ever-evolving digital ecosystem.\nLink: https://www.linkedin.com/in/mayankmaggon/\ |
|
\ \nOther Leadership Members:\nRahul Aggarwal – Senior Director, Technology: Rahul\ |
|
\ brings a wealth of technical expertise, overseeing the delivery of high-impact\ |
|
\ digital solutions.\nLink: https://www.linkedin.com/in/rahul-aggarwal-84288a59/\ |
|
\ \nAkshit Maggon – Associate Director, Delivery: Akshit is responsible for ensuring\ |
|
\ that projects are delivered on time, within scope, and meet the highest quality\ |
|
\ standards.\nLink: https://www.linkedin.com/in/akshit-maggon/ \nKunal Bhardwaj\ |
|
\ – Director, Technology: Kunal drives the company’s technical innovation and\ |
|
\ ensures that our solutions leverage the latest in AI, cloud, and digital technologies.\n\ |
|
Link: https://www.linkedin.com/in/kunal-bhardwaj-in/ \n" |
|
- 'Web & Mobile Development |
|
|
|
Frontend Development: |
|
|
|
HTML5: Markup language for structuring web content. |
|
|
|
CSS/JS: Styling and interactivity for dynamic user experiences. |
|
|
|
React JS: JavaScript library for building user interfaces with a component-based |
|
approach. |
|
|
|
Angular JS: JavaScript framework for developing dynamic, single-page applications |
|
(SPAs). |
|
|
|
Vue JS: Progressive JavaScript framework for building user interfaces and SPAs. |
|
|
|
Next JS: React-based framework for server-side rendering and static website generation. |
|
|
|
Mobile Development: |
|
|
|
React Native: Framework for building native mobile applications using React. |
|
|
|
Flutter: UI toolkit for building natively compiled applications for mobile, web, |
|
and desktop from a single codebase. |
|
|
|
Backend Development: |
|
|
|
Node JS: JavaScript runtime for building scalable backend services. |
|
|
|
Python: High-level programming language used for backend services, machine learning, |
|
and data science. |
|
|
|
Frappe: Full-stack web application framework based on Python and JavaScript. |
|
|
|
Java: Widely used programming language for enterprise-grade backend solutions. |
|
|
|
Spring Boot: Java-based framework for building production-grade applications. |
|
|
|
Go Lang: Language designed for simplicity and performance, ideal for scalable |
|
applications. |
|
|
|
Databases: |
|
|
|
MongoDB: NoSQL database known for its scalability and flexibility. |
|
|
|
PostgreSQL: Open-source relational database system. |
|
|
|
MySQL: Popular relational database management system (RDBMS). |
|
|
|
|
|
2. Content Management Systems (CMS) |
|
|
|
Adobe Experience Manager (AEM): Leading enterprise CMS platform for building personalized, |
|
scalable digital experiences. |
|
|
|
Acquia / Drupal: Flexible CMS solution for creating customized websites and applications. |
|
|
|
Strapi: Open-source headless CMS to build APIs in JavaScript. |
|
|
|
WordPress: Popular open-source CMS for creating and managing websites. |
|
|
|
|
|
3. 3D, AR & VR |
|
|
|
Maya: Leading 3D animation software for creating realistic 3D models and animations. |
|
|
|
Unity: Cross-platform game engine used for developing immersive AR/VR experiences. |
|
|
|
Three JS: JavaScript library for creating 3D content on the web. |
|
|
|
WebGL: API for rendering interactive 3D and 2D graphics in a browser without plugins. |
|
|
|
React 360: Framework for creating virtual reality (VR) content using React. |
|
|
|
AR.js: Open-source library for building Augmented Reality (AR) applications on |
|
the web. |
|
|
|
|
|
4. Learning Management System (LMS) |
|
|
|
Canvas: Modern, open-source learning management system used for creating and managing |
|
educational content. |
|
|
|
Adobe Learning Manager: Scalable and customizable platform for delivering learning |
|
content and experiences. |
|
|
|
|
|
5. E-Commerce Solutions |
|
|
|
Adobe Commerce Cloud: Enterprise e-commerce platform with powerful features for |
|
building digital storefronts and managing customer experiences. |
|
|
|
Magento: Open-source e-commerce platform for building custom e-commerce websites. |
|
|
|
Shopify: Leading cloud-based e-commerce platform for building online stores. |
|
|
|
Salesforce Commerce Cloud (SFCC): Cloud-based e-commerce solution for delivering |
|
personalized shopping experiences. |
|
|
|
|
|
6. Analytics |
|
|
|
Google Analytics - GA4: Web analytics service for tracking website traffic and |
|
user behavior. |
|
|
|
Adobe Analytics: Advanced analytics solution for real-time data collection and |
|
reporting. |
|
|
|
Microsoft Clarity: Free, easy-to-use analytics tool that provides insights into |
|
user behavior. |
|
|
|
Hotjar: Behavioral analytics tool to track user activity, heatmaps, and feedback. |
|
|
|
|
|
7. Personalization & Marketing Cloud |
|
|
|
Adobe Target: Personalized content and experiences using AI and machine learning |
|
to enhance customer engagement. |
|
|
|
Adobe Marketo Engage: Marketing automation platform to streamline customer engagement |
|
and lead management. |
|
|
|
Adobe Campaign Manager: Marketing campaign management tool for creating, automating, |
|
and analyzing cross-channel marketing campaigns. |
|
|
|
Salesforce Marketing Cloud (SFMC): Cloud-based platform for managing and optimizing |
|
customer journeys and marketing campaigns. |
|
|
|
Webengage: Marketing automation platform for personalizing messages and increasing |
|
engagement. |
|
|
|
Moengage: Customer engagement platform offering push notifications, in-app messaging, |
|
and email marketing. |
|
|
|
Clevertap: Platform for customer retention and engagement through personalized |
|
messaging and automation. |
|
|
|
|
|
8. Cloud & DevSecOps |
|
|
|
Cloud Platforms: |
|
|
|
AWS: Cloud computing services from Amazon for infrastructure, applications, and |
|
scalability. |
|
|
|
MS-Azure: Cloud platform from Microsoft offering a range of cloud services. |
|
|
|
Google Cloud: Cloud computing services from Google for scalable infrastructure |
|
and machine learning. |
|
|
|
Infrastructure as Code & Automation: |
|
|
|
Terraform: Open-source infrastructure as code tool for provisioning and managing |
|
cloud infrastructure. |
|
|
|
Kubernetes: Open-source system for automating containerized applications'' deployment |
|
and scaling. |
|
|
|
Docker: Platform for developing, shipping, and running applications in containers. |
|
|
|
Monitoring & Security: |
|
|
|
ELK Stack (Elasticsearch, Logstash, Kibana): Set of tools for logging, data analysis, |
|
and visualizing logs. |
|
|
|
Grafana: Open-source platform for monitoring and analyzing time-series data. |
|
|
|
New Relic: Application performance management tool for monitoring and optimizing |
|
applications. |
|
|
|
Prometheus: Open-source monitoring system and time-series database. |
|
|
|
Jenkins: Open-source automation server for continuous integration and continuous |
|
delivery (CI/CD). |
|
|
|
Apache Kafka: Distributed event streaming platform for real-time data processing. |
|
|
|
Elastic Search: Search and analytics engine for exploring large datasets. |
|
|
|
Redis: In-memory data structure store used for caching and real-time analytics. |
|
|
|
Web Servers & Proxy Servers: |
|
|
|
NGINX: Web server and reverse proxy server for high-performance web applications. |
|
|
|
Apache HTTP Server: Popular open-source web server software. |
|
|
|
Security & Performance Monitoring: |
|
|
|
Splunk: Platform for searching, monitoring, and analyzing machine data. |
|
|
|
Datadog: Cloud-based platform for monitoring applications and infrastructure. |
|
|
|
Beats: Lightweight data shippers for sending log data to centralized systems like |
|
ELK. |
|
|
|
Git: Version control system for managing source code |
|
|
|
' |
|
- source_sentence: What e-commerce platforms do you develop on? |
|
sentences: |
|
- 'Business Process Automation: LLM Powered Agents |
|
|
|
Overview: |
|
|
|
Our AI-powered agents are designed to automate complex, time-consuming business |
|
processes. By leveraging the latest technologies such as Langchain and MongoDB, |
|
these agents can handle a variety of tasks, including data collection and web |
|
navigation, all tailored to your specific business needs. |
|
|
|
How it works: |
|
|
|
AI Agents can be customized to automate business workflows. |
|
|
|
Use of Langchain ensures advanced capabilities for handling and processing web |
|
content and data. |
|
|
|
Integration with MongoDB enables efficient data storage and management. |
|
|
|
Impact: |
|
|
|
Significant time savings by automating repetitive tasks. |
|
|
|
Enhanced productivity, allowing employees to focus on higher-value work. |
|
|
|
Increased accuracy and reduction of human errors in critical processes. |
|
|
|
|
|
Customer Service: Sentiment Classification Using BERT |
|
|
|
Overview: |
|
|
|
This accelerator leverages Advanced AI and Hugging Face transformers to categorize |
|
customer reviews into positive, negative, or neutral sentiments. It helps businesses |
|
gain actionable insights into customer feedback by analyzing reviews, enabling |
|
companies to respond proactively to customer concerns and improve their offerings. |
|
|
|
How it works: |
|
|
|
BERT (Bidirectional Encoder Representations from Transformers) is fine-tuned to |
|
understand sentiment in customer feedback. |
|
|
|
The tool processes customer reviews, assigning sentiment categories that can help |
|
prioritize responses or improvements. |
|
|
|
The solution helps automate feedback analysis, improving the speed and accuracy |
|
of customer service interactions. |
|
|
|
Impact: |
|
|
|
Actionable insights for customer service teams to improve engagement and responses. |
|
|
|
Proactive improvements based on real-time feedback analysis. |
|
|
|
Enhanced customer experience by responding quickly and appropriately to customer |
|
sentiments. |
|
|
|
|
|
Artificial Intelligence: Fine-Tuning Large Language Models |
|
|
|
Overview: |
|
|
|
Large Language Models (LLMs), such as Mistral 7B, are at the forefront of AI innovation. |
|
In this accelerator, TechChefz Digital showcases its technical prowess by fine-tuning |
|
the Mistral 7B model on the VIGO dataset, which is an open-source dataset for |
|
training large-scale language models. |
|
|
|
How it works: |
|
|
|
We fine-tune Mistral 7B to improve its accuracy and relevancy based on specific |
|
datasets like VIGO. |
|
|
|
This allows the AI to be more context-aware and aligned with your particular business |
|
needs. |
|
|
|
Impact: |
|
|
|
Enhanced AI accuracy, enabling more effective AI-driven applications. |
|
|
|
Open-source innovation that leads to cost-effective AI solutions. |
|
|
|
Potential to integrate fine-tuned models into a range of industries like customer |
|
service, marketing, and automation. |
|
|
|
|
|
E-Commerce: Image Similarity Search |
|
|
|
Overview: |
|
|
|
In the e-commerce world, product discovery can be a challenge. Our AI-powered |
|
Image Similarity Search Accelerator revolutionizes product search by allowing |
|
customers to upload an image and instantly find matching or similar items. This |
|
tool enhances the shopping experience and drives higher engagement by enabling |
|
users to find products more efficiently. |
|
|
|
How it works: |
|
|
|
Customers upload an image of the product they are looking for. |
|
|
|
The AI model uses image recognition to search for visually similar products from |
|
the e-commerce site’s catalog. |
|
|
|
Product recommendations are delivered instantly based on visual matches. |
|
|
|
Impact: |
|
|
|
Improved user experience, reducing time spent searching for products. |
|
|
|
Higher conversion rates as customers can quickly find what they are looking for. |
|
|
|
Differentiation from competitors with advanced AI-powered product discovery features. |
|
|
|
|
|
Customer Service: RAG Chatbots |
|
|
|
Overview: |
|
|
|
RAG (Retrieval-Augmented Generation) chatbots are designed to provide timely and |
|
relevant responses to customer queries. By combining retrieval-based models with |
|
generative capabilities, these chatbots offer precise and contextually accurate |
|
answers. Our RAG-powered chatbots provide a more intelligent and tailored experience, |
|
making customer interactions smoother and more efficient. |
|
|
|
How it works: |
|
|
|
The chatbot first retrieves relevant data from a knowledge base or external sources. |
|
|
|
It then generates responses based on this data, ensuring that each answer is aligned |
|
with the user’s query. |
|
|
|
RAG technology ensures that chatbots provide relevant and up-to-date information. |
|
|
|
Impact: |
|
|
|
Enhanced customer satisfaction with more precise and relevant answers. |
|
|
|
24/7 support capabilities, improving overall customer service availability. |
|
|
|
Increased operational efficiency by automating customer interactions at scale. |
|
|
|
|
|
Request a Demo and Browse Accelerators: |
|
|
|
In our company, we offer you the opportunity to experience the power and potential |
|
of these accelerators first-hand. Whether you''re looking to streamline business |
|
processes, enhance customer service, or accelerate your e-commerce strategies, |
|
our solution accelerators are built to drive fast, impactful results. |
|
|
|
Get started today by requesting a demo or browsing through our accelerator offerings |
|
to discover the right tools that will transform your tech projects and accelerate |
|
your success. |
|
|
|
' |
|
- "Global Presence \nTechChefz Digital has established a global footprint with operations\ |
|
\ in the following regions:\nIndia: Noida, New Delhi, Pune\nUnited States: Delaware\n\ |
|
United Kingdom & Europe\nMiddle East: Dubai\nCompany Location \nLocation: HQ India\ |
|
\ Noida\n 4th Floor, Insignia Tower, Subarea, Sector 126, Noida, Uttar Pradesh\ |
|
\ - 201313 +91 7428835009 India New Delhi \nN-161,\ |
|
\ Saira Tower, G.F, Gautam Nagar Near Green Park Metro Station Gate No. 2 Delhi\ |
|
\ - 110049 \nUnited States Delaware Delaware, USA (989) 474-4346\nOur team of\ |
|
\ over 250+ dedicated professionals works together to innovate, strategize, and\ |
|
\ implement transformative digital solutions for businesses across the world.\ |
|
\ Email: [email protected] / [email protected] or fill out our contact\ |
|
\ form -https://www.techchefz.digital/contact-us \nPhone no: +91 7428835009\n\ |
|
Social Media:\nLinkedin: www.linkedin.com/company/techchefzdigital/ \nInstagram:\ |
|
\ https://www.instagram.com/techchefz_digital/\nFacebook: https://www.facebook.com/profile.php?id=61562947256189\n\ |
|
Twitter: https://x.com/tcz_digital\nYoutube: https://youtube.com/@techchefzdigital?feature=shared\n\ |
|
Clutch.co: https://clutch.co/profile/tcz-digital-private \nMedium.com: https://medium.com/@TechchefzDigital\n\ |
|
Glassdoor: https://www.glassdoor.co.in/Reviews/TechChefz-Digital-Reviews-E3262688.htm\ |
|
\ \nGoodifrms: https://www.goodfirms.co/company/techchefz-digital \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ We provide\ |
|
\ a free consultation to understand your business needs and suggest solutions.\n\ |
|
We welcome collaborations, white-label partnerships, and outsourcing opportunities.\ |
|
\ Contact us to discuss potential synergies.We provide continuous monitoring,\ |
|
\ security updates, and optimization services for long-term business success.\n\ |
|
We build custom e-commerce solutions, including Shopify, Magento, WooCommerce,\ |
|
\ and headless commerce platforms with AI-driven recommendations.\nWe provide\ |
|
\ website revamps focused on performance, UI/UX, SEO optimization, and modern\ |
|
\ frameworks like React, Next.js, and Angular.\nSales process- \nOur sales process\ |
|
\ follows these five simple steps:\n1️⃣ Discovery Call – Understanding your business\ |
|
\ needs\n2️⃣ Proposal & Scope Definition – Defining objectives & deliverables\n\ |
|
3️⃣ Agreement & Onboarding – Finalizing contract & project plan\n4️⃣ Development\ |
|
\ & Execution – Delivering high-quality solutions\n5️⃣ Ongoing Support & Scaling\ |
|
\ – Continuous improvements & updates\n\[email protected] / [email protected]\ |
|
\ or fill out our contact form -https://www.techchefz.digital/contact-us \n\n\ |
|
Pricing structure: Contact us link: https://www.techchefz.digital/contact-us \n\ |
|
\ \n\n" |
|
- 'Web & Mobile Development |
|
|
|
Frontend Development: |
|
|
|
HTML5: Markup language for structuring web content. |
|
|
|
CSS/JS: Styling and interactivity for dynamic user experiences. |
|
|
|
React JS: JavaScript library for building user interfaces with a component-based |
|
approach. |
|
|
|
Angular JS: JavaScript framework for developing dynamic, single-page applications |
|
(SPAs). |
|
|
|
Vue JS: Progressive JavaScript framework for building user interfaces and SPAs. |
|
|
|
Next JS: React-based framework for server-side rendering and static website generation. |
|
|
|
Mobile Development: |
|
|
|
React Native: Framework for building native mobile applications using React. |
|
|
|
Flutter: UI toolkit for building natively compiled applications for mobile, web, |
|
and desktop from a single codebase. |
|
|
|
Backend Development: |
|
|
|
Node JS: JavaScript runtime for building scalable backend services. |
|
|
|
Python: High-level programming language used for backend services, machine learning, |
|
and data science. |
|
|
|
Frappe: Full-stack web application framework based on Python and JavaScript. |
|
|
|
Java: Widely used programming language for enterprise-grade backend solutions. |
|
|
|
Spring Boot: Java-based framework for building production-grade applications. |
|
|
|
Go Lang: Language designed for simplicity and performance, ideal for scalable |
|
applications. |
|
|
|
Databases: |
|
|
|
MongoDB: NoSQL database known for its scalability and flexibility. |
|
|
|
PostgreSQL: Open-source relational database system. |
|
|
|
MySQL: Popular relational database management system (RDBMS). |
|
|
|
|
|
2. Content Management Systems (CMS) |
|
|
|
Adobe Experience Manager (AEM): Leading enterprise CMS platform for building personalized, |
|
scalable digital experiences. |
|
|
|
Acquia / Drupal: Flexible CMS solution for creating customized websites and applications. |
|
|
|
Strapi: Open-source headless CMS to build APIs in JavaScript. |
|
|
|
WordPress: Popular open-source CMS for creating and managing websites. |
|
|
|
|
|
3. 3D, AR & VR |
|
|
|
Maya: Leading 3D animation software for creating realistic 3D models and animations. |
|
|
|
Unity: Cross-platform game engine used for developing immersive AR/VR experiences. |
|
|
|
Three JS: JavaScript library for creating 3D content on the web. |
|
|
|
WebGL: API for rendering interactive 3D and 2D graphics in a browser without plugins. |
|
|
|
React 360: Framework for creating virtual reality (VR) content using React. |
|
|
|
AR.js: Open-source library for building Augmented Reality (AR) applications on |
|
the web. |
|
|
|
|
|
4. Learning Management System (LMS) |
|
|
|
Canvas: Modern, open-source learning management system used for creating and managing |
|
educational content. |
|
|
|
Adobe Learning Manager: Scalable and customizable platform for delivering learning |
|
content and experiences. |
|
|
|
|
|
5. E-Commerce Solutions |
|
|
|
Adobe Commerce Cloud: Enterprise e-commerce platform with powerful features for |
|
building digital storefronts and managing customer experiences. |
|
|
|
Magento: Open-source e-commerce platform for building custom e-commerce websites. |
|
|
|
Shopify: Leading cloud-based e-commerce platform for building online stores. |
|
|
|
Salesforce Commerce Cloud (SFCC): Cloud-based e-commerce solution for delivering |
|
personalized shopping experiences. |
|
|
|
|
|
6. Analytics |
|
|
|
Google Analytics - GA4: Web analytics service for tracking website traffic and |
|
user behavior. |
|
|
|
Adobe Analytics: Advanced analytics solution for real-time data collection and |
|
reporting. |
|
|
|
Microsoft Clarity: Free, easy-to-use analytics tool that provides insights into |
|
user behavior. |
|
|
|
Hotjar: Behavioral analytics tool to track user activity, heatmaps, and feedback. |
|
|
|
|
|
7. Personalization & Marketing Cloud |
|
|
|
Adobe Target: Personalized content and experiences using AI and machine learning |
|
to enhance customer engagement. |
|
|
|
Adobe Marketo Engage: Marketing automation platform to streamline customer engagement |
|
and lead management. |
|
|
|
Adobe Campaign Manager: Marketing campaign management tool for creating, automating, |
|
and analyzing cross-channel marketing campaigns. |
|
|
|
Salesforce Marketing Cloud (SFMC): Cloud-based platform for managing and optimizing |
|
customer journeys and marketing campaigns. |
|
|
|
Webengage: Marketing automation platform for personalizing messages and increasing |
|
engagement. |
|
|
|
Moengage: Customer engagement platform offering push notifications, in-app messaging, |
|
and email marketing. |
|
|
|
Clevertap: Platform for customer retention and engagement through personalized |
|
messaging and automation. |
|
|
|
|
|
8. Cloud & DevSecOps |
|
|
|
Cloud Platforms: |
|
|
|
AWS: Cloud computing services from Amazon for infrastructure, applications, and |
|
scalability. |
|
|
|
MS-Azure: Cloud platform from Microsoft offering a range of cloud services. |
|
|
|
Google Cloud: Cloud computing services from Google for scalable infrastructure |
|
and machine learning. |
|
|
|
Infrastructure as Code & Automation: |
|
|
|
Terraform: Open-source infrastructure as code tool for provisioning and managing |
|
cloud infrastructure. |
|
|
|
Kubernetes: Open-source system for automating containerized applications'' deployment |
|
and scaling. |
|
|
|
Docker: Platform for developing, shipping, and running applications in containers. |
|
|
|
Monitoring & Security: |
|
|
|
ELK Stack (Elasticsearch, Logstash, Kibana): Set of tools for logging, data analysis, |
|
and visualizing logs. |
|
|
|
Grafana: Open-source platform for monitoring and analyzing time-series data. |
|
|
|
New Relic: Application performance management tool for monitoring and optimizing |
|
applications. |
|
|
|
Prometheus: Open-source monitoring system and time-series database. |
|
|
|
Jenkins: Open-source automation server for continuous integration and continuous |
|
delivery (CI/CD). |
|
|
|
Apache Kafka: Distributed event streaming platform for real-time data processing. |
|
|
|
Elastic Search: Search and analytics engine for exploring large datasets. |
|
|
|
Redis: In-memory data structure store used for caching and real-time analytics. |
|
|
|
Web Servers & Proxy Servers: |
|
|
|
NGINX: Web server and reverse proxy server for high-performance web applications. |
|
|
|
Apache HTTP Server: Popular open-source web server software. |
|
|
|
Security & Performance Monitoring: |
|
|
|
Splunk: Platform for searching, monitoring, and analyzing machine data. |
|
|
|
Datadog: Cloud-based platform for monitoring applications and infrastructure. |
|
|
|
Beats: Lightweight data shippers for sending log data to centralized systems like |
|
ELK. |
|
|
|
Git: Version control system for managing source code |
|
|
|
' |
|
- source_sentence: Do you have anything for education firms or universities? |
|
sentences: |
|
- "Global Universities: Multi-Brand, Multi-Locale, and Multilingual Digital Platform\n\ |
|
Industry: Higher Education\nPlatform: Web, Responsive\nTechnologies Used: AEM\ |
|
\ (Adobe Experience Manager), React JS\nServices Provided: Web Design, Content\ |
|
\ Management System (CMS)\nOverview:\nTechChefz Digital developed a robust, scalable,\ |
|
\ and efficient digital platform for Graphic Era University that caters to multiple\ |
|
\ campuses, languages, and regions. The project involved creating a multi-brand,\ |
|
\ multi-locale, and multilingual digital platform that ensured brand consistency\ |
|
\ and user satisfaction across all campuses.\nGoals & Objectives:\nMaximize Brand\ |
|
\ Consistency: Build a platform that maintains consistent branding across all\ |
|
\ locations and provides seamless navigation for users.\nImplement a Robust CMS:\ |
|
\ Leverage AEM as the Content Management System (CMS) to create reusable templates\ |
|
\ and components, enabling scalable content management for each campus.\nContent\ |
|
\ Automation: Introduce automation through React-based Global Variables dashboards\ |
|
\ to streamline content management, ensuring up-to-date and accurate information.\n\ |
|
System Integration: Integrate with Admission Automation, CRM, and ERP systems\ |
|
\ for smooth data flow and to enhance user experiences, boosting conversion rates.\n\ |
|
Challenges:\nEnsuring consistent branding across multiple campuses and locations.\n\ |
|
Creating a structured, easy-to-navigate website that works well for various types\ |
|
\ of users.\nManaging website content across multiple locations and ensuring localization\ |
|
\ without compromising the user experience.\nEnsuring accessibility compliance\ |
|
\ with ADA (Americans with Disabilities Act).\nSolutions:\nBuilt a digital platform\ |
|
\ on AEM with reusable components and templates.\nIntroduced Content Ops Automation\ |
|
\ using React-based dashboards to simplify content management.\nIntegrated with\ |
|
\ key systems (Admission, CRM, ERP) for a unified user experience.\nBusiness Impact:\n\ |
|
Customization of content and marketing strategies based on locales, languages,\ |
|
\ and markets.\nIncreased website traffic and user engagement by 2x.\nReduced\ |
|
\ website maintenance costs by 80% and optimized hosting.\n\nHousing Finance &\ |
|
\ Banking Firm: Revolutionizing Digital Experiences\nIndustry: Banking & Finance\n\ |
|
Platform: Web, Responsive\nServices Provided: Web Design, Content Management,\ |
|
\ Retail CMS\nOverview:\nTechChefz Digital worked with a leading Indian Mortgage\ |
|
\ Finance and Realty firm to create a seamless digital ecosystem for customer,\ |
|
\ partner, and internal stakeholder touchpoints. The focus was on making home\ |
|
\ loans paperless, enhancing customer engagement, and introducing AI-based recommendations\ |
|
\ to optimize user interactions.\nGoals & Objectives:\nBecome the top housing\ |
|
\ finance company in India by offering seamless online services.\nDigitize Home\ |
|
\ Loans and paperless processes for enhanced customer convenience.\nIntroduce\ |
|
\ AI to deliver personalized market data analysis and recommendations.\nImplement\ |
|
\ an omnichannel experience to provide a seamless journey for users across all\ |
|
\ touchpoints.\nChallenges:\nThe company lacked a digital presence and had only\ |
|
\ a static website.\nNeeded to build a digital ecosystem that integrates with\ |
|
\ existing banking systems.\nRequired a solution to enhance customer engagement\ |
|
\ without requiring physical branch visits.\nSolutions:\nDeveloped multi-regional\ |
|
\ corporate websites with language localization and analytics for enhanced user\ |
|
\ personalization.\nIntroduced AI-driven recommendations and paperless loan applications\ |
|
\ to streamline processes.\nBuilt internal portals and dashboards for efficient\ |
|
\ management of data and customer interactions.\nBusiness Impact:\nUnified technology\ |
|
\ and improved collaboration across teams (Sales, Marketing, and Branches).\n\ |
|
Enhanced customer retention by 4x.\nStreamlined data governance and compliance,\ |
|
\ ensuring 100% adherence to regulations.\n\nGlobal Automotive Brand: Transforming\ |
|
\ the Digital Ecosystem\nIndustry: Automotive/Manufacturing\nPlatform: Web, Responsive\n\ |
|
Technologies Used: AEM, Magento Commerce, React JS, Node JS, Python, MS-Azure,\ |
|
\ Kubernetes, Docker\nServices Provided: Web Design, Content Management, E-commerce\ |
|
\ Solutions, Microservices\nOverview:\nTechChefz Digital helped a global automotive\ |
|
\ brand develop a comprehensive digital ecosystem that spans multiple countries\ |
|
\ and business units. The platform provides services like motorcycle sales (new\ |
|
\ and pre-owned), accessories, apparel, service & repair, events, tours, and rentals.\n\ |
|
Goals & Objectives:\nEnhance Omni-Channel Growth and customer experience by unifying\ |
|
\ online and offline data for seamless interactions.\nImplement personalized content\ |
|
\ strategies and user-centric design to improve conversion rates and user engagement.\n\ |
|
Streamline technology across markets and ensure consistent brand messaging.\n\ |
|
Challenges:\nDecentralized digital interfaces prevented unified brand growth.\n\ |
|
Disconnected data between offline dealers and the online platform.\nDealers were\ |
|
\ isolated from the brand’s marketing strategy, leading to missed opportunities.\n\ |
|
Solutions:\nCreated a multi-locale, multilingual platform that integrates Dealer\ |
|
\ Management Systems (DMS), CRM, and other business applications.\nImplemented\ |
|
\ a scalable Adobe Experience Manager (AEM) platform with Magento Commerce for\ |
|
\ e-commerce.\nIntegrated online and offline data, including dealer and customer\ |
|
\ interactions, to drive personalized experiences.\nBusiness Impact:\nIncreased\ |
|
\ customer retention by 1.7x.\nEnhanced brand awareness by 192%.\nSupported operations\ |
|
\ in 35+ countries, enabling a consistent omnichannel experience across dealers,\ |
|
\ service centers, and distributors.\nWe cater to various industries, including\ |
|
\ finance, automotive, e-commerce, retail, healthcare, technology, Oil and gas\ |
|
\ industry, etc. \n" |
|
- 'Strategy & Digital Transformation |
|
|
|
Digital Transformation Roadmap: Modernizing tech stacks, guiding businesses through |
|
their digital journey. |
|
|
|
Product Strategy: Crafting effective product strategies aligned with business |
|
goals. |
|
|
|
Customer Experience (CX) Optimization: Enhancing customer engagement with personalized |
|
experiences. |
|
|
|
Data Analytics: Leveraging data for business insights and better decision-making. |
|
|
|
Cloud Transformation: Transitioning to scalable and cost-efficient cloud solutions. |
|
|
|
|
|
Product Engineering & Custom Development |
|
|
|
Enterprise Web & Mobile Development: Tailored web and mobile apps for enterprises. |
|
|
|
Microservices & API Integration: Building scalable systems with microservices |
|
architecture and seamless API integrations. |
|
|
|
Quality Engineering: Ensuring optimal product performance through automated testing |
|
and quality assurance. |
|
|
|
Custom Software Development: Designing custom software solutions to meet unique |
|
business needs. |
|
|
|
|
|
Customer Experience & Marketing Technology |
|
|
|
Journey Mapping & Analytics: Understanding customer journeys to create targeted |
|
experiences. |
|
|
|
Content Architecture: Structuring content efficiently across multiple platforms. |
|
|
|
Personalization: Dynamic content and personalized engagement based on user behavior. |
|
|
|
Campaign Management: AI-driven automation for smarter, more effective campaigns. |
|
|
|
Conversion Rate Optimization (CRO): A/B testing, analytics, and optimization techniques |
|
to improve conversion rates. |
|
|
|
|
|
Enterprise Platforms & Systems Integration |
|
|
|
CMS Platform Selection & Integration: Implementing best-fit CMS solutions (including |
|
AEM). |
|
|
|
E-commerce Platforms: Implementing and optimizing e-commerce platforms like Magento, |
|
Shopify, and WooCommerce. |
|
|
|
Learning Management Systems (LMS): Integrating learning platforms that align with |
|
business goals. |
|
|
|
CRM & ERP System Integration: Seamless integration between enterprise systems |
|
like CRM (Salesforce, HubSpot) and ERP. |
|
|
|
Analytics, Data Science & Business Intelligence |
|
|
|
Predictive Analytics: Utilizing machine learning and predictive models to forecast |
|
trends and customer behavior. |
|
|
|
Business Intelligence (BI): Dashboards and tools to provide real-time business |
|
insights. |
|
|
|
Recommendation Engines: AI-based engines for product recommendations and content |
|
personalization. |
|
|
|
Intelligent Search & NLP: Enhancing search experiences using Natural Language |
|
Processing and machine learning algorithms. |
|
|
|
|
|
AI & Automation Solutions |
|
|
|
Generative AI: Creating content such as images, text, and videos using AI-driven |
|
models. |
|
|
|
AI-Powered Chatbots & Voice Assistants: Enhancing customer support and engagement |
|
through AI-driven conversational agents. |
|
|
|
Robotic Process Automation (RPA): Automating repetitive tasks and improving workflow |
|
efficiency. |
|
|
|
AI for Fraud Detection: Using AI to detect and prevent fraudulent activities within |
|
systems and transactions. |
|
|
|
|
|
Adobe Experience Manager (AEM) Solutions |
|
|
|
AEM Implementation & Customization: Full-service implementation, including setup, |
|
configuration, and custom development. |
|
|
|
Content Management: Streamlining content creation and management through AEM’s |
|
user-friendly interface. |
|
|
|
AEM Personalization: Delivering personalized digital experiences using AEM’s targeting |
|
and audience segmentation features. |
|
|
|
Multi-Site Management: Managing and scaling multiple websites and regions with |
|
AEM’s multi-site capabilities. |
|
|
|
AEM Integration: Integrating AEM with third-party platforms such as CRM, ERP, |
|
and e-commerce systems. |
|
|
|
AEM Migration: Helping businesses migrate from legacy CMS platforms to AEM seamlessly. |
|
|
|
AEM Support & Maintenance: Providing ongoing support and optimization for AEM |
|
environments. |
|
|
|
|
|
Cloud Services |
|
|
|
Cloud Strategy & Consulting: Helping businesses define and execute cloud adoption |
|
strategies. |
|
|
|
Cloud Migration: Smooth migration of business operations and applications to the |
|
cloud (AWS, Azure, GCP). |
|
|
|
Cloud Infrastructure Management: Managing and optimizing cloud infrastructure |
|
for efficiency and scalability. |
|
|
|
Cloud Security: Implementing security measures to protect cloud-hosted data and |
|
applications. |
|
|
|
|
|
E-Commerce Solutions |
|
|
|
Marketplace Development: Building scalable, multi-vendor marketplace platforms |
|
using technologies like Magento, Shopify Plus, and WooCommerce. |
|
|
|
Omnichannel Commerce: Integrating e-commerce platforms with physical and digital |
|
sales channels for seamless shopping experiences. |
|
|
|
AI-Powered Commerce: Leveraging AI for product recommendations, inventory management, |
|
and customer insights. |
|
|
|
|
|
UX/UI Design & User-Centered Development |
|
|
|
UI/UX Design: Creating intuitive, engaging interfaces that improve user experience |
|
across websites and apps. |
|
|
|
User Research & Testing: Understanding user behavior through research and testing |
|
to create optimal digital solutions. |
|
|
|
Prototyping & Wireframing: Designing interactive prototypes and wireframes to |
|
visualize digital products. |
|
|
|
' |
|
- "Global Presence \nTechChefz Digital has established a global footprint with operations\ |
|
\ in the following regions:\nIndia: Noida, New Delhi, Pune\nUnited States: Delaware\n\ |
|
United Kingdom & Europe\nMiddle East: Dubai\nCompany Location \nLocation: HQ India\ |
|
\ Noida\n 4th Floor, Insignia Tower, Subarea, Sector 126, Noida, Uttar Pradesh\ |
|
\ - 201313 +91 7428835009 India New Delhi \nN-161,\ |
|
\ Saira Tower, G.F, Gautam Nagar Near Green Park Metro Station Gate No. 2 Delhi\ |
|
\ - 110049 \nUnited States Delaware Delaware, USA (989) 474-4346\nOur team of\ |
|
\ over 250+ dedicated professionals works together to innovate, strategize, and\ |
|
\ implement transformative digital solutions for businesses across the world.\ |
|
\ Email: [email protected] / [email protected] or fill out our contact\ |
|
\ form -https://www.techchefz.digital/contact-us \nPhone no: +91 7428835009\n\ |
|
Social Media:\nLinkedin: www.linkedin.com/company/techchefzdigital/ \nInstagram:\ |
|
\ https://www.instagram.com/techchefz_digital/\nFacebook: https://www.facebook.com/profile.php?id=61562947256189\n\ |
|
Twitter: https://x.com/tcz_digital\nYoutube: https://youtube.com/@techchefzdigital?feature=shared\n\ |
|
Clutch.co: https://clutch.co/profile/tcz-digital-private \nMedium.com: https://medium.com/@TechchefzDigital\n\ |
|
Glassdoor: https://www.glassdoor.co.in/Reviews/TechChefz-Digital-Reviews-E3262688.htm\ |
|
\ \nGoodifrms: https://www.goodfirms.co/company/techchefz-digital \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ We provide\ |
|
\ a free consultation to understand your business needs and suggest solutions.\n\ |
|
We welcome collaborations, white-label partnerships, and outsourcing opportunities.\ |
|
\ Contact us to discuss potential synergies.We provide continuous monitoring,\ |
|
\ security updates, and optimization services for long-term business success.\n\ |
|
We build custom e-commerce solutions, including Shopify, Magento, WooCommerce,\ |
|
\ and headless commerce platforms with AI-driven recommendations.\nWe provide\ |
|
\ website revamps focused on performance, UI/UX, SEO optimization, and modern\ |
|
\ frameworks like React, Next.js, and Angular.\nSales process- \nOur sales process\ |
|
\ follows these five simple steps:\n1️⃣ Discovery Call – Understanding your business\ |
|
\ needs\n2️⃣ Proposal & Scope Definition – Defining objectives & deliverables\n\ |
|
3️⃣ Agreement & Onboarding – Finalizing contract & project plan\n4️⃣ Development\ |
|
\ & Execution – Delivering high-quality solutions\n5️⃣ Ongoing Support & Scaling\ |
|
\ – Continuous improvements & updates\n\[email protected] / [email protected]\ |
|
\ or fill out our contact form -https://www.techchefz.digital/contact-us \n\n\ |
|
Pricing structure: Contact us link: https://www.techchefz.digital/contact-us \n\ |
|
\ \n\n" |
|
- source_sentence: What generative AI solutions do you offer? |
|
sentences: |
|
- 'Strategy & Digital Transformation |
|
|
|
Digital Transformation Roadmap: Modernizing tech stacks, guiding businesses through |
|
their digital journey. |
|
|
|
Product Strategy: Crafting effective product strategies aligned with business |
|
goals. |
|
|
|
Customer Experience (CX) Optimization: Enhancing customer engagement with personalized |
|
experiences. |
|
|
|
Data Analytics: Leveraging data for business insights and better decision-making. |
|
|
|
Cloud Transformation: Transitioning to scalable and cost-efficient cloud solutions. |
|
|
|
|
|
Product Engineering & Custom Development |
|
|
|
Enterprise Web & Mobile Development: Tailored web and mobile apps for enterprises. |
|
|
|
Microservices & API Integration: Building scalable systems with microservices |
|
architecture and seamless API integrations. |
|
|
|
Quality Engineering: Ensuring optimal product performance through automated testing |
|
and quality assurance. |
|
|
|
Custom Software Development: Designing custom software solutions to meet unique |
|
business needs. |
|
|
|
|
|
Customer Experience & Marketing Technology |
|
|
|
Journey Mapping & Analytics: Understanding customer journeys to create targeted |
|
experiences. |
|
|
|
Content Architecture: Structuring content efficiently across multiple platforms. |
|
|
|
Personalization: Dynamic content and personalized engagement based on user behavior. |
|
|
|
Campaign Management: AI-driven automation for smarter, more effective campaigns. |
|
|
|
Conversion Rate Optimization (CRO): A/B testing, analytics, and optimization techniques |
|
to improve conversion rates. |
|
|
|
|
|
Enterprise Platforms & Systems Integration |
|
|
|
CMS Platform Selection & Integration: Implementing best-fit CMS solutions (including |
|
AEM). |
|
|
|
E-commerce Platforms: Implementing and optimizing e-commerce platforms like Magento, |
|
Shopify, and WooCommerce. |
|
|
|
Learning Management Systems (LMS): Integrating learning platforms that align with |
|
business goals. |
|
|
|
CRM & ERP System Integration: Seamless integration between enterprise systems |
|
like CRM (Salesforce, HubSpot) and ERP. |
|
|
|
Analytics, Data Science & Business Intelligence |
|
|
|
Predictive Analytics: Utilizing machine learning and predictive models to forecast |
|
trends and customer behavior. |
|
|
|
Business Intelligence (BI): Dashboards and tools to provide real-time business |
|
insights. |
|
|
|
Recommendation Engines: AI-based engines for product recommendations and content |
|
personalization. |
|
|
|
Intelligent Search & NLP: Enhancing search experiences using Natural Language |
|
Processing and machine learning algorithms. |
|
|
|
|
|
AI & Automation Solutions |
|
|
|
Generative AI: Creating content such as images, text, and videos using AI-driven |
|
models. |
|
|
|
AI-Powered Chatbots & Voice Assistants: Enhancing customer support and engagement |
|
through AI-driven conversational agents. |
|
|
|
Robotic Process Automation (RPA): Automating repetitive tasks and improving workflow |
|
efficiency. |
|
|
|
AI for Fraud Detection: Using AI to detect and prevent fraudulent activities within |
|
systems and transactions. |
|
|
|
|
|
Adobe Experience Manager (AEM) Solutions |
|
|
|
AEM Implementation & Customization: Full-service implementation, including setup, |
|
configuration, and custom development. |
|
|
|
Content Management: Streamlining content creation and management through AEM’s |
|
user-friendly interface. |
|
|
|
AEM Personalization: Delivering personalized digital experiences using AEM’s targeting |
|
and audience segmentation features. |
|
|
|
Multi-Site Management: Managing and scaling multiple websites and regions with |
|
AEM’s multi-site capabilities. |
|
|
|
AEM Integration: Integrating AEM with third-party platforms such as CRM, ERP, |
|
and e-commerce systems. |
|
|
|
AEM Migration: Helping businesses migrate from legacy CMS platforms to AEM seamlessly. |
|
|
|
AEM Support & Maintenance: Providing ongoing support and optimization for AEM |
|
environments. |
|
|
|
|
|
Cloud Services |
|
|
|
Cloud Strategy & Consulting: Helping businesses define and execute cloud adoption |
|
strategies. |
|
|
|
Cloud Migration: Smooth migration of business operations and applications to the |
|
cloud (AWS, Azure, GCP). |
|
|
|
Cloud Infrastructure Management: Managing and optimizing cloud infrastructure |
|
for efficiency and scalability. |
|
|
|
Cloud Security: Implementing security measures to protect cloud-hosted data and |
|
applications. |
|
|
|
|
|
E-Commerce Solutions |
|
|
|
Marketplace Development: Building scalable, multi-vendor marketplace platforms |
|
using technologies like Magento, Shopify Plus, and WooCommerce. |
|
|
|
Omnichannel Commerce: Integrating e-commerce platforms with physical and digital |
|
sales channels for seamless shopping experiences. |
|
|
|
AI-Powered Commerce: Leveraging AI for product recommendations, inventory management, |
|
and customer insights. |
|
|
|
|
|
UX/UI Design & User-Centered Development |
|
|
|
UI/UX Design: Creating intuitive, engaging interfaces that improve user experience |
|
across websites and apps. |
|
|
|
User Research & Testing: Understanding user behavior through research and testing |
|
to create optimal digital solutions. |
|
|
|
Prototyping & Wireframing: Designing interactive prototypes and wireframes to |
|
visualize digital products. |
|
|
|
' |
|
- "Yes! We are constantly looking for talented individuals. Check our Careers Page\ |
|
\ for openings.\nYou can submit your resume on our website or via our LinkedIn\ |
|
\ page.\nWe foster a people-centric, collaborative, and innovation-driven culture.\n\ |
|
Glassdoor: 4.3 + rating\n\nSharing Stories from Our Team\n\nDiscover firsthand\ |
|
\ experiences, growth journeys, and the vibrant culture that fuels our success.\n\ |
|
\nI have been a part of Techchefz for 3 years, and I can confidently say it's\ |
|
\ been a remarkable journey. From day one, I was welcomed into a vibrant community\ |
|
\ that values collaboration, creativity, and personal growth. The company culture\ |
|
\ here isn't just a buzzword, it's tangible in every interaction and initiative.\n\ |
|
profileImg\n\nAashish Massand\n\nSr. Manager Delivery\n\nTechChefz has been a\ |
|
\ transformative journey, equipping me with invaluable skills and fostering a\ |
|
\ supportive community. From coding fundamentals to advanced techniques, I've\ |
|
\ gained confidence and expertise. Grateful for this experience and opportunity.\n\ |
|
profileImg\n\nPankaj Datt\n\nAssociate Technology \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \n \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ Being a member of TechChefz's HR team is truly uplifting. The genuine\ |
|
\ positivity, motivation, and mentorship we share make each day uniquely rewarding.\ |
|
\ Fun is woven into the work culture, fostering authentic connections. I'm grateful\ |
|
\ for the authenticity and dynamism that make every day at TechChefz truly special.\n\ |
|
profileImg\n\nShreya Shukla\n\nHuman Resource Associate\n\nAdvancing from an initial\ |
|
\ team member to leading a new division, the opportunity to innovate and take\ |
|
\ risks drives my motivation. It's rare to find an organization that both nurtures\ |
|
\ passion and aligns with your mindset.\nprofileImg\n\nMohit Kumar\n\nLead - DevSecOps\n\ |
|
\nWorking at TechChefz has been an exceptional journey. The commitment to continuous\ |
|
\ learning and professional development is unparalleled, ensuring employees stay\ |
|
\ at the forefront of the tech industry. The leadership is forward-thinking, promoting\ |
|
\ transparency and a harmonious work-life balance.\nprofileImg\n\nHarprit Singh\ |
|
\ Kohli\n\nSr. Manager - Delivery" |
|
- "Global Universities: Multi-Brand, Multi-Locale, and Multilingual Digital Platform\n\ |
|
Industry: Higher Education\nPlatform: Web, Responsive\nTechnologies Used: AEM\ |
|
\ (Adobe Experience Manager), React JS\nServices Provided: Web Design, Content\ |
|
\ Management System (CMS)\nOverview:\nTechChefz Digital developed a robust, scalable,\ |
|
\ and efficient digital platform for Graphic Era University that caters to multiple\ |
|
\ campuses, languages, and regions. The project involved creating a multi-brand,\ |
|
\ multi-locale, and multilingual digital platform that ensured brand consistency\ |
|
\ and user satisfaction across all campuses.\nGoals & Objectives:\nMaximize Brand\ |
|
\ Consistency: Build a platform that maintains consistent branding across all\ |
|
\ locations and provides seamless navigation for users.\nImplement a Robust CMS:\ |
|
\ Leverage AEM as the Content Management System (CMS) to create reusable templates\ |
|
\ and components, enabling scalable content management for each campus.\nContent\ |
|
\ Automation: Introduce automation through React-based Global Variables dashboards\ |
|
\ to streamline content management, ensuring up-to-date and accurate information.\n\ |
|
System Integration: Integrate with Admission Automation, CRM, and ERP systems\ |
|
\ for smooth data flow and to enhance user experiences, boosting conversion rates.\n\ |
|
Challenges:\nEnsuring consistent branding across multiple campuses and locations.\n\ |
|
Creating a structured, easy-to-navigate website that works well for various types\ |
|
\ of users.\nManaging website content across multiple locations and ensuring localization\ |
|
\ without compromising the user experience.\nEnsuring accessibility compliance\ |
|
\ with ADA (Americans with Disabilities Act).\nSolutions:\nBuilt a digital platform\ |
|
\ on AEM with reusable components and templates.\nIntroduced Content Ops Automation\ |
|
\ using React-based dashboards to simplify content management.\nIntegrated with\ |
|
\ key systems (Admission, CRM, ERP) for a unified user experience.\nBusiness Impact:\n\ |
|
Customization of content and marketing strategies based on locales, languages,\ |
|
\ and markets.\nIncreased website traffic and user engagement by 2x.\nReduced\ |
|
\ website maintenance costs by 80% and optimized hosting.\n\nHousing Finance &\ |
|
\ Banking Firm: Revolutionizing Digital Experiences\nIndustry: Banking & Finance\n\ |
|
Platform: Web, Responsive\nServices Provided: Web Design, Content Management,\ |
|
\ Retail CMS\nOverview:\nTechChefz Digital worked with a leading Indian Mortgage\ |
|
\ Finance and Realty firm to create a seamless digital ecosystem for customer,\ |
|
\ partner, and internal stakeholder touchpoints. The focus was on making home\ |
|
\ loans paperless, enhancing customer engagement, and introducing AI-based recommendations\ |
|
\ to optimize user interactions.\nGoals & Objectives:\nBecome the top housing\ |
|
\ finance company in India by offering seamless online services.\nDigitize Home\ |
|
\ Loans and paperless processes for enhanced customer convenience.\nIntroduce\ |
|
\ AI to deliver personalized market data analysis and recommendations.\nImplement\ |
|
\ an omnichannel experience to provide a seamless journey for users across all\ |
|
\ touchpoints.\nChallenges:\nThe company lacked a digital presence and had only\ |
|
\ a static website.\nNeeded to build a digital ecosystem that integrates with\ |
|
\ existing banking systems.\nRequired a solution to enhance customer engagement\ |
|
\ without requiring physical branch visits.\nSolutions:\nDeveloped multi-regional\ |
|
\ corporate websites with language localization and analytics for enhanced user\ |
|
\ personalization.\nIntroduced AI-driven recommendations and paperless loan applications\ |
|
\ to streamline processes.\nBuilt internal portals and dashboards for efficient\ |
|
\ management of data and customer interactions.\nBusiness Impact:\nUnified technology\ |
|
\ and improved collaboration across teams (Sales, Marketing, and Branches).\n\ |
|
Enhanced customer retention by 4x.\nStreamlined data governance and compliance,\ |
|
\ ensuring 100% adherence to regulations.\n\nGlobal Automotive Brand: Transforming\ |
|
\ the Digital Ecosystem\nIndustry: Automotive/Manufacturing\nPlatform: Web, Responsive\n\ |
|
Technologies Used: AEM, Magento Commerce, React JS, Node JS, Python, MS-Azure,\ |
|
\ Kubernetes, Docker\nServices Provided: Web Design, Content Management, E-commerce\ |
|
\ Solutions, Microservices\nOverview:\nTechChefz Digital helped a global automotive\ |
|
\ brand develop a comprehensive digital ecosystem that spans multiple countries\ |
|
\ and business units. The platform provides services like motorcycle sales (new\ |
|
\ and pre-owned), accessories, apparel, service & repair, events, tours, and rentals.\n\ |
|
Goals & Objectives:\nEnhance Omni-Channel Growth and customer experience by unifying\ |
|
\ online and offline data for seamless interactions.\nImplement personalized content\ |
|
\ strategies and user-centric design to improve conversion rates and user engagement.\n\ |
|
Streamline technology across markets and ensure consistent brand messaging.\n\ |
|
Challenges:\nDecentralized digital interfaces prevented unified brand growth.\n\ |
|
Disconnected data between offline dealers and the online platform.\nDealers were\ |
|
\ isolated from the brand’s marketing strategy, leading to missed opportunities.\n\ |
|
Solutions:\nCreated a multi-locale, multilingual platform that integrates Dealer\ |
|
\ Management Systems (DMS), CRM, and other business applications.\nImplemented\ |
|
\ a scalable Adobe Experience Manager (AEM) platform with Magento Commerce for\ |
|
\ e-commerce.\nIntegrated online and offline data, including dealer and customer\ |
|
\ interactions, to drive personalized experiences.\nBusiness Impact:\nIncreased\ |
|
\ customer retention by 1.7x.\nEnhanced brand awareness by 192%.\nSupported operations\ |
|
\ in 35+ countries, enabling a consistent omnichannel experience across dealers,\ |
|
\ service centers, and distributors.\nWe cater to various industries, including\ |
|
\ finance, automotive, e-commerce, retail, healthcare, technology, Oil and gas\ |
|
\ industry, etc. \n" |
|
- source_sentence: What's it like working here? |
|
sentences: |
|
- 'Business Process Automation: LLM Powered Agents |
|
|
|
Overview: |
|
|
|
Our AI-powered agents are designed to automate complex, time-consuming business |
|
processes. By leveraging the latest technologies such as Langchain and MongoDB, |
|
these agents can handle a variety of tasks, including data collection and web |
|
navigation, all tailored to your specific business needs. |
|
|
|
How it works: |
|
|
|
AI Agents can be customized to automate business workflows. |
|
|
|
Use of Langchain ensures advanced capabilities for handling and processing web |
|
content and data. |
|
|
|
Integration with MongoDB enables efficient data storage and management. |
|
|
|
Impact: |
|
|
|
Significant time savings by automating repetitive tasks. |
|
|
|
Enhanced productivity, allowing employees to focus on higher-value work. |
|
|
|
Increased accuracy and reduction of human errors in critical processes. |
|
|
|
|
|
Customer Service: Sentiment Classification Using BERT |
|
|
|
Overview: |
|
|
|
This accelerator leverages Advanced AI and Hugging Face transformers to categorize |
|
customer reviews into positive, negative, or neutral sentiments. It helps businesses |
|
gain actionable insights into customer feedback by analyzing reviews, enabling |
|
companies to respond proactively to customer concerns and improve their offerings. |
|
|
|
How it works: |
|
|
|
BERT (Bidirectional Encoder Representations from Transformers) is fine-tuned to |
|
understand sentiment in customer feedback. |
|
|
|
The tool processes customer reviews, assigning sentiment categories that can help |
|
prioritize responses or improvements. |
|
|
|
The solution helps automate feedback analysis, improving the speed and accuracy |
|
of customer service interactions. |
|
|
|
Impact: |
|
|
|
Actionable insights for customer service teams to improve engagement and responses. |
|
|
|
Proactive improvements based on real-time feedback analysis. |
|
|
|
Enhanced customer experience by responding quickly and appropriately to customer |
|
sentiments. |
|
|
|
|
|
Artificial Intelligence: Fine-Tuning Large Language Models |
|
|
|
Overview: |
|
|
|
Large Language Models (LLMs), such as Mistral 7B, are at the forefront of AI innovation. |
|
In this accelerator, TechChefz Digital showcases its technical prowess by fine-tuning |
|
the Mistral 7B model on the VIGO dataset, which is an open-source dataset for |
|
training large-scale language models. |
|
|
|
How it works: |
|
|
|
We fine-tune Mistral 7B to improve its accuracy and relevancy based on specific |
|
datasets like VIGO. |
|
|
|
This allows the AI to be more context-aware and aligned with your particular business |
|
needs. |
|
|
|
Impact: |
|
|
|
Enhanced AI accuracy, enabling more effective AI-driven applications. |
|
|
|
Open-source innovation that leads to cost-effective AI solutions. |
|
|
|
Potential to integrate fine-tuned models into a range of industries like customer |
|
service, marketing, and automation. |
|
|
|
|
|
E-Commerce: Image Similarity Search |
|
|
|
Overview: |
|
|
|
In the e-commerce world, product discovery can be a challenge. Our AI-powered |
|
Image Similarity Search Accelerator revolutionizes product search by allowing |
|
customers to upload an image and instantly find matching or similar items. This |
|
tool enhances the shopping experience and drives higher engagement by enabling |
|
users to find products more efficiently. |
|
|
|
How it works: |
|
|
|
Customers upload an image of the product they are looking for. |
|
|
|
The AI model uses image recognition to search for visually similar products from |
|
the e-commerce site’s catalog. |
|
|
|
Product recommendations are delivered instantly based on visual matches. |
|
|
|
Impact: |
|
|
|
Improved user experience, reducing time spent searching for products. |
|
|
|
Higher conversion rates as customers can quickly find what they are looking for. |
|
|
|
Differentiation from competitors with advanced AI-powered product discovery features. |
|
|
|
|
|
Customer Service: RAG Chatbots |
|
|
|
Overview: |
|
|
|
RAG (Retrieval-Augmented Generation) chatbots are designed to provide timely and |
|
relevant responses to customer queries. By combining retrieval-based models with |
|
generative capabilities, these chatbots offer precise and contextually accurate |
|
answers. Our RAG-powered chatbots provide a more intelligent and tailored experience, |
|
making customer interactions smoother and more efficient. |
|
|
|
How it works: |
|
|
|
The chatbot first retrieves relevant data from a knowledge base or external sources. |
|
|
|
It then generates responses based on this data, ensuring that each answer is aligned |
|
with the user’s query. |
|
|
|
RAG technology ensures that chatbots provide relevant and up-to-date information. |
|
|
|
Impact: |
|
|
|
Enhanced customer satisfaction with more precise and relevant answers. |
|
|
|
24/7 support capabilities, improving overall customer service availability. |
|
|
|
Increased operational efficiency by automating customer interactions at scale. |
|
|
|
|
|
Request a Demo and Browse Accelerators: |
|
|
|
In our company, we offer you the opportunity to experience the power and potential |
|
of these accelerators first-hand. Whether you''re looking to streamline business |
|
processes, enhance customer service, or accelerate your e-commerce strategies, |
|
our solution accelerators are built to drive fast, impactful results. |
|
|
|
Get started today by requesting a demo or browsing through our accelerator offerings |
|
to discover the right tools that will transform your tech projects and accelerate |
|
your success. |
|
|
|
' |
|
- "Mayank Maggon – Founder, CEO & CTO\nMayank Maggon is the visionary leader of\ |
|
\ TechChefz Digital, responsible for driving the company's strategic direction.\ |
|
\ With over 15 years of experience in entrepreneurship and technology, Mayank\ |
|
\ has a deep understanding of AI, cloud technologies, and digital transformation.\ |
|
\ His leadership is centered on building a culture of innovation, operational\ |
|
\ excellence, and customer-first solutions.\nMayank holds a postgraduate certificate\ |
|
\ in Technology Leadership & Innovation from MIT and a postgraduate diploma in\ |
|
\ Sales & Marketing Communication from MICA, making him uniquely equipped to lead\ |
|
\ the company's growth in an ever-evolving digital ecosystem.\nLink: https://www.linkedin.com/in/mayankmaggon/\ |
|
\ \nOther Leadership Members:\nRahul Aggarwal – Senior Director, Technology: Rahul\ |
|
\ brings a wealth of technical expertise, overseeing the delivery of high-impact\ |
|
\ digital solutions.\nLink: https://www.linkedin.com/in/rahul-aggarwal-84288a59/\ |
|
\ \nAkshit Maggon – Associate Director, Delivery: Akshit is responsible for ensuring\ |
|
\ that projects are delivered on time, within scope, and meet the highest quality\ |
|
\ standards.\nLink: https://www.linkedin.com/in/akshit-maggon/ \nKunal Bhardwaj\ |
|
\ – Director, Technology: Kunal drives the company’s technical innovation and\ |
|
\ ensures that our solutions leverage the latest in AI, cloud, and digital technologies.\n\ |
|
Link: https://www.linkedin.com/in/kunal-bhardwaj-in/ \n" |
|
- "Yes! We are constantly looking for talented individuals. Check our Careers Page\ |
|
\ for openings.\nYou can submit your resume on our website or via our LinkedIn\ |
|
\ page.\nWe foster a people-centric, collaborative, and innovation-driven culture.\n\ |
|
Glassdoor: 4.3 + rating\n\nSharing Stories from Our Team\n\nDiscover firsthand\ |
|
\ experiences, growth journeys, and the vibrant culture that fuels our success.\n\ |
|
\nI have been a part of Techchefz for 3 years, and I can confidently say it's\ |
|
\ been a remarkable journey. From day one, I was welcomed into a vibrant community\ |
|
\ that values collaboration, creativity, and personal growth. The company culture\ |
|
\ here isn't just a buzzword, it's tangible in every interaction and initiative.\n\ |
|
profileImg\n\nAashish Massand\n\nSr. Manager Delivery\n\nTechChefz has been a\ |
|
\ transformative journey, equipping me with invaluable skills and fostering a\ |
|
\ supportive community. From coding fundamentals to advanced techniques, I've\ |
|
\ gained confidence and expertise. Grateful for this experience and opportunity.\n\ |
|
profileImg\n\nPankaj Datt\n\nAssociate Technology \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \n \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ \ |
|
\ Being a member of TechChefz's HR team is truly uplifting. The genuine\ |
|
\ positivity, motivation, and mentorship we share make each day uniquely rewarding.\ |
|
\ Fun is woven into the work culture, fostering authentic connections. I'm grateful\ |
|
\ for the authenticity and dynamism that make every day at TechChefz truly special.\n\ |
|
profileImg\n\nShreya Shukla\n\nHuman Resource Associate\n\nAdvancing from an initial\ |
|
\ team member to leading a new division, the opportunity to innovate and take\ |
|
\ risks drives my motivation. It's rare to find an organization that both nurtures\ |
|
\ passion and aligns with your mindset.\nprofileImg\n\nMohit Kumar\n\nLead - DevSecOps\n\ |
|
\nWorking at TechChefz has been an exceptional journey. The commitment to continuous\ |
|
\ learning and professional development is unparalleled, ensuring employees stay\ |
|
\ at the forefront of the tech industry. The leadership is forward-thinking, promoting\ |
|
\ transparency and a harmonious work-life balance.\nprofileImg\n\nHarprit Singh\ |
|
\ Kohli\n\nSr. Manager - Delivery" |
|
pipeline_tag: sentence-similarity |
|
library_name: sentence-transformers |
|
metrics: |
|
- cosine_accuracy@1 |
|
- cosine_accuracy@3 |
|
- cosine_accuracy@5 |
|
- cosine_accuracy@10 |
|
- cosine_precision@1 |
|
- cosine_precision@3 |
|
- cosine_precision@5 |
|
- cosine_precision@10 |
|
- cosine_recall@1 |
|
- cosine_recall@3 |
|
- cosine_recall@5 |
|
- cosine_recall@10 |
|
- cosine_ndcg@10 |
|
- cosine_mrr@10 |
|
- cosine_map@100 |
|
model-index: |
|
- name: BGE base Financial Matryoshka |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.0 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.375 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.875 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.0 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.125 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08750000000000001 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.0 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.375 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.875 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.36914698568341187 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.21646825396825395 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2234126984126984 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.0 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.375 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.875 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.0 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.125 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08750000000000001 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.0 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.375 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.875 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.37312930837000663 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.22132936507936507 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.2296626984126984 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.0 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.375 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.375 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.875 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.0 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.125 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.07500000000000001 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08750000000000001 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.0 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.375 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.375 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.875 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.37583197830566967 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.22738095238095235 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.23779761904761904 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.125 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.375 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.375 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.875 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.125 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.125 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.07500000000000001 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08750000000000001 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.125 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.375 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.375 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.875 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.4249570514457608 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.2926587301587301 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.30227411477411475 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.0 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.375 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.5 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.625 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.0 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.125 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.1 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0625 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.0 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.375 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.5 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.625 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.3157336748187052 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.2157738095238095 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.24797077922077923 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# BGE base Financial Matryoshka |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
- **Model Type:** Sentence Transformer |
|
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a --> |
|
- **Maximum Sequence Length:** 512 tokens |
|
- **Output Dimensionality:** 768 dimensions |
|
- **Similarity Function:** Cosine Similarity |
|
<!-- - **Training Dataset:** Unknown --> |
|
- **Language:** en |
|
- **License:** apache-2.0 |
|
|
|
### Model Sources |
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
|
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
|
### Full Model Architecture |
|
|
|
``` |
|
SentenceTransformer( |
|
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
(2): Normalize() |
|
) |
|
``` |
|
|
|
## Usage |
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
First install the Sentence Transformers library: |
|
|
|
```bash |
|
pip install -U sentence-transformers |
|
``` |
|
|
|
Then you can load this model and run inference. |
|
```python |
|
from sentence_transformers import SentenceTransformer |
|
|
|
# Download from the 🤗 Hub |
|
model = SentenceTransformer("Shashwat13333/bge-base-en-v1.5_v4") |
|
# Run inference |
|
sentences = [ |
|
"What's it like working here?", |
|
"Yes! We are constantly looking for talented individuals. Check our Careers Page for openings.\nYou can submit your resume on our website or via our LinkedIn page.\nWe foster a people-centric, collaborative, and innovation-driven culture.\nGlassdoor: 4.3 + rating\n\nSharing Stories from Our Team\n\nDiscover firsthand experiences, growth journeys, and the vibrant culture that fuels our success.\n\nI have been a part of Techchefz for 3 years, and I can confidently say it's been a remarkable journey. From day one, I was welcomed into a vibrant community that values collaboration, creativity, and personal growth. The company culture here isn't just a buzzword, it's tangible in every interaction and initiative.\nprofileImg\n\nAashish Massand\n\nSr. Manager Delivery\n\nTechChefz has been a transformative journey, equipping me with invaluable skills and fostering a supportive community. From coding fundamentals to advanced techniques, I've gained confidence and expertise. Grateful for this experience and opportunity.\nprofileImg\n\nPankaj Datt\n\nAssociate Technology \n Being a member of TechChefz's HR team is truly uplifting. The genuine positivity, motivation, and mentorship we share make each day uniquely rewarding. Fun is woven into the work culture, fostering authentic connections. I'm grateful for the authenticity and dynamism that make every day at TechChefz truly special.\nprofileImg\n\nShreya Shukla\n\nHuman Resource Associate\n\nAdvancing from an initial team member to leading a new division, the opportunity to innovate and take risks drives my motivation. It's rare to find an organization that both nurtures passion and aligns with your mindset.\nprofileImg\n\nMohit Kumar\n\nLead - DevSecOps\n\nWorking at TechChefz has been an exceptional journey. The commitment to continuous learning and professional development is unparalleled, ensuring employees stay at the forefront of the tech industry. The leadership is forward-thinking, promoting transparency and a harmonious work-life balance.\nprofileImg\n\nHarprit Singh Kohli\n\nSr. Manager - Delivery", |
|
"Business Process Automation: LLM Powered Agents\nOverview:\nOur AI-powered agents are designed to automate complex, time-consuming business processes. By leveraging the latest technologies such as Langchain and MongoDB, these agents can handle a variety of tasks, including data collection and web navigation, all tailored to your specific business needs.\nHow it works:\nAI Agents can be customized to automate business workflows.\nUse of Langchain ensures advanced capabilities for handling and processing web content and data.\nIntegration with MongoDB enables efficient data storage and management.\nImpact:\nSignificant time savings by automating repetitive tasks.\nEnhanced productivity, allowing employees to focus on higher-value work.\nIncreased accuracy and reduction of human errors in critical processes.\n\nCustomer Service: Sentiment Classification Using BERT\nOverview:\nThis accelerator leverages Advanced AI and Hugging Face transformers to categorize customer reviews into positive, negative, or neutral sentiments. It helps businesses gain actionable insights into customer feedback by analyzing reviews, enabling companies to respond proactively to customer concerns and improve their offerings.\nHow it works:\nBERT (Bidirectional Encoder Representations from Transformers) is fine-tuned to understand sentiment in customer feedback.\nThe tool processes customer reviews, assigning sentiment categories that can help prioritize responses or improvements.\nThe solution helps automate feedback analysis, improving the speed and accuracy of customer service interactions.\nImpact:\nActionable insights for customer service teams to improve engagement and responses.\nProactive improvements based on real-time feedback analysis.\nEnhanced customer experience by responding quickly and appropriately to customer sentiments.\n\nArtificial Intelligence: Fine-Tuning Large Language Models\nOverview:\nLarge Language Models (LLMs), such as Mistral 7B, are at the forefront of AI innovation. In this accelerator, TechChefz Digital showcases its technical prowess by fine-tuning the Mistral 7B model on the VIGO dataset, which is an open-source dataset for training large-scale language models.\nHow it works:\nWe fine-tune Mistral 7B to improve its accuracy and relevancy based on specific datasets like VIGO.\nThis allows the AI to be more context-aware and aligned with your particular business needs.\nImpact:\nEnhanced AI accuracy, enabling more effective AI-driven applications.\nOpen-source innovation that leads to cost-effective AI solutions.\nPotential to integrate fine-tuned models into a range of industries like customer service, marketing, and automation.\n\nE-Commerce: Image Similarity Search\nOverview:\nIn the e-commerce world, product discovery can be a challenge. Our AI-powered Image Similarity Search Accelerator revolutionizes product search by allowing customers to upload an image and instantly find matching or similar items. This tool enhances the shopping experience and drives higher engagement by enabling users to find products more efficiently.\nHow it works:\nCustomers upload an image of the product they are looking for.\nThe AI model uses image recognition to search for visually similar products from the e-commerce site’s catalog.\nProduct recommendations are delivered instantly based on visual matches.\nImpact:\nImproved user experience, reducing time spent searching for products.\nHigher conversion rates as customers can quickly find what they are looking for.\nDifferentiation from competitors with advanced AI-powered product discovery features.\n\nCustomer Service: RAG Chatbots\nOverview:\nRAG (Retrieval-Augmented Generation) chatbots are designed to provide timely and relevant responses to customer queries. By combining retrieval-based models with generative capabilities, these chatbots offer precise and contextually accurate answers. Our RAG-powered chatbots provide a more intelligent and tailored experience, making customer interactions smoother and more efficient.\nHow it works:\nThe chatbot first retrieves relevant data from a knowledge base or external sources.\nIt then generates responses based on this data, ensuring that each answer is aligned with the user’s query.\nRAG technology ensures that chatbots provide relevant and up-to-date information.\nImpact:\nEnhanced customer satisfaction with more precise and relevant answers.\n24/7 support capabilities, improving overall customer service availability.\nIncreased operational efficiency by automating customer interactions at scale.\n\nRequest a Demo and Browse Accelerators:\nIn our company, we offer you the opportunity to experience the power and potential of these accelerators first-hand. Whether you're looking to streamline business processes, enhance customer service, or accelerate your e-commerce strategies, our solution accelerators are built to drive fast, impactful results.\nGet started today by requesting a demo or browsing through our accelerator offerings to discover the right tools that will transform your tech projects and accelerate your success.\n", |
|
] |
|
embeddings = model.encode(sentences) |
|
print(embeddings.shape) |
|
# [3, 768] |
|
|
|
# Get the similarity scores for the embeddings |
|
similarities = model.similarity(embeddings, embeddings) |
|
print(similarities.shape) |
|
# [3, 3] |
|
``` |
|
|
|
<!-- |
|
### Direct Usage (Transformers) |
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
</details> |
|
--> |
|
|
|
<!-- |
|
### Downstream Usage (Sentence Transformers) |
|
|
|
You can finetune this model on your own dataset. |
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
</details> |
|
--> |
|
|
|
<!-- |
|
### Out-of-Scope Use |
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
--> |
|
|
|
## Evaluation |
|
|
|
### Metrics |
|
|
|
#### Information Retrieval |
|
|
|
* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64` |
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
|
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 | |
|
|:--------------------|:-----------|:-----------|:-----------|:----------|:-----------| |
|
| cosine_accuracy@1 | 0.0 | 0.0 | 0.0 | 0.125 | 0.0 | |
|
| cosine_accuracy@3 | 0.375 | 0.375 | 0.375 | 0.375 | 0.375 | |
|
| cosine_accuracy@5 | 0.5 | 0.5 | 0.375 | 0.375 | 0.5 | |
|
| cosine_accuracy@10 | 0.875 | 0.875 | 0.875 | 0.875 | 0.625 | |
|
| cosine_precision@1 | 0.0 | 0.0 | 0.0 | 0.125 | 0.0 | |
|
| cosine_precision@3 | 0.125 | 0.125 | 0.125 | 0.125 | 0.125 | |
|
| cosine_precision@5 | 0.1 | 0.1 | 0.075 | 0.075 | 0.1 | |
|
| cosine_precision@10 | 0.0875 | 0.0875 | 0.0875 | 0.0875 | 0.0625 | |
|
| cosine_recall@1 | 0.0 | 0.0 | 0.0 | 0.125 | 0.0 | |
|
| cosine_recall@3 | 0.375 | 0.375 | 0.375 | 0.375 | 0.375 | |
|
| cosine_recall@5 | 0.5 | 0.5 | 0.375 | 0.375 | 0.5 | |
|
| cosine_recall@10 | 0.875 | 0.875 | 0.875 | 0.875 | 0.625 | |
|
| **cosine_ndcg@10** | **0.3691** | **0.3731** | **0.3758** | **0.425** | **0.3157** | |
|
| cosine_mrr@10 | 0.2165 | 0.2213 | 0.2274 | 0.2927 | 0.2158 | |
|
| cosine_map@100 | 0.2234 | 0.2297 | 0.2378 | 0.3023 | 0.248 | |
|
|
|
<!-- |
|
## Bias, Risks and Limitations |
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
--> |
|
|
|
<!-- |
|
### Recommendations |
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
--> |
|
|
|
## Training Details |
|
|
|
### Training Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
* Size: 16 training samples |
|
* Columns: <code>anchor</code> and <code>positive</code> |
|
* Approximate statistics based on the first 16 samples: |
|
| | anchor | positive | |
|
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------| |
|
| type | string | string | |
|
| details | <ul><li>min: 8 tokens</li><li>mean: 11.12 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 332 tokens</li><li>mean: 479.62 tokens</li><li>max: 512 tokens</li></ul> | |
|
* Samples: |
|
| anchor | positive | |
|
|:----------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
| <code>What e-commerce platforms do you develop on?</code> | <code>Web & Mobile Development<br>Frontend Development:<br>HTML5: Markup language for structuring web content.<br>CSS/JS: Styling and interactivity for dynamic user experiences.<br>React JS: JavaScript library for building user interfaces with a component-based approach.<br>Angular JS: JavaScript framework for developing dynamic, single-page applications (SPAs).<br>Vue JS: Progressive JavaScript framework for building user interfaces and SPAs.<br>Next JS: React-based framework for server-side rendering and static website generation.<br>Mobile Development:<br>React Native: Framework for building native mobile applications using React.<br>Flutter: UI toolkit for building natively compiled applications for mobile, web, and desktop from a single codebase.<br>Backend Development:<br>Node JS: JavaScript runtime for building scalable backend services.<br>Python: High-level programming language used for backend services, machine learning, and data science.<br>Frappe: Full-stack web application framework based on Python and JavaScript.<br>Java:...</code> | |
|
| <code>Do you have any job openings right now?</code> | <code>Yes! We are constantly looking for talented individuals. Check our Careers Page for openings.<br>You can submit your resume on our website or via our LinkedIn page.<br>We foster a people-centric, collaborative, and innovation-driven culture.<br>Glassdoor: 4.3 + rating<br><br>Sharing Stories from Our Team<br><br>Discover firsthand experiences, growth journeys, and the vibrant culture that fuels our success.<br><br>I have been a part of Techchefz for 3 years, and I can confidently say it's been a remarkable journey. From day one, I was welcomed into a vibrant community that values collaboration, creativity, and personal growth. The company culture here isn't just a buzzword, it's tangible in every interaction and initiative.<br>profileImg<br><br>Aashish Massand<br><br>Sr. Manager Delivery<br><br>TechChefz has been a transformative journey, equipping me with invaluable skills and fostering a supportive community. From coding fundamentals to advanced techniques, I've gained confidence and expertise. Grateful for this experience and oppo...</code> | |
|
| <code>What does the CEO of your company do?</code> | <code>Mayank Maggon – Founder, CEO & CTO<br>Mayank Maggon is the visionary leader of TechChefz Digital, responsible for driving the company's strategic direction. With over 15 years of experience in entrepreneurship and technology, Mayank has a deep understanding of AI, cloud technologies, and digital transformation. His leadership is centered on building a culture of innovation, operational excellence, and customer-first solutions.<br>Mayank holds a postgraduate certificate in Technology Leadership & Innovation from MIT and a postgraduate diploma in Sales & Marketing Communication from MICA, making him uniquely equipped to lead the company's growth in an ever-evolving digital ecosystem.<br>Link: https://www.linkedin.com/in/mayankmaggon/ <br>Other Leadership Members:<br>Rahul Aggarwal – Senior Director, Technology: Rahul brings a wealth of technical expertise, overseeing the delivery of high-impact digital solutions.<br>Link: https://www.linkedin.com/in/rahul-aggarwal-84288a59/ <br>Akshit Maggon – Associate Dire...</code> | |
|
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: |
|
```json |
|
{ |
|
"loss": "MultipleNegativesRankingLoss", |
|
"matryoshka_dims": [ |
|
768, |
|
512, |
|
256, |
|
128, |
|
64 |
|
], |
|
"matryoshka_weights": [ |
|
1, |
|
1, |
|
1, |
|
1, |
|
1 |
|
], |
|
"n_dims_per_step": -1 |
|
} |
|
``` |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `eval_strategy`: epoch |
|
- `gradient_accumulation_steps`: 4 |
|
- `learning_rate`: 1e-05 |
|
- `weight_decay`: 0.01 |
|
- `num_train_epochs`: 4 |
|
- `lr_scheduler_type`: cosine |
|
- `warmup_ratio`: 0.1 |
|
- `fp16`: True |
|
- `load_best_model_at_end`: True |
|
- `optim`: adamw_torch_fused |
|
- `push_to_hub`: True |
|
- `hub_model_id`: Shashwat13333/bge-base-en-v1.5_v4 |
|
- `push_to_hub_model_id`: bge-base-en-v1.5_v4 |
|
- `batch_sampler`: no_duplicates |
|
|
|
#### All Hyperparameters |
|
<details><summary>Click to expand</summary> |
|
|
|
- `overwrite_output_dir`: False |
|
- `do_predict`: False |
|
- `eval_strategy`: epoch |
|
- `prediction_loss_only`: True |
|
- `per_device_train_batch_size`: 8 |
|
- `per_device_eval_batch_size`: 8 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 4 |
|
- `eval_accumulation_steps`: None |
|
- `torch_empty_cache_steps`: None |
|
- `learning_rate`: 1e-05 |
|
- `weight_decay`: 0.01 |
|
- `adam_beta1`: 0.9 |
|
- `adam_beta2`: 0.999 |
|
- `adam_epsilon`: 1e-08 |
|
- `max_grad_norm`: 1.0 |
|
- `num_train_epochs`: 4 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: cosine |
|
- `lr_scheduler_kwargs`: {} |
|
- `warmup_ratio`: 0.1 |
|
- `warmup_steps`: 0 |
|
- `log_level`: passive |
|
- `log_level_replica`: warning |
|
- `log_on_each_node`: True |
|
- `logging_nan_inf_filter`: True |
|
- `save_safetensors`: True |
|
- `save_on_each_node`: False |
|
- `save_only_model`: False |
|
- `restore_callback_states_from_checkpoint`: False |
|
- `no_cuda`: False |
|
- `use_cpu`: False |
|
- `use_mps_device`: False |
|
- `seed`: 42 |
|
- `data_seed`: None |
|
- `jit_mode_eval`: False |
|
- `use_ipex`: False |
|
- `bf16`: False |
|
- `fp16`: True |
|
- `fp16_opt_level`: O1 |
|
- `half_precision_backend`: auto |
|
- `bf16_full_eval`: False |
|
- `fp16_full_eval`: False |
|
- `tf32`: None |
|
- `local_rank`: 0 |
|
- `ddp_backend`: None |
|
- `tpu_num_cores`: None |
|
- `tpu_metrics_debug`: False |
|
- `debug`: [] |
|
- `dataloader_drop_last`: False |
|
- `dataloader_num_workers`: 0 |
|
- `dataloader_prefetch_factor`: None |
|
- `past_index`: -1 |
|
- `disable_tqdm`: False |
|
- `remove_unused_columns`: True |
|
- `label_names`: None |
|
- `load_best_model_at_end`: True |
|
- `ignore_data_skip`: False |
|
- `fsdp`: [] |
|
- `fsdp_min_num_params`: 0 |
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
- `deepspeed`: None |
|
- `label_smoothing_factor`: 0.0 |
|
- `optim`: adamw_torch_fused |
|
- `optim_args`: None |
|
- `adafactor`: False |
|
- `group_by_length`: False |
|
- `length_column_name`: length |
|
- `ddp_find_unused_parameters`: None |
|
- `ddp_bucket_cap_mb`: None |
|
- `ddp_broadcast_buffers`: False |
|
- `dataloader_pin_memory`: True |
|
- `dataloader_persistent_workers`: False |
|
- `skip_memory_metrics`: True |
|
- `use_legacy_prediction_loop`: False |
|
- `push_to_hub`: True |
|
- `resume_from_checkpoint`: None |
|
- `hub_model_id`: Shashwat13333/bge-base-en-v1.5_v4 |
|
- `hub_strategy`: every_save |
|
- `hub_private_repo`: None |
|
- `hub_always_push`: False |
|
- `gradient_checkpointing`: False |
|
- `gradient_checkpointing_kwargs`: None |
|
- `include_inputs_for_metrics`: False |
|
- `include_for_metrics`: [] |
|
- `eval_do_concat_batches`: True |
|
- `fp16_backend`: auto |
|
- `push_to_hub_model_id`: bge-base-en-v1.5_v4 |
|
- `push_to_hub_organization`: None |
|
- `mp_parameters`: |
|
- `auto_find_batch_size`: False |
|
- `full_determinism`: False |
|
- `torchdynamo`: None |
|
- `ray_scope`: last |
|
- `ddp_timeout`: 1800 |
|
- `torch_compile`: False |
|
- `torch_compile_backend`: None |
|
- `torch_compile_mode`: None |
|
- `dispatch_batches`: None |
|
- `split_batches`: None |
|
- `include_tokens_per_second`: False |
|
- `include_num_input_tokens_seen`: False |
|
- `neftune_noise_alpha`: None |
|
- `optim_target_modules`: None |
|
- `batch_eval_metrics`: False |
|
- `eval_on_start`: False |
|
- `use_liger_kernel`: False |
|
- `eval_use_gather_object`: False |
|
- `average_tokens_across_devices`: False |
|
- `prompts`: None |
|
- `batch_sampler`: no_duplicates |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |
|
|:-------:|:-----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
|
| **1.0** | **1** | **13.1742** | **0.3388** | **0.4638** | **0.2489** | **0.3873** | **0.2666** | |
|
| 2.0 | 2 | - | 0.4500 | 0.4278 | 0.2872 | 0.4212 | 0.3400 | |
|
| 3.0 | 3 | - | 0.3936 | 0.3370 | 0.3036 | 0.3289 | 0.4710 | |
|
| 4.0 | 4 | - | 0.3691 | 0.3731 | 0.3758 | 0.4250 | 0.3157 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### Framework Versions |
|
- Python: 3.11.11 |
|
- Sentence Transformers: 3.4.1 |
|
- Transformers: 4.48.3 |
|
- PyTorch: 2.5.1+cu124 |
|
- Accelerate: 1.3.0 |
|
- Datasets: 3.3.1 |
|
- Tokenizers: 0.21.0 |
|
|
|
## Citation |
|
|
|
### BibTeX |
|
|
|
#### Sentence Transformers |
|
```bibtex |
|
@inproceedings{reimers-2019-sentence-bert, |
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
month = "11", |
|
year = "2019", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://arxiv.org/abs/1908.10084", |
|
} |
|
``` |
|
|
|
#### MatryoshkaLoss |
|
```bibtex |
|
@misc{kusupati2024matryoshka, |
|
title={Matryoshka Representation Learning}, |
|
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, |
|
year={2024}, |
|
eprint={2205.13147}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.LG} |
|
} |
|
``` |
|
|
|
#### MultipleNegativesRankingLoss |
|
```bibtex |
|
@misc{henderson2017efficient, |
|
title={Efficient Natural Language Response Suggestion for Smart Reply}, |
|
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, |
|
year={2017}, |
|
eprint={1705.00652}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL} |
|
} |
|
``` |
|
|
|
<!-- |
|
## Glossary |
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Authors |
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Contact |
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
--> |
